Long-short term memory
Contents
# Install the necessary dependencies
import os
import sys
!{sys.executable} -m pip install --quiet pandas scikit-learn numpy matplotlib jupyterlab_myst ipython
24.1.1. Long-short term memory#
As we have learned the normal RNNs on the previous lessons, today we are going to use long-short term memory (LSTM) to fix the problems that are induced from the RNN architecture.
The vanilla LSTM is proposed in 2005, the paper is Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition, and after that, a lot of paper based on it appeared.
from IPython.display import HTML
display(HTML("""
<p style="text-align: center;">
<iframe src="https://static-1300131294.cos.ap-shanghai.myqcloud.com/html/rnn-vis/index.html" width="100%" height="250px;"
style="border:none;" scrolling="auto"></iframe>
A demo of advanced RNNs. <a
href="https://distill.pub/2019/memorization-in-rnns/"> [source]</a>
</p>
"""))
A demo of advanced RNNs. [source]
24.1.1.1. Overview#
The essential problems of RNN are vanishing/exploding gradient problems. The gradient vanishing/exploding problem is a common issue in training deep neural networks. This problem occurs when the gradient of the loss function with respect to the weights of the network becomes very small or very large.
There are several possibilities will bring on this kind of problem, for example:
a poor choice of hyper-parameters
a poor architecture,
a bug in the code.
Luckily, LSTM can use a memory cell for modeling long-range dependencies and avoid vanishing/exploding gradient problems.
First, let’s see the architecture of LSTM cell.
It looks like the cell of RNN, but there are still some differences between them. The same part is the direction of data, one input and two outputs. However, the LSTM cell adds a cell state \(c^{<t>}\), which updates with the time. \(c^{<t-1>}\) means cell state at previous time step and \(c^{<t-1>}\) means cell state at current time step. The \(h^{t}\) is still the activation.
24.1.1.2. Special Gates#
Then, we take a look at the inside of cell. \(\bigodot\) means element-wise multiplication operator, \(\bigoplus\) means element-wise addition operator and \(\sigma\) means logistic sigmoid activation functions.
Now, we should pay attention to ‘Gates’.
The first is ‘Forget Gate’ \(f\), and it controls which information is remembered, and which is forgotten; can reset the cell state. This function can be written as \(f_t = \sigma (W_{fx}x^{<t>} + W_{fh}h^{<t-1>} + b_f)\)
Next, ‘Input Gate’ is \(i_t = \sigma(W_{ix}x^{<t>} + W_{ih}h^{<t-1>} + b_i)\) and ‘Input Node’ is \(g_t = tanh(W_{gt}x^{<t>} + W_{gh}x^{<t-1>} + b_g)\).
To brief summarize the previous gates in an expression: \(C^{<t>} = (C^{<t-1>} \bigodot f_t) \bigoplus (i_t \bigodot g_t)\). Since \(i_t\) is ‘Input Gate’ and \(g_t\) is ‘Input Gate’, \((i_t \bigodot g_t)\) is for updatting the cell state.
Finally, ‘Output Gate’ is for updating the values of hidden units: \(o_t = \sigma(W_{ox}x^{<t>} + W_{oh}x^{<t-1>} + b_o)\). So the activateion of the current time is \(h^{<t>} = o_t \bigodot tanh(C^{<t>})\).
24.1.1.2.1. Code#
Here we implement an LSTM model on all a data set of Shakespeare works.
import os
import re
import string
import requests
import numpy as np
import collections
import random
import pickle
import matplotlib.pyplot as plt
import tensorflow as tf
from tensorflow.python.framework import ops
ops.reset_default_graph()
tf.config.run_functions_eagerly(True)
Set RNN Parameters.
min_word_freq = 5 # Trim the less frequent words off
rnn_size = 128 # RNN Model size
epochs = 10 # Number of epochs to cycle through data
batch_size = 100 # Train on this many examples at once
learning_rate = 0.001 # Learning rate
training_seq_len = 50 # how long of a word group to consider
embedding_size = rnn_size # Word embedding size
save_every = 500 # How often to save model checkpoints
eval_every = 50 # How often to evaluate the test sentences
prime_texts = ['thou art more', 'to be or not to', 'wherefore art thou']
Download/store Shakespeare data.
data_dir = 'tmp'
data_file = 'shakespeare.txt'
model_path = 'shakespeare_model'
full_model_dir = os.path.join(data_dir, model_path)
Declare punctuation to remove, everything except hyphens and apostrophes.
punctuation = string.punctuation
punctuation = ''.join([x for x in punctuation if x not in ['-', "'"]])
Make Model Directory.
if not os.path.exists(full_model_dir):
os.makedirs(full_model_dir)
Make data directory.
if not os.path.exists(data_dir):
os.makedirs(data_dir)
print('Loading Shakespeare Data')
Loading Shakespeare Data
Check if file is downloaded.
if not os.path.isfile(os.path.join(data_dir, data_file)):
print('Not found, downloading Shakespeare texts from www.gutenberg.org')
shakespeare_url = 'http://www.gutenberg.org/cache/epub/100/pg100.txt'
# Get Shakespeare text
response = requests.get(shakespeare_url)
shakespeare_file = response.content
# Decode binary into string
s_text = shakespeare_file.decode('utf-8')
# Drop first few descriptive paragraphs.
s_text = s_text[7675:]
# Remove newlines
s_text = s_text.replace('\r\n', '')
s_text = s_text.replace('\n', '')
# Write to file
with open(os.path.join(data_dir, data_file), 'w') as out_conn:
out_conn.write(s_text)
else:
# If file has been saved, load from that file
with open(os.path.join(data_dir, data_file), 'r') as file_conn:
s_text = file_conn.read().replace('\n', '')
Clean text.
print('Cleaning Text')
s_text = re.sub(r'[{}]'.format(punctuation), ' ', s_text)
s_text = re.sub('\s+', ' ', s_text).strip().lower()
Cleaning Text
Build word vocabulary function.
def build_vocab(text, min_freq):
word_counts = collections.Counter(text.split(' '))
# limit word counts to those more frequent than cutoff
word_counts = {key: val for key, val in word_counts.items() if val > min_freq}
# Create vocab --> index mapping
words = word_counts.keys()
vocab_to_ix_dict = {key: (i_x+1) for i_x, key in enumerate(words)}
# Add unknown key --> 0 index
vocab_to_ix_dict['unknown'] = 0
# Create index --> vocab mapping
ix_to_vocab_dict = {val: key for key, val in vocab_to_ix_dict.items()}
return ix_to_vocab_dict, vocab_to_ix_dict
Build Shakespeare vocabulary.
print('Building Shakespeare Vocab')
ix2vocab, vocab2ix = build_vocab(s_text, min_word_freq)
vocab_size = len(ix2vocab) + 1
print('Vocabulary Length = {}'.format(vocab_size))
Building Shakespeare Vocab
Vocabulary Length = 8286
Sanity Check.
assert(len(ix2vocab) == len(vocab2ix))
Convert text to word vectors.
s_text_words = s_text.split(' ')
s_text_ix = []
for ix, x in enumerate(s_text_words):
try:
s_text_ix.append(vocab2ix[x])
except KeyError:
s_text_ix.append(0)
s_text_ix = np.array(s_text_ix)
Define LSTM RNN Model.
class LSTM_Model(tf.keras.Model):
def __init__(self, embedding_size, rnn_size, batch_size, learning_rate,
training_seq_len, vocab_size, infer_sample=False):
super(LSTM_Model, self).__init__()
self.embedding_size = embedding_size
self.rnn_size = rnn_size
self.vocab_size = vocab_size
self.infer_sample = infer_sample
self.learning_rate = learning_rate
if infer_sample:
self.batch_size = 1
self.training_seq_len = 1
else:
self.batch_size = batch_size
self.training_seq_len = training_seq_len
self.lstm = tf.keras.layers.LSTM(self.rnn_size, return_sequences=True, return_state=True)
self.x_data = tf.keras.layers.Input(shape=(self.training_seq_len,), dtype=tf.int32)
self.y_output = tf.keras.layers.Input(shape=(self.training_seq_len,), dtype=tf.int32)
# Softmax Output Weights
self.W = tf.Variable(tf.random.normal([self.rnn_size, self.vocab_size]), name='W')
self.b = tf.Variable(tf.zeros([self.vocab_size]), name='b')
# Define Embedding
self.embedding_mat = tf.Variable(tf.random.normal([self.vocab_size, self.embedding_size]), name='embedding_mat')
embedding_output = tf.nn.embedding_lookup(self.embedding_mat, self.x_data)
outputs, last_state, _ = self.lstm(embedding_output)
# Non inferred outputs
output = tf.reshape(tf.concat(axis=1, values=outputs), [-1, self.rnn_size])
# Logits and output
self.logit_output = tf.matmul(output, self.W) + self.b
self.model_output = tf.nn.softmax(self.logit_output)
loss_fun = tf.keras.losses.sparse_categorical_crossentropy
loss = loss_fun(tf.reshape(self.y_output, [-1]), self.logit_output)
self.cost = tf.reduce_sum(loss) / (self.batch_size * self.training_seq_len)
self.final_state = last_state
optimizer = tf.keras.optimizers.Adam(self.learning_rate)
@tf.function
def train_step(x, y,state):
with tf.GradientTape() as tape:
embedding_output = tf.nn.embedding_lookup(self.embedding_mat, x)
outputs, last_state, _ = self.lstm(embedding_output,initial_state=state)
output = tf.reshape(tf.concat(axis=1, values=outputs), [-1, self.rnn_size])
logit_output = tf.matmul(output, self.W) + self.b
cost = tf.reduce_sum(loss_fun(tf.reshape(y, [-1]), logit_output)) / (self.batch_size * self.training_seq_len)
trainable_variables = self.trainable_variables
gradients = tape.gradient(cost, trainable_variables)
optimizer.apply_gradients(zip(gradients, trainable_variables))
return cost
self.train_op = train_step
def call(self, x, initial_state):
embedding_output = tf.nn.embedding_lookup(self.embedding_mat, x)
lstm_output, final_state_h, final_state_c = self.lstm(embedding_output, initial_state=initial_state)
output = tf.reshape(tf.concat(axis=1, values=lstm_output), [-1, self.rnn_size])
logit_output = tf.matmul(output, self.W) + self.b
model_output = tf.nn.softmax(logit_output)
return model_output, (final_state_h, final_state_c)
def loss(self, targets, logits):
loss_fun = tf.keras.losses.sparse_categorical_crossentropy
loss = loss_fun(targets, logits)
return tf.reduce_mean(loss)
def get_initial_state(self, batch_size):
return [tf.zeros((batch_size, self.lstm.units)) for i in range(2)]
def sample(self, words=ix2vocab, vocab=vocab2ix, num=10, prime_text='art'):
state = [tf.zeros([1, self.rnn_size]), tf.zeros([1, self.rnn_size])]
word_list = prime_text.split()
for word in word_list[:-1]:
print(word)
#x = tf.expand_dims(vocab[word], axis=0)
x = np.zeros((1, 1))
x[0, 0] = vocab[word]
x = tf.cast(x, tf.int32)
print(x)
embedding_output = tf.nn.embedding_lookup(self.embedding_mat, x)
#embedding_output = tf.expand_dims(embedding_output, axis=1)
prediction, state_h, state_c = self.lstm(embedding_output, initial_state=state)
state = [state_h, state_c]
out_sentence = prime_text
word = word_list[-1]
for n in range(num):
#x = tf.expand_dims(vocab[word], axis=0)
x = np.zeros((1, 1))
x[0, 0] = vocab[word]
x = tf.cast(x, tf.int32)
embedding_output = tf.nn.embedding_lookup(self.embedding_mat, x)
prediction, state_h, state_c = self.lstm(embedding_output, initial_state=state)
logits = tf.matmul(prediction, self.W) + self.b
sample = tf.argmax(tf.nn.softmax(logits), axis=1).numpy()[0]
for i in sample:
if i== 0:
break
print(i)
word = words[i]
out_sentence = out_sentence + ' ' + word
state = [state_h, state_c]
return out_sentence
Define LSTM Model.
lstm_model = LSTM_Model(embedding_size, rnn_size, batch_size, learning_rate,
training_seq_len, vocab_size, infer_sample=True)
WARNING:tensorflow:The following Variables were used in a Lambda layer's call (tf.compat.v1.nn.embedding_lookup), but are not present in its tracked objects: <tf.Variable 'embedding_mat:0' shape=(8286, 128) dtype=float32>. This is a strong indication that the Lambda layer should be rewritten as a subclassed Layer.
WARNING:tensorflow:The following Variables were used in a Lambda layer's call (tf.linalg.matmul), but are not present in its tracked objects: <tf.Variable 'W:0' shape=(128, 8286) dtype=float32>. This is a strong indication that the Lambda layer should be rewritten as a subclassed Layer.
WARNING:tensorflow:The following Variables were used in a Lambda layer's call (tf.__operators__.add), but are not present in its tracked objects: <tf.Variable 'b:0' shape=(8286,) dtype=float32>. This is a strong indication that the Lambda layer should be rewritten as a subclassed Layer.
Train model.
num_batches = int(len(s_text_ix)/(batch_size * training_seq_len)) + 1
batches = np.array_split(s_text_ix, num_batches)
batches = [np.resize(x, [batch_size, training_seq_len]) for x in batches]
print(batches)
print(batch_size)
test_lstm_model = LSTM_Model(embedding_size, rnn_size, batch_size, learning_rate,
training_seq_len, vocab_size, infer_sample=True)
num_batches = int(len(s_text_ix)/(batch_size * training_seq_len)) + 1
batches = np.array_split(s_text_ix, num_batches)
batches = [np.resize(x, [batch_size, training_seq_len]) for x in batches]
print(batches)
print(batch_size)
train_loss = []
iteration_count = 1
state = lstm_model.get_initial_state(batch_size)
for epoch in range(epochs):
# Shuffle word indices
print('Starting Epoch #{} of {}.'.format(epoch+1, epochs))
random.shuffle(batches)
# Create targets from shuffled batches
targets = [np.roll(x, -1, axis=1) for x in batches]
# Run a through one epoch
print('Starting Epoch #{} of {}.'.format(epoch+1, epochs))
# Reset initial LSTM state every epoch
#state = lstm_model.get_initial_state(batch_size)
#state = sess.run(lstm_model.initial_state)
for ix, batch in enumerate(batches):
batch_loss = lstm_model.train_op(batch, targets[ix],state)
train_loss.append(batch_loss)
print('Loss = {}'.format(batch_loss))
generated_text = lstm_model.sample(words=ix2vocab, vocab=vocab2ix, num=20, prime_text='oh my')
print(generated_text)
[array([[ 0, 1, 2, ..., 39, 40, 41],
[ 42, 43, 44, ..., 66, 26, 67],
[ 68, 69, 70, ..., 7, 0, 88],
...,
[ 62, 932, 154, ..., 219, 895, 223],
[ 10, 51, 236, ..., 1129, 2, 12],
[ 0, 61, 81, ..., 1, 2, 3]]), array([[ 0, 81, 228, ..., 29, 119, 1207],
[ 23, 227, 2, ..., 557, 50, 227],
[ 17, 79, 79, ..., 18, 1235, 107],
...,
[ 688, 14, 20, ..., 7, 299, 510],
[ 12, 566, 29, ..., 536, 818, 47],
[ 398, 0, 0, ..., 81, 228, 943]]), array([[ 53, 431, 23, ..., 2, 141, 51],
[1788, 58, 555, ..., 269, 295, 337],
[ 214, 1644, 279, ..., 85, 735, 197],
...,
[ 124, 322, 2209, ..., 121, 41, 1085],
[ 376, 21, 517, ..., 21, 2217, 2218],
[2219, 279, 545, ..., 431, 23, 51]]), array([[ 517, 1104, 1279, ..., 409, 7, 121],
[ 369, 327, 23, ..., 62, 16, 107],
[ 7, 80, 151, ..., 0, 2235, 10],
...,
[ 496, 1407, 50, ..., 270, 27, 1742],
[ 596, 0, 20, ..., 228, 2389, 2674],
[2385, 1411, 100, ..., 1104, 1279, 23]]), array([[1521, 1508, 162, ..., 1014, 842, 27],
[1915, 26, 263, ..., 12, 82, 1925],
[2333, 29, 870, ..., 335, 125, 689],
...,
[ 29, 1921, 863, ..., 12, 1685, 247],
[ 61, 0, 81, ..., 343, 136, 3019],
[ 559, 0, 567, ..., 1508, 162, 1356]]), array([[ 578, 2524, 18, ..., 344, 470, 101],
[ 479, 2379, 535, ..., 100, 207, 273],
[ 16, 2625, 100, ..., 12, 0, 12],
...,
[ 227, 1972, 223, ..., 708, 51, 3145],
[ 125, 227, 578, ..., 224, 81, 0],
[ 12, 0, 29, ..., 2524, 18, 1541]]), array([[ 2, 51, 1391, ..., 0, 23, 10],
[ 47, 3327, 136, ..., 526, 478, 2378],
[ 540, 349, 2524, ..., 2816, 23, 10],
...,
[ 0, 224, 14, ..., 224, 2381, 3161],
[ 18, 1470, 2664, ..., 67, 224, 2794],
[ 12, 0, 498, ..., 51, 1391, 0]]), array([[ 141, 3557, 1132, ..., 1096, 227, 0],
[ 61, 0, 3558, ..., 498, 2479, 26],
[ 102, 227, 23, ..., 101, 2380, 2379],
...,
[1566, 51, 19, ..., 100, 179, 2388],
[ 27, 101, 274, ..., 1030, 228, 3134],
[ 136, 55, 1096, ..., 3557, 1132, 10]]), array([[1015, 474, 474, ..., 61, 100, 1590],
[ 16, 1308, 67, ..., 7, 21, 1733],
[ 23, 815, 769, ..., 1925, 186, 162],
...,
[3967, 907, 535, ..., 23, 12, 1056],
[ 81, 509, 101, ..., 53, 223, 3929],
[3338, 23, 0, ..., 474, 474, 1015]]), array([[1872, 150, 3974, ..., 136, 81, 82],
[1984, 26, 100, ..., 51, 0, 408],
[ 12, 239, 909, ..., 100, 738, 88],
...,
[1162, 136, 55, ..., 2, 3000, 0],
[4162, 337, 41, ..., 325, 12, 0],
[ 111, 12, 2568, ..., 150, 3974, 1703]]), array([[1893, 349, 29, ..., 100, 554, 118],
[2670, 20, 2, ..., 21, 1006, 100],
[ 174, 2977, 16, ..., 81, 1899, 61],
...,
[ 941, 1075, 97, ..., 1645, 23, 3950],
[4120, 23, 2465, ..., 1521, 71, 3781],
[ 36, 204, 3071, ..., 349, 29, 228]]), array([[3769, 0, 100, ..., 39, 761, 4334],
[ 23, 7, 165, ..., 12, 4336, 2664],
[ 761, 13, 582, ..., 1000, 23, 1523],
...,
[ 174, 0, 3788, ..., 1091, 0, 58],
[ 112, 122, 23, ..., 201, 10, 12],
[ 0, 4539, 2241, ..., 0, 100, 2809]]), array([[ 946, 101, 1812, ..., 117, 12, 3822],
[ 102, 11, 10, ..., 53, 51, 2716],
[ 12, 4544, 29, ..., 12, 1438, 100],
...,
[ 226, 2443, 2386, ..., 12, 3510, 29],
[ 0, 53, 2416, ..., 1419, 50, 100],
[ 262, 12, 2251, ..., 101, 1812, 53]]), array([[ 0, 3781, 36, ..., 4699, 136, 1872],
[4291, 4291, 274, ..., 534, 1068, 23],
[ 524, 101, 239, ..., 219, 61, 2105],
...,
[4764, 100, 382, ..., 105, 1364, 4786],
[ 97, 18, 274, ..., 265, 4764, 12],
[2377, 101, 264, ..., 3781, 36, 2427]]), array([[ 101, 1023, 4786, ..., 227, 85, 228],
[4842, 662, 23, ..., 894, 246, 85],
[ 118, 6, 85, ..., 174, 141, 2426],
...,
[ 90, 12, 3306, ..., 23, 0, 0],
[ 85, 5014, 67, ..., 0, 23, 2995],
[2053, 4975, 446, ..., 1023, 4786, 1162]]), array([[2377, 4730, 1276, ..., 1021, 7, 74],
[ 88, 818, 910, ..., 12, 2732, 0],
[ 21, 4590, 81, ..., 272, 0, 3425],
...,
[ 29, 223, 4928, ..., 29, 790, 0],
[ 151, 2, 62, ..., 266, 88, 0],
[1284, 12, 1466, ..., 4730, 1276, 251]]), array([[ 148, 88, 20, ..., 4896, 5155, 5156],
[ 349, 100, 174, ..., 349, 638, 12],
[ 864, 509, 421, ..., 534, 1128, 465],
...,
[1064, 100, 1064, ..., 1671, 129, 12],
[ 0, 29, 55, ..., 250, 23, 141],
[ 12, 4265, 26, ..., 88, 20, 21]]), array([[ 232, 1683, 101, ..., 0, 29, 18],
[3202, 4741, 2037, ..., 1093, 2513, 0],
[ 50, 12, 621, ..., 1973, 0, 1972],
...,
[ 88, 1346, 227, ..., 2243, 337, 272],
[ 227, 31, 12, ..., 118, 23, 5378],
[ 88, 337, 81, ..., 1683, 101, 4764]]), array([[ 102, 20, 3612, ..., 105, 136, 337],
[ 81, 12, 424, ..., 842, 50, 10],
[3316, 227, 124, ..., 29, 0, 1340],
...,
[ 967, 204, 106, ..., 1321, 227, 174],
[5465, 67, 509, ..., 0, 3385, 233],
[ 101, 644, 1475, ..., 20, 3612, 2416]]), array([[ 19, 29, 509, ..., 189, 12, 883],
[1328, 21, 823, ..., 61, 5296, 29],
[5295, 88, 2127, ..., 274, 10, 1032],
...,
[1752, 2398, 1847, ..., 47, 14, 227],
[5154, 118, 7, ..., 2498, 3249, 30],
[ 7, 922, 10, ..., 29, 509, 279]]), array([[5554, 23, 1593, ..., 328, 67, 16],
[4087, 341, 710, ..., 5296, 29, 5293],
[ 23, 5299, 29, ..., 228, 1733, 263],
...,
[ 729, 82, 2526, ..., 105, 219, 0],
[ 2, 228, 4029, ..., 295, 107, 701],
[ 498, 5643, 1133, ..., 23, 1593, 540]]), array([[ 12, 639, 6, ..., 101, 506, 100],
[ 14, 0, 0, ..., 1132, 17, 18],
[5416, 55, 197, ..., 5008, 0, 5643],
...,
[ 337, 1869, 102, ..., 335, 2398, 5699],
[5640, 85, 51, ..., 47, 100, 219],
[ 0, 107, 227, ..., 639, 6, 12]]), array([[ 10, 1180, 228, ..., 214, 0, 578],
[ 212, 744, 5631, ..., 228, 1132, 2701],
[5638, 100, 1590, ..., 23, 5761, 5631],
...,
[ 100, 148, 214, ..., 12, 3238, 61],
[ 232, 1683, 18, ..., 96, 5637, 27],
[2404, 2465, 1093, ..., 1180, 228, 0]]), array([[3085, 5637, 3085, ..., 272, 0, 1287],
[1807, 5643, 50, ..., 2671, 2971, 5643],
[ 227, 272, 3117, ..., 355, 26, 100],
...,
[ 85, 967, 863, ..., 2, 69, 0],
[ 81, 569, 23, ..., 1798, 856, 125],
[ 7, 710, 0, ..., 5637, 3085, 2404]]), array([[5861, 932, 4007, ..., 588, 0, 115],
[ 874, 898, 111, ..., 101, 0, 0],
[ 207, 0, 101, ..., 555, 118, 349],
...,
[ 208, 224, 1096, ..., 2404, 224, 2794],
[ 107, 78, 729, ..., 127, 214, 14],
[ 328, 29, 322, ..., 932, 4007, 107]]), array([[ 322, 1991, 1315, ..., 29, 3028, 1531],
[ 81, 18, 1521, ..., 29, 0, 498],
[5954, 1004, 23, ..., 18, 604, 5777],
...,
[ 51, 2387, 51, ..., 184, 12, 3697],
[ 174, 5451, 12, ..., 150, 55, 387],
[ 0, 376, 100, ..., 1991, 1315, 5954]]), array([[ 308, 505, 10, ..., 100, 534, 451],
[ 7, 30, 1207, ..., 0, 387, 2398],
[ 85, 967, 1869, ..., 29, 26, 5657],
...,
[ 227, 53, 3191, ..., 343, 0, 29],
[ 0, 23, 3670, ..., 101, 3894, 842],
[ 88, 3471, 961, ..., 505, 10, 0]]), array([[6124, 2, 604, ..., 2340, 294, 6125],
[ 23, 399, 0, ..., 6088, 932, 61],
[ 673, 0, 107, ..., 272, 818, 107],
...,
[ 973, 6201, 2398, ..., 2450, 1004, 10],
[ 38, 42, 3080, ..., 227, 1029, 328],
[ 417, 359, 0, ..., 2, 604, 125]]), array([[ 573, 81, 0, ..., 932, 1385, 6205],
[6107, 10, 973, ..., 359, 452, 2404],
[ 227, 555, 118, ..., 86, 227, 125],
...,
[3444, 317, 1607, ..., 101, 482, 554],
[ 88, 588, 4400, ..., 6092, 1162, 100],
[ 207, 11, 23, ..., 81, 0, 100]]), array([[ 0, 29, 12, ..., 6088, 26, 850],
[1207, 201, 101, ..., 540, 21, 0],
[ 204, 20, 0, ..., 3208, 23, 10],
...,
[ 0, 2278, 27, ..., 53, 6053, 2447],
[6075, 97, 7, ..., 819, 0, 115],
[ 223, 4013, 10, ..., 29, 12, 6065]]), array([[ 111, 47, 51, ..., 240, 55, 1071],
[3245, 6246, 81, ..., 2966, 81, 6081],
[2127, 2398, 6078, ..., 996, 29, 138],
...,
[ 236, 105, 911, ..., 4562, 4535, 6088],
[1686, 1033, 7, ..., 272, 596, 1354],
[ 23, 291, 216, ..., 47, 51, 434]]), array([[ 911, 0, 13, ..., 0, 6387, 102],
[ 20, 0, 6388, ..., 885, 111, 216],
[ 111, 2833, 571, ..., 12, 1541, 2404],
...,
[ 359, 951, 588, ..., 100, 738, 100],
[ 578, 295, 350, ..., 81, 6451, 465],
[6451, 18, 3861, ..., 0, 13, 18]]), array([[ 967, 542, 100, ..., 26, 535, 61],
[ 0, 233, 911, ..., 55, 3650, 4148],
[ 23, 1364, 12, ..., 6451, 82, 17],
...,
[ 88, 101, 2380, ..., 55, 3877, 227],
[ 63, 12, 5266, ..., 0, 135, 162],
[4012, 946, 34, ..., 542, 100, 272]]), array([[ 727, 725, 328, ..., 2241, 16, 2451],
[5622, 23, 6442, ..., 2451, 2354, 2361],
[ 18, 162, 1050, ..., 5622, 5622, 1921],
...,
[ 39, 12, 0, ..., 48, 421, 29],
[ 227, 6, 227, ..., 141, 101, 3836],
[ 0, 141, 0, ..., 725, 328, 23]]), array([[ 10, 118, 105, ..., 3966, 29, 0],
[ 23, 270, 10, ..., 3234, 88, 0],
[6538, 10, 738, ..., 118, 12, 0],
...,
[ 101, 2387, 568, ..., 731, 329, 37],
[ 960, 51, 4, ..., 12, 1765, 3791],
[ 223, 23, 0, ..., 118, 105, 18]]), array([[ 0, 2018, 2, ..., 0, 23, 5330],
[3843, 50, 3342, ..., 0, 141, 6492],
[ 14, 214, 273, ..., 911, 3752, 232],
...,
[1475, 224, 3497, ..., 208, 1703, 227],
[ 85, 238, 2692, ..., 6473, 729, 23],
[ 150, 295, 262, ..., 2018, 2, 12]]), array([[1358, 81, 997, ..., 101, 2380, 85],
[ 12, 778, 585, ..., 1944, 10, 20],
[ 0, 18, 0, ..., 17, 48, 5202],
...,
[ 26, 3140, 148, ..., 0, 2397, 498],
[2386, 81, 159, ..., 2156, 2, 42],
[ 369, 220, 1315, ..., 81, 997, 29]]), array([[4350, 0, 159, ..., 50, 6, 12],
[1063, 387, 10, ..., 136, 263, 88],
[1311, 18, 2389, ..., 0, 23, 0],
...,
[ 174, 16, 274, ..., 12, 2357, 10],
[ 980, 6442, 12, ..., 1685, 2738, 6471],
[ 224, 81, 3723, ..., 0, 159, 0]]), array([[1765, 1287, 227, ..., 7, 6754, 933],
[ 118, 23, 101, ..., 521, 4300, 694],
[ 0, 102, 120, ..., 85, 1088, 387],
...,
[ 23, 3105, 107, ..., 10, 5067, 23],
[ 150, 295, 6500, ..., 12, 3326, 29],
[ 12, 1234, 337, ..., 1287, 227, 26]]), array([[ 12, 28, 29, ..., 221, 51, 1358],
[ 224, 102, 88, ..., 291, 223, 33],
[ 224, 389, 2326, ..., 540, 10, 6096],
...,
[3596, 863, 4612, ..., 6893, 6786, 107],
[ 907, 142, 0, ..., 100, 534, 18],
[ 0, 29, 0, ..., 28, 29, 47]]), array([[ 100, 272, 770, ..., 47, 1073, 7],
[ 0, 50, 908, ..., 465, 142, 50],
[1073, 319, 349, ..., 417, 4381, 6784],
...,
[2450, 6771, 88, ..., 3571, 53, 21],
[ 0, 6, 7, ..., 856, 10, 1749],
[3109, 111, 20, ..., 272, 770, 908]]), array([[ 169, 23, 204, ..., 53, 907, 102],
[3133, 272, 1187, ..., 371, 26, 7],
[ 74, 1132, 0, ..., 3349, 29, 21],
...,
[ 10, 12, 3113, ..., 240, 223, 204],
[1425, 6783, 88, ..., 55, 328, 29],
[ 554, 23, 139, ..., 23, 204, 10]]), array([[ 150, 55, 20, ..., 911, 5526, 1984],
[ 0, 101, 2559, ..., 12, 0, 1720],
[ 0, 23, 1048, ..., 1685, 6, 227],
...,
[1117, 3248, 111, ..., 112, 0, 23],
[2556, 18, 437, ..., 55, 6821, 100],
[ 0, 223, 1810, ..., 55, 20, 818]]), array([[ 55, 85, 12, ..., 214, 266, 53],
[2849, 224, 26, ..., 6758, 6767, 6768],
[ 23, 64, 85, ..., 911, 898, 550],
...,
[ 209, 100, 1856, ..., 1695, 100, 272],
[ 12, 2528, 53, ..., 1163, 23, 987],
[ 911, 346, 23, ..., 85, 12, 0]]), array([[1580, 0, 46, ..., 29, 1692, 2380],
[6788, 12, 205, ..., 3748, 417, 0],
[ 907, 263, 51, ..., 85, 643, 6962],
...,
[ 23, 148, 863, ..., 23, 0, 12],
[1521, 160, 2522, ..., 81, 509, 3703],
[5463, 0, 2404, ..., 0, 46, 85]]), array([[2840, 842, 0, ..., 5349, 227, 2056],
[2056, 2411, 1096, ..., 0, 6, 42],
[1572, 1749, 552, ..., 1137, 4448, 540],
...,
[ 557, 2404, 100, ..., 398, 0, 1023],
[ 350, 0, 159, ..., 18, 434, 815],
[ 392, 246, 18, ..., 842, 0, 2329]]), array([[ 274, 2629, 5468, ..., 2639, 387, 2404],
[3331, 125, 1073, ..., 29, 227, 2639],
[2404, 3331, 2404, ..., 18, 491, 0],
...,
[ 88, 51, 2710, ..., 23, 7, 710],
[1823, 223, 6770, ..., 274, 1425, 29],
[ 51, 0, 1430, ..., 2629, 5468, 1411]]), array([[ 2, 12, 1229, ..., 85, 4818, 575],
[ 136, 6770, 23, ..., 0, 0, 111],
[3170, 0, 7009, ..., 4434, 1685, 82],
...,
[ 2, 5292, 33, ..., 4153, 29, 0],
[ 53, 227, 2639, ..., 48, 907, 102],
[ 20, 3086, 349, ..., 12, 1229, 29]]), array([[ 88, 129, 5395, ..., 12, 6530, 2670],
[4557, 18, 0, ..., 2639, 1162, 465],
[2418, 18, 1685, ..., 6784, 588, 61],
...,
[ 2, 2063, 1071, ..., 1346, 64, 17],
[4676, 2860, 4077, ..., 201, 12, 1394],
[ 12, 639, 0, ..., 129, 5395, 21]]), array([[2815, 387, 10, ..., 10, 2376, 101],
[2976, 1087, 228, ..., 930, 29, 0],
[ 23, 2009, 1685, ..., 111, 465, 2954],
...,
[ 0, 29, 0, ..., 227, 204, 0],
[1879, 23, 1376, ..., 17, 18, 3737],
[ 26, 6, 0, ..., 387, 10, 123]]), array([[ 778, 494, 127, ..., 907, 14, 305],
[ 29, 136, 2692, ..., 227, 112, 694],
[1096, 101, 1685, ..., 1315, 5091, 29],
...,
[ 10, 228, 2978, ..., 2451, 2354, 2367],
[ 12, 2383, 2366, ..., 12, 160, 1191],
[ 29, 6212, 6123, ..., 494, 127, 12]]), array([[ 88, 98, 101, ..., 742, 33, 224],
[ 391, 55, 12, ..., 442, 23, 1063],
[1093, 785, 0, ..., 17, 12, 2768],
...,
[ 55, 7185, 590, ..., 81, 2838, 12],
[1112, 29, 0, ..., 23, 266, 0],
[ 81, 2250, 0, ..., 98, 101, 1191]]), array([[ 51, 2904, 107, ..., 12, 13, 50],
[ 907, 2, 55, ..., 214, 142, 88],
[ 232, 23, 241, ..., 4071, 6, 911],
...,
[5654, 854, 7343, ..., 62, 55, 279],
[ 228, 1908, 23, ..., 7343, 7, 8],
[ 11, 7189, 227, ..., 2904, 107, 4427]]), array([[5281, 100, 2243, ..., 55, 81, 274],
[ 53, 228, 200, ..., 162, 3975, 10],
[ 228, 7311, 465, ..., 2243, 227, 1345],
...,
[ 0, 2398, 116, ..., 7327, 842, 4588],
[ 12, 5278, 815, ..., 10, 0, 51],
[ 317, 224, 2409, ..., 100, 2243, 227]]), array([[1250, 23, 5689, ..., 4219, 328, 5342],
[ 23, 0, 946, ..., 1720, 2089, 23],
[ 0, 0, 142, ..., 2202, 1364, 53],
...,
[ 852, 12, 585, ..., 112, 113, 1317],
[2763, 812, 3022, ..., 1836, 7054, 47],
[ 18, 5820, 224, ..., 23, 5689, 0]]), array([[4974, 6263, 67, ..., 23, 51, 0],
[ 33, 2613, 2, ..., 1745, 125, 29],
[ 136, 4635, 0, ..., 4670, 42, 639],
...,
[6312, 4758, 2250, ..., 125, 624, 0],
[ 379, 26, 42, ..., 2713, 4758, 12],
[ 0, 29, 911, ..., 6263, 67, 12]]), array([[ 174, 5807, 67, ..., 615, 29, 2376],
[2447, 48, 3412, ..., 69, 18, 3681],
[2465, 997, 29, ..., 150, 27, 642],
...,
[ 0, 29, 339, ..., 67, 101, 3184],
[1191, 23, 815, ..., 18, 1279, 29],
[ 118, 12, 13, ..., 5807, 67, 12]]), array([[ 10, 11, 3331, ..., 535, 1523, 3146],
[ 954, 849, 12, ..., 23, 1200, 149],
[ 232, 67, 101, ..., 50, 88, 10],
...,
[ 694, 26, 2, ..., 23, 2933, 1],
[ 7, 8, 20, ..., 0, 4758, 588],
[ 987, 1545, 26, ..., 11, 3331, 7327]]), array([[ 0, 125, 100, ..., 3100, 124, 911],
[7117, 88, 29, ..., 12, 297, 55],
[ 81, 228, 0, ..., 1132, 6095, 227],
...,
[ 0, 107, 159, ..., 0, 0, 159],
[ 14, 956, 10, ..., 907, 272, 1048],
[2377, 7010, 2, ..., 125, 100, 272]]), array([[7363, 7495, 7184, ..., 20, 3005, 29],
[ 12, 52, 150, ..., 108, 535, 21],
[4938, 7012, 7012, ..., 5180, 735, 535],
...,
[ 118, 100, 2243, ..., 21, 479, 36],
[7488, 4448, 100, ..., 112, 16, 85],
[ 18, 5142, 2069, ..., 7495, 7184, 6765]]), array([[ 2, 0, 856, ..., 297, 23, 6969],
[ 29, 136, 639, ..., 0, 1275, 85],
[ 51, 7110, 0, ..., 0, 3904, 236],
...,
[7329, 47, 0, ..., 0, 1749, 911],
[1770, 343, 18, ..., 2, 12, 0],
[ 0, 148, 88, ..., 0, 856, 7111]]), array([[ 2, 12, 4405, ..., 254, 101, 482],
[ 23, 319, 85, ..., 23, 3822, 118],
[ 107, 0, 0, ..., 7012, 7184, 23],
...,
[ 30, 7, 18, ..., 223, 85, 51],
[ 466, 23, 0, ..., 16, 1075, 224],
[ 102, 20, 0, ..., 12, 4405, 23]]), array([[2710, 85, 3145, ..., 1795, 542, 1612],
[ 111, 11, 7493, ..., 1, 18, 0],
[ 74, 7, 88, ..., 7493, 1004, 2278],
...,
[ 37, 11, 7495, ..., 68, 1107, 228],
[2978, 1685, 6758, ..., 1153, 946, 12],
[ 108, 29, 18, ..., 85, 3145, 23]]), array([[3623, 722, 273, ..., 7495, 61, 709],
[ 55, 227, 101, ..., 69, 18, 166],
[ 23, 1093, 120, ..., 223, 10, 51],
...,
[ 7, 0, 21, ..., 295, 613, 23],
[ 613, 214, 102, ..., 359, 1545, 2427],
[ 16, 791, 1685, ..., 722, 273, 118]]), array([[ 88, 1709, 694, ..., 23, 17, 48],
[4400, 0, 67, ..., 2355, 6670, 0],
[7153, 6348, 23, ..., 3894, 540, 4974],
...,
[1133, 10, 0, ..., 227, 3730, 6946],
[ 10, 911, 1795, ..., 23, 2, 26],
[3894, 510, 55, ..., 1709, 694, 2451]]), array([[ 809, 3168, 1880, ..., 280, 1685, 6758],
[1162, 2529, 101, ..., 7598, 7599, 0],
[7153, 349, 2118, ..., 7153, 100, 534],
...,
[ 432, 322, 2401, ..., 5700, 6348, 23],
[7104, 350, 2203, ..., 1685, 7153, 204],
[2427, 228, 43, ..., 3168, 1880, 223]]), array([[ 118, 6, 100, ..., 2480, 2450, 2149],
[1162, 204, 100, ..., 101, 1498, 1685],
[7153, 48, 1896, ..., 81, 154, 159],
...,
[1004, 2, 472, ..., 85, 2383, 2396],
[7012, 561, 118, ..., 106, 7009, 1276],
[1107, 7012, 23, ..., 6, 100, 240]]), array([[ 20, 121, 23, ..., 107, 7645, 23],
[1397, 0, 0, ..., 3319, 223, 227],
[ 26, 14, 2241, ..., 10, 1160, 12],
...,
[ 12, 1765, 124, ..., 118, 88, 53],
[2710, 6, 7, ..., 0, 118, 10],
[ 101, 2481, 2710, ..., 121, 23, 349]]), array([[ 23, 221, 2489, ..., 0, 1685, 7153],
[ 694, 673, 911, ..., 151, 2268, 26],
[ 12, 0, 2310, ..., 7422, 88, 18],
...,
[7673, 247, 954, ..., 26, 12, 0],
[ 0, 23, 2376, ..., 50, 33, 12],
[ 856, 842, 0, ..., 221, 2489, 53]]), array([[ 369, 1425, 7598, ..., 228, 1827, 5518],
[6294, 55, 5518, ..., 534, 0, 179],
[ 227, 4782, 124, ..., 3010, 97, 101],
...,
[2377, 23, 3782, ..., 251, 986, 105],
[ 136, 498, 3177, ..., 100, 534, 2855],
[ 227, 102, 2404, ..., 1425, 7598, 100]]), array([[6026, 151, 0, ..., 274, 1765, 84],
[ 223, 85, 18, ..., 136, 81, 1710],
[1315, 3177, 100, ..., 2354, 2355, 48],
...,
[1508, 0, 29, ..., 114, 61, 50],
[ 540, 10, 115, ..., 377, 0, 53],
[ 69, 317, 111, ..., 151, 0, 1444]]), array([[1388, 228, 2021, ..., 945, 1490, 2672],
[ 101, 729, 214, ..., 2404, 7688, 555],
[ 228, 1334, 1163, ..., 356, 53, 885],
...,
[5189, 10, 228, ..., 0, 0, 337],
[ 12, 4802, 1029, ..., 630, 10, 0],
[ 337, 159, 1527, ..., 228, 2021, 23]]), array([[5981, 1839, 0, ..., 12, 5834, 0],
[ 85, 12, 1955, ..., 660, 0, 0],
[ 0, 18, 198, ..., 12, 4459, 3782],
...,
[ 102, 262, 78, ..., 100, 179, 228],
[ 59, 588, 101, ..., 715, 993, 100],
[ 382, 266, 162, ..., 1839, 0, 7340]]), array([[ 228, 274, 603, ..., 174, 88, 100],
[ 262, 227, 53, ..., 2055, 4, 417],
[7603, 136, 81, ..., 2357, 2692, 0],
...,
[ 0, 10, 0, ..., 369, 1026, 165],
[4229, 509, 253, ..., 81, 791, 204],
[ 274, 101, 2387, ..., 274, 603, 417]]), array([[ 842, 0, 115, ..., 88, 356, 18],
[ 811, 264, 238, ..., 279, 38, 51],
[4635, 482, 124, ..., 10, 1310, 387],
...,
[1184, 6532, 136, ..., 50, 53, 1021],
[ 224, 58, 88, ..., 266, 465, 81],
[ 27, 1359, 50, ..., 0, 115, 1254]]), array([[7728, 7073, 23, ..., 242, 55, 954],
[ 20, 7, 710, ..., 0, 118, 53],
[ 100, 534, 1583, ..., 14, 6213, 23],
...,
[2333, 475, 7247, ..., 2109, 12, 1991],
[ 29, 0, 98, ..., 6053, 6, 50],
[ 18, 3619, 0, ..., 7073, 23, 7184]]), array([[ 322, 2070, 349, ..., 6445, 2398, 7721],
[ 23, 908, 7730, ..., 643, 228, 2919],
[ 14, 246, 328, ..., 3596, 107, 37],
...,
[ 101, 1239, 26, ..., 10, 12, 7386],
[ 208, 100, 10, ..., 81, 50, 4762],
[2398, 12, 1442, ..., 2070, 349, 26]]), array([[7034, 308, 385, ..., 4782, 149, 1685],
[3331, 26, 4087, ..., 0, 12, 1071],
[ 29, 18, 1964, ..., 0, 17, 12],
...,
[7788, 18, 610, ..., 1175, 3802, 10],
[2333, 7784, 53, ..., 1285, 34, 3082],
[ 20, 24, 1531, ..., 308, 385, 29]]), array([[4119, 18, 3805, ..., 81, 18, 0],
[ 150, 967, 973, ..., 150, 118, 88],
[3333, 4120, 228, ..., 4119, 4120, 20],
...,
[ 111, 911, 1163, ..., 2137, 223, 100],
[ 738, 224, 14, ..., 51, 2832, 5456],
[ 911, 705, 911, ..., 18, 3805, 1114]]), array([[ 88, 2472, 7786, ..., 295, 37, 36],
[2761, 61, 0, ..., 4771, 29, 3338],
[ 150, 967, 20, ..., 23, 106, 729],
...,
[ 0, 1307, 118, ..., 111, 102, 907],
[ 67, 23, 88, ..., 4119, 111, 301],
[ 142, 136, 18, ..., 2472, 7786, 102]]), array([[2040, 18, 772, ..., 26, 125, 224],
[ 14, 3715, 4119, ..., 23, 900, 7312],
[ 55, 102, 1425, ..., 3338, 23, 266],
...,
[1068, 247, 359, ..., 240, 118, 228],
[ 478, 4119, 23, ..., 3477, 738, 228],
[2387, 4419, 23, ..., 18, 772, 863]]), array([[ 50, 434, 102, ..., 0, 348, 4119],
[2427, 227, 226, ..., 1285, 12, 0],
[ 10, 3261, 322, ..., 1713, 4120, 29],
...,
[ 26, 0, 2, ..., 136, 475, 5957],
[2387, 382, 490, ..., 39, 3111, 29],
[3141, 238, 147, ..., 434, 102, 332]]), array([[2713, 3177, 6775, ..., 958, 996, 23],
[ 149, 224, 102, ..., 1440, 465, 262],
[ 26, 907, 272, ..., 18, 294, 14],
...,
[ 55, 7829, 272, ..., 908, 0, 10],
[ 18, 2054, 6866, ..., 359, 12, 7499],
[ 29, 51, 0, ..., 3177, 6775, 6775]]), array([[ 52, 223, 232, ..., 0, 6866, 136],
[ 81, 88, 3471, ..., 23, 815, 240],
[ 16, 0, 7812, ..., 552, 189, 12],
...,
[ 725, 228, 265, ..., 6522, 4270, 392],
[ 595, 12, 1201, ..., 2392, 6866, 85],
[ 12, 3248, 2404, ..., 223, 232, 39]]), array([[ 205, 7, 979, ..., 2529, 5805, 150],
[ 208, 21, 241, ..., 55, 209, 18],
[1291, 439, 55, ..., 26, 2235, 149],
...,
[ 929, 12, 2629, ..., 6076, 491, 2451],
[2354, 2361, 18, ..., 842, 88, 3471],
[ 228, 4775, 0, ..., 7, 979, 36]]), array([[ 29, 2376, 97, ..., 21, 264, 81],
[ 26, 224, 37, ..., 16, 23, 7],
[ 8, 291, 18, ..., 14, 88, 1306],
...,
[ 97, 2446, 223, ..., 407, 111, 778],
[2882, 227, 2404, ..., 710, 438, 30],
[1040, 943, 0, ..., 2376, 97, 3697]]), array([[ 12, 0, 739, ..., 201, 61, 540],
[ 966, 1137, 227, ..., 4345, 224, 263],
[ 18, 622, 6230, ..., 860, 2922, 23],
...,
[ 399, 2, 127, ..., 41, 6775, 7],
[ 30, 3128, 1091, ..., 272, 227, 758],
[ 231, 540, 272, ..., 0, 739, 61]]), array([[ 963, 29, 434, ..., 6369, 223, 124],
[1806, 1093, 4084, ..., 1532, 908, 4236],
[ 29, 481, 609, ..., 4071, 10, 4704],
...,
[ 223, 201, 7868, ..., 272, 818, 238],
[ 102, 179, 7868, ..., 20, 695, 2451],
[7868, 23, 7852, ..., 29, 434, 0]]), array([[ 125, 81, 2293, ..., 5192, 23, 542],
[ 417, 359, 4067, ..., 0, 81, 2],
[ 62, 978, 224, ..., 12, 4802, 29],
...,
[2416, 7870, 227, ..., 1885, 107, 5405],
[ 12, 5465, 55, ..., 491, 7871, 48],
[ 100, 954, 954, ..., 81, 2293, 0]]), array([[2450, 150, 12, ..., 3817, 228, 478],
[ 81, 2, 7852, ..., 2451, 7871, 23],
[7870, 7852, 39, ..., 12, 123, 1098],
...,
[ 0, 0, 0, ..., 0, 10, 115],
[5552, 5537, 7858, ..., 2404, 2045, 7868],
[2203, 10, 7852, ..., 150, 12, 1468]]), array([[ 0, 7, 74, ..., 0, 82, 6371],
[5033, 85, 18, ..., 7752, 349, 39],
[ 12, 2719, 5753, ..., 7, 0, 17],
...,
[ 33, 2975, 1687, ..., 10, 7871, 23],
[ 254, 88, 0, ..., 208, 227, 535],
[6117, 11, 33, ..., 7, 74, 7749]]), array([[1276, 1475, 581, ..., 81, 958, 7852],
[ 88, 61, 2404, ..., 7860, 39, 3737],
[ 100, 1544, 1106, ..., 534, 107, 214],
...,
[ 12, 7567, 29, ..., 29, 295, 3087],
[ 535, 214, 6345, ..., 20, 748, 7909],
[ 227, 102, 20, ..., 1475, 581, 7]]), array([[ 12, 0, 621, ..., 2916, 107, 0],
[3612, 85, 3612, ..., 986, 253, 224],
[2824, 118, 124, ..., 50, 1123, 1040],
...,
[ 12, 1052, 29, ..., 12, 610, 478],
[ 29, 1293, 100, ..., 174, 3246, 88],
[5370, 85, 295, ..., 0, 621, 51]]), array([[7906, 136, 6750, ..., 1184, 135, 12],
[6445, 2398, 7912, ..., 731, 2318, 6999],
[ 51, 344, 311, ..., 67, 7030, 1438],
...,
[ 389, 23, 1033, ..., 88, 2780, 6374],
[ 20, 0, 517, ..., 0, 274, 4914],
[ 660, 1817, 1093, ..., 136, 6750, 7107]]), array([[ 141, 1164, 10, ..., 23, 764, 51],
[ 482, 387, 17, ..., 239, 0, 463],
[ 81, 17, 12, ..., 873, 18, 0],
...,
[6308, 997, 85, ..., 2759, 3889, 2],
[ 136, 1712, 1192, ..., 204, 81, 2061],
[ 27, 162, 55, ..., 1164, 10, 262]]), array([[3208, 7908, 36, ..., 179, 55, 234],
[ 100, 266, 18, ..., 12, 5514, 26],
[ 389, 17, 297, ..., 761, 2831, 2664],
...,
[2291, 4038, 272, ..., 907, 174, 88],
[ 179, 907, 3067, ..., 224, 207, 11],
[2398, 7936, 3288, ..., 7908, 36, 266]]), array([[7936, 3288, 36, ..., 149, 6, 735],
[ 20, 274, 3801, ..., 6982, 100, 174],
[1645, 343, 3015, ..., 29, 23, 7293],
...,
[ 214, 115, 4655, ..., 1290, 907, 535],
[ 154, 10, 20, ..., 0, 2915, 67],
[ 12, 0, 3618, ..., 3288, 36, 290]]), array([[ 88, 7203, 6, ..., 23, 82, 5610],
[ 506, 1430, 1430, ..., 227, 23, 101],
[ 52, 2475, 761, ..., 214, 2175, 53],
...,
[ 53, 118, 232, ..., 100, 14, 129],
[ 343, 227, 826, ..., 26, 0, 81],
[ 18, 0, 0, ..., 7203, 6, 227]]), array([[ 292, 291, 136, ..., 1132, 18, 93],
[2475, 761, 1036, ..., 270, 154, 987],
[ 10, 0, 1541, ..., 174, 23, 272],
...,
[ 107, 17, 107, ..., 224, 263, 61],
[2727, 224, 148, ..., 23, 85, 0],
[ 0, 12, 275, ..., 291, 136, 856]]), array([[ 223, 61, 1356, ..., 18, 0, 7682],
[ 100, 174, 88, ..., 136, 7682, 20],
[1028, 7934, 50, ..., 1414, 5669, 228],
...,
[ 29, 101, 0, ..., 159, 81, 249],
[ 23, 103, 105, ..., 42, 0, 0],
[ 67, 42, 5919, ..., 61, 1356, 967]]), array([[ 0, 100, 94, ..., 10, 7949, 10],
[ 249, 7785, 208, ..., 308, 585, 81],
[ 0, 29, 136, ..., 542, 10, 20],
...,
[ 735, 2222, 1882, ..., 7958, 6, 7],
[ 38, 851, 100, ..., 272, 88, 154],
[ 274, 4238, 7954, ..., 100, 94, 0]]), array([[1731, 12, 2208, ..., 7968, 39, 228],
[ 973, 2404, 7958, ..., 53, 136, 7762],
[3022, 100, 534, ..., 249, 7971, 7958],
...,
[ 326, 270, 343, ..., 516, 295, 0],
[ 26, 326, 82, ..., 3105, 1056, 12],
[ 91, 0, 48, ..., 12, 2208, 7968]]), array([[ 7, 7558, 1009, ..., 97, 62, 20],
[2433, 6026, 21, ..., 939, 6098, 67],
[ 12, 3081, 29, ..., 42, 41, 4795],
...,
[ 0, 1653, 136, ..., 153, 81, 12],
[2155, 227, 2241, ..., 3502, 7963, 67],
[ 47, 3323, 207, ..., 7558, 1009, 125]]), array([[1764, 2477, 811, ..., 0, 10, 1293],
[ 68, 23, 394, ..., 879, 29, 2259],
[ 100, 272, 2418, ..., 88, 1660, 10],
...,
[ 51, 434, 29, ..., 23, 907, 14],
[1741, 141, 521, ..., 0, 100, 142],
[ 0, 85, 12, ..., 2477, 811, 105]]), array([[2354, 2360, 18, ..., 2, 7990, 250],
[2354, 2360, 18, ..., 2, 12, 3054],
[5328, 2354, 2365, ..., 1892, 10, 0],
...,
[ 349, 18, 945, ..., 100, 3942, 3942],
[ 204, 2278, 162, ..., 62, 118, 39],
[ 118, 121, 369, ..., 2360, 18, 1254]]), array([[ 18, 475, 3291, ..., 983, 118, 1162],
[ 0, 18, 5132, ..., 1892, 23, 561],
[ 118, 100, 842, ..., 12, 1362, 97],
...,
[ 227, 53, 7351, ..., 150, 967, 6646],
[ 204, 4147, 387, ..., 866, 1419, 2488],
[2404, 12, 0, ..., 475, 3291, 47]]), array([[ 29, 45, 100, ..., 0, 29, 0],
[ 18, 622, 1750, ..., 7225, 7991, 1368],
[1276, 742, 10, ..., 3055, 2398, 1892],
...,
[ 61, 2404, 197, ..., 5291, 23, 112],
[ 51, 3228, 18, ..., 227, 102, 578],
[ 107, 274, 276, ..., 45, 100, 0]]), array([[ 0, 2020, 6535, ..., 0, 2, 12],
[4691, 18, 0, ..., 322, 4691, 100],
[ 0, 0, 925, ..., 498, 48, 0],
...,
[2387, 319, 874, ..., 10, 12, 2807],
[ 349, 694, 55, ..., 214, 207, 141],
[ 20, 846, 23, ..., 2020, 6535, 4681]]), array([[ 125, 346, 159, ..., 7131, 564, 3301],
[ 36, 1733, 228, ..., 6784, 3819, 27],
[ 162, 0, 208, ..., 2427, 227, 18],
...,
[1885, 62, 81, ..., 3146, 204, 10],
[ 12, 2103, 14, ..., 8012, 8013, 3326],
[8014, 8015, 23, ..., 346, 159, 10]]), array([[2377, 23, 7486, ..., 18, 1521, 274],
[3861, 29, 669, ..., 1075, 53, 8016],
[3326, 47, 81, ..., 0, 1461, 10],
...,
[ 228, 6581, 81, ..., 4448, 1570, 4448],
[ 915, 2451, 0, ..., 17, 1191, 5516],
[7844, 246, 1068, ..., 23, 7486, 0]]), array([[ 228, 369, 174, ..., 219, 3106, 2115],
[ 201, 23, 1075, ..., 663, 3326, 742],
[ 12, 0, 12, ..., 61, 8020, 100],
...,
[ 118, 23, 42, ..., 37, 141, 10],
[3764, 552, 242, ..., 2328, 889, 189],
[3159, 1393, 58, ..., 369, 174, 227]]), array([[ 41, 174, 0, ..., 597, 8019, 2137],
[1839, 24, 1839, ..., 29, 4947, 790],
[ 0, 85, 8005, ..., 911, 3146, 273],
...,
[8039, 4833, 10, ..., 7952, 1683, 136],
[6845, 3759, 2706, ..., 0, 746, 1346],
[ 0, 100, 291, ..., 174, 0, 51]]), array([[ 29, 18, 3202, ..., 61, 359, 26],
[ 609, 382, 88, ..., 105, 10, 609],
[ 0, 8039, 100, ..., 7980, 2706, 97],
...,
[3555, 55, 81, ..., 582, 12, 557],
[ 29, 2450, 1595, ..., 223, 18, 4608],
[ 0, 2158, 111, ..., 18, 3202, 224]]), array([[ 76, 7, 115, ..., 929, 55, 272],
[3664, 51, 0, ..., 1084, 42, 159],
[ 81, 359, 3925, ..., 100, 842, 12],
...,
[ 64, 266, 7, ..., 2335, 101, 2380],
[ 6, 0, 118, ..., 660, 10, 12],
[ 919, 29, 51, ..., 7, 115, 18]]), array([[8033, 6897, 100, ..., 4654, 3089, 8033],
[ 100, 272, 12, ..., 2794, 55, 6691],
[ 270, 266, 100, ..., 124, 0, 3379],
...,
[ 10, 42, 0, ..., 29, 526, 491],
[ 0, 26, 125, ..., 81, 238, 1220],
[1682, 2, 12, ..., 6897, 100, 534]]), array([[ 297, 29, 42, ..., 279, 101, 1439],
[ 4, 5350, 118, ..., 136, 1167, 228],
[2392, 232, 12, ..., 136, 47, 14],
...,
[ 50, 2020, 1239, ..., 100, 14, 3595],
[ 223, 18, 1525, ..., 53, 125, 29],
[ 101, 274, 381, ..., 29, 42, 735]]), array([[ 14, 917, 55, ..., 8039, 26, 1441],
[ 2, 12, 178, ..., 5767, 23, 18],
[4449, 2, 4222, ..., 23, 349, 273],
...,
[ 157, 534, 100, ..., 100, 863, 162],
[ 105, 0, 10, ..., 69, 3100, 100],
[ 534, 1480, 2334, ..., 917, 55, 53]]), array([[ 55, 81, 268, ..., 0, 10, 136],
[ 920, 224, 501, ..., 6678, 1908, 111],
[2176, 55, 39, ..., 174, 241, 29],
...,
[ 174, 1469, 12, ..., 1350, 61, 0],
[ 268, 954, 1930, ..., 417, 115, 12],
[6651, 1590, 118, ..., 81, 268, 0]]), array([[ 55, 81, 8046, ..., 2208, 55, 81],
[ 12, 7704, 29, ..., 5292, 2, 12],
[6445, 2398, 8045, ..., 6779, 274, 183],
...,
[ 89, 233, 21, ..., 890, 26, 535],
[ 88, 4554, 228, ..., 47, 710, 7],
[2568, 8049, 274, ..., 81, 8046, 508]]), array([[ 118, 29, 26, ..., 12, 0, 4790],
[ 125, 49, 0, ..., 50, 1679, 0],
[ 81, 107, 639, ..., 10, 20, 624],
...,
[1167, 81, 811, ..., 8049, 350, 227],
[3843, 4362, 1641, ..., 12, 125, 224],
[2945, 174, 50, ..., 29, 26, 125]]), array([[ 228, 19, 100, ..., 2529, 88, 892],
[ 50, 270, 38, ..., 123, 224, 33],
[ 224, 3270, 29, ..., 227, 240, 118],
...,
[ 915, 2882, 956, ..., 535, 0, 21],
[ 663, 0, 102, ..., 18, 1040, 183],
[ 735, 37, 20, ..., 19, 100, 266]]), array([[3082, 81, 136, ..., 2629, 8049, 47],
[ 535, 227, 232, ..., 8058, 23, 7959],
[ 47, 535, 227, ..., 576, 81, 136],
...,
[ 107, 735, 335, ..., 100, 534, 27],
[ 0, 270, 100, ..., 227, 14, 120],
[5072, 55, 227, ..., 81, 136, 26]]), array([[ 382, 24, 225, ..., 23, 228, 896],
[ 12, 4334, 247, ..., 343, 21, 4],
[ 53, 2529, 48, ..., 18, 625, 29],
...,
[4189, 2472, 55, ..., 2282, 509, 253],
[ 815, 4350, 12, ..., 12, 1541, 0],
[ 0, 0, 0, ..., 24, 225, 241]]), array([[ 873, 343, 51, ..., 51, 4781, 18],
[7807, 29, 6983, ..., 58, 51, 1391],
[ 23, 14, 125, ..., 5013, 2681, 8059],
...,
[1254, 2, 0, ..., 5083, 178, 50],
[ 939, 0, 39, ..., 88, 6527, 673],
[ 337, 227, 37, ..., 343, 51, 0]]), array([[8061, 0, 23, ..., 691, 42, 885],
[ 12, 482, 23, ..., 1984, 2, 911],
[1648, 0, 474, ..., 24, 0, 85],
...,
[5047, 232, 907, ..., 4567, 0, 1112],
[ 10, 38, 124, ..., 102, 20, 0],
[ 709, 227, 941, ..., 0, 23, 1157]]), array([[ 239, 10, 12, ..., 81, 228, 14],
[8066, 26, 224, ..., 908, 5336, 6842],
[ 23, 208, 67, ..., 960, 12, 138],
...,
[ 0, 864, 101, ..., 50, 10, 2403],
[ 125, 209, 907, ..., 6983, 2380, 6657],
[2403, 911, 0, ..., 10, 12, 4041]]), array([[2408, 233, 12, ..., 1718, 0, 2],
[ 16, 27, 6254, ..., 151, 6388, 39],
[ 12, 4803, 1371, ..., 23, 7563, 344],
...,
[ 23, 61, 49, ..., 174, 2480, 238],
[2272, 1199, 911, ..., 35, 993, 279],
[ 12, 7209, 29, ..., 233, 12, 5155]]), array([[ 842, 1093, 3202, ..., 233, 51, 729],
[ 51, 2713, 0, ..., 148, 409, 3116],
[1685, 6348, 1162, ..., 88, 7125, 120],
...,
[ 88, 12, 2357, ..., 50, 247, 1683],
[ 232, 2398, 2404, ..., 47, 869, 81],
[ 55, 10, 20, ..., 1093, 3202, 0]]), array([[ 36, 107, 967, ..., 12, 13, 142],
[ 141, 0, 10, ..., 3839, 0, 3055],
[ 233, 21, 1879, ..., 3838, 61, 548],
...,
[ 118, 61, 7668, ..., 224, 23, 270],
[1658, 6, 290, ..., 232, 2559, 3414],
[ 12, 1879, 232, ..., 107, 967, 1405]]), array([[1075, 23, 997, ..., 101, 1713, 24],
[ 534, 100, 1685, ..., 1000, 12, 3064],
[ 100, 240, 100, ..., 540, 100, 14],
...,
[ 118, 51, 0, ..., 2145, 125, 3078],
[ 343, 101, 482, ..., 55, 272, 5492],
[5105, 10, 322, ..., 23, 997, 29]]), array([[6208, 3954, 2593, ..., 21, 3075, 1685],
[ 33, 7, 497, ..., 61, 423, 30],
[ 0, 26, 1191, ..., 101, 2593, 478],
...,
[ 50, 869, 29, ..., 29, 6348, 7011],
[ 18, 491, 26, ..., 29, 7495, 23],
[8091, 7495, 274, ..., 3954, 2593, 3596]]), array([[ 88, 118, 20, ..., 27, 0, 3308],
[1765, 7596, 1632, ..., 197, 227, 6313],
[ 85, 223, 7495, ..., 81, 112, 12],
...,
[ 10, 7428, 81, ..., 7390, 238, 1921],
[ 2, 21, 568, ..., 174, 815, 755],
[ 227, 2, 12, ..., 118, 20, 227]]), array([[3697, 12, 2377, ..., 100, 208, 1525],
[ 107, 7, 74, ..., 12, 4785, 1685],
[7153, 1583, 1765, ..., 102, 557, 10],
...,
[ 272, 55, 61, ..., 3596, 48, 6],
[ 214, 120, 100, ..., 88, 5766, 39],
[ 51, 4854, 0, ..., 12, 2377, 102]]), array([[6175, 10, 920, ..., 2413, 4261, 8100],
[ 224, 53, 51, ..., 8100, 23, 107],
[ 55, 142, 673, ..., 139, 5330, 20],
...,
[ 115, 27, 2255, ..., 1594, 535, 3625],
[ 23, 3670, 141, ..., 1685, 29, 2376],
[ 735, 885, 555, ..., 10, 920, 47]]), array([[7851, 0, 39, ..., 697, 29, 1748],
[ 6, 88, 10, ..., 75, 322, 900],
[2155, 6348, 1981, ..., 12, 406, 228],
...,
[3105, 2753, 29, ..., 1558, 106, 2450],
[1765, 7596, 201, ..., 0, 10, 526],
[ 406, 29, 509, ..., 0, 39, 42]]), array([[ 925, 26, 12, ..., 101, 2392, 124],
[ 21, 1358, 61, ..., 115, 42, 1765],
[ 29, 4767, 1765, ..., 6348, 26, 148],
...,
[1629, 2, 284, ..., 29, 141, 26],
[ 100, 263, 0, ..., 7036, 67, 322],
[4450, 1685, 6348, ..., 26, 12, 1852]]), array([[ 12, 0, 0, ..., 2568, 10, 4869],
[ 124, 118, 2451, ..., 474, 5704, 2],
[ 18, 7305, 0, ..., 1745, 343, 12],
...,
[3483, 101, 2392, ..., 47, 81, 228],
[ 14, 2450, 8115, ..., 8115, 2975, 88],
[2974, 546, 815, ..., 0, 0, 1038]]), array([[ 147, 387, 0, ..., 102, 159, 2488],
[ 100, 1492, 55, ..., 101, 2380, 23],
[ 227, 142, 204, ..., 27, 1187, 100],
...,
[3394, 0, 100, ..., 24, 350, 465],
[ 0, 540, 100, ..., 478, 17, 18],
[ 639, 5101, 2, ..., 387, 0, 7866]]), array([[ 69, 236, 0, ..., 261, 9, 10],
[ 273, 2447, 2354, ..., 12, 518, 1580],
[ 51, 5803, 421, ..., 1558, 29, 5085],
...,
[8117, 559, 0, ..., 39, 23, 39],
[1683, 552, 10, ..., 81, 18, 3309],
[ 10, 12, 7599, ..., 236, 0, 100]]), array([[8106, 3242, 223, ..., 100, 272, 48],
[ 784, 2, 228, ..., 542, 510, 79],
[ 150, 8106, 226, ..., 5802, 4906, 69],
...,
[ 238, 938, 546, ..., 55, 160, 227],
[1616, 85, 12, ..., 111, 6, 55],
[ 197, 88, 228, ..., 3242, 223, 224]]), array([[2460, 118, 5531, ..., 1359, 10, 356],
[ 118, 694, 1412, ..., 10, 11, 2447],
[2318, 2369, 100, ..., 3605, 45, 6797],
...,
[ 937, 3952, 29, ..., 249, 1954, 812],
[3548, 232, 81, ..., 207, 2416, 23],
[ 542, 2176, 100, ..., 118, 5531, 359]]), array([[ 62, 16, 811, ..., 112, 16, 1885],
[ 214, 621, 1892, ..., 47, 1014, 101],
[ 491, 33, 101, ..., 21, 478, 123],
...,
[ 23, 136, 2577, ..., 0, 23, 12],
[ 0, 251, 10, ..., 5950, 23, 929],
[ 18, 4906, 2472, ..., 16, 811, 105]]), array([[ 53, 540, 100, ..., 228, 508, 8134],
[ 10, 5055, 42, ..., 227, 142, 29],
[5857, 0, 5908, ..., 17, 18, 1291],
...,
[1419, 3346, 23, ..., 227, 535, 1521],
[1276, 2404, 10, ..., 1286, 85, 8135],
[8121, 23, 8132, ..., 540, 100, 7549]]), array([[ 101, 264, 36, ..., 380, 29, 101],
[5027, 23, 2, ..., 33, 12, 1213],
[ 505, 81, 36, ..., 376, 308, 1068],
...,
[ 20, 8133, 150, ..., 2404, 214, 20],
[4071, 12, 0, ..., 815, 88, 20],
[ 791, 500, 100, ..., 264, 36, 23]]), array([[ 332, 101, 972, ..., 3112, 227, 26],
[1064, 67, 42, ..., 29, 47, 81],
[ 509, 369, 159, ..., 7980, 8137, 464],
...,
[ 227, 23, 53, ..., 4071, 23, 0],
[ 123, 704, 10, ..., 0, 62, 101],
[2392, 23, 159, ..., 101, 972, 8134]]), array([[ 102, 272, 101, ..., 8134, 81, 0],
[ 24, 23, 3611, ..., 471, 81, 136],
[ 26, 112, 61, ..., 17, 10, 20],
...,
[ 0, 1093, 3468, ..., 1240, 29, 6041],
[ 2, 16, 100, ..., 272, 0, 10],
[ 273, 118, 47, ..., 272, 101, 2392]]), array([[ 174, 88, 738, ..., 105, 48, 0],
[ 101, 750, 0, ..., 540, 7, 2880],
[ 232, 7, 128, ..., 101, 2392, 23],
...,
[ 510, 29, 3327, ..., 0, 3916, 111],
[4522, 2313, 0, ..., 2640, 8145, 100],
[ 148, 85, 69, ..., 88, 738, 7]]), array([[ 10, 2840, 3852, ..., 47, 18, 2069],
[ 842, 465, 1326, ..., 208, 0, 3286],
[1490, 274, 101, ..., 2326, 100, 356],
...,
[ 208, 27, 2692, ..., 319, 232, 100],
[ 14, 555, 708, ..., 53, 123, 0],
[ 0, 12, 0, ..., 2840, 3852, 0]]), array([[3286, 100, 266, ..., 729, 3245, 8145],
[5531, 236, 1839, ..., 2196, 387, 10],
[ 118, 23, 815, ..., 214, 535, 29],
...,
[ 10, 2677, 266, ..., 5250, 0, 4647],
[ 23, 0, 0, ..., 142, 1048, 0],
[2673, 8147, 2203, ..., 100, 266, 3022]]), array([[ 292, 8143, 2404, ..., 2203, 10, 8147],
[ 387, 2673, 1267, ..., 491, 3120, 53],
[ 141, 12, 627, ..., 81, 100, 534],
...,
[ 815, 5218, 85, ..., 136, 10, 638],
[ 223, 47, 18, ..., 10, 322, 4876],
[ 36, 148, 100, ..., 8143, 2404, 101]]), array([[ 228, 369, 2224, ..., 0, 100, 6245],
[ 67, 588, 230, ..., 273, 227, 401],
[ 815, 129, 10, ..., 1683, 2, 6053],
...,
[ 555, 2, 349, ..., 482, 2, 3519],
[5699, 509, 3513, ..., 100, 316, 911],
[4448, 37, 1939, ..., 369, 2224, 232]]), array([[ 94, 20, 61, ..., 465, 81, 88],
[ 61, 359, 31, ..., 8155, 4243, 295],
[ 0, 498, 5695, ..., 100, 534, 18],
...,
[ 16, 47, 30, ..., 2624, 23, 1941],
[8154, 74, 7, ..., 12, 2178, 4],
[ 29, 3764, 142, ..., 20, 61, 7780]]), array([[ 55, 81, 50, ..., 1124, 53, 232],
[ 55, 3673, 23, ..., 635, 55, 7888],
[ 10, 3975, 21, ..., 16, 1810, 55],
...,
[ 23, 1405, 29, ..., 2354, 2355, 3756],
[ 18, 1254, 2, ..., 1508, 4192, 29],
[3756, 1974, 0, ..., 81, 50, 0]]), array([[ 265, 10, 0, ..., 2395, 2396, 23],
[3773, 3756, 23, ..., 3015, 29, 101],
[1163, 85, 3055, ..., 729, 4434, 0],
...,
[ 142, 4179, 3776, ..., 88, 118, 3776],
[ 279, 118, 61, ..., 118, 8141, 842],
[ 88, 162, 0, ..., 10, 0, 265]]), array([[5952, 465, 0, ..., 1522, 14, 907],
[2687, 85, 141, ..., 12, 7590, 535],
[7483, 3181, 723, ..., 136, 196, 18],
...,
[ 20, 3163, 101, ..., 79, 29, 885],
[ 50, 535, 29, ..., 4149, 101, 478],
[ 102, 208, 3837, ..., 465, 0, 39]]), array([[ 53, 911, 2401, ..., 815, 976, 295],
[ 885, 1222, 118, ..., 5628, 708, 8169],
[ 478, 2398, 3837, ..., 53, 101, 2963],
...,
[ 227, 232, 7302, ..., 100, 272, 636],
[ 10, 920, 2278, ..., 2854, 18, 5720],
[4303, 12, 519, ..., 911, 2401, 1023]]), array([[ 18, 0, 1075, ..., 609, 2398, 12],
[2386, 85, 18, ..., 207, 88, 20],
[4204, 500, 12, ..., 850, 7, 88],
...,
[2028, 5699, 4815, ..., 4093, 709, 227],
[1810, 4093, 709, ..., 3133, 5699, 1162],
[ 465, 214, 535, ..., 1075, 502, 885]]), array([[5699, 3837, 219, ..., 18, 3146, 29],
[ 0, 39, 413, ..., 2287, 0, 174],
[3672, 5807, 67, ..., 0, 1648, 29],
...,
[1253, 2332, 197, ..., 0, 1862, 2],
[ 317, 12, 0, ..., 1245, 3210, 0],
[ 112, 141, 0, ..., 219, 12, 2617]]), array([[1056, 932, 3903, ..., 204, 12, 1599],
[1604, 559, 872, ..., 12, 0, 0],
[ 0, 12, 5165, ..., 911, 384, 1358],
...,
[ 12, 1733, 6, ..., 0, 55, 81],
[ 987, 159, 0, ..., 38, 2525, 24],
[ 53, 588, 18, ..., 3903, 540, 78]]), array([[7343, 0, 162, ..., 0, 334, 1425],
[ 29, 18, 2945, ..., 0, 322, 610],
[1720, 1635, 607, ..., 4066, 118, 23],
...,
[ 18, 663, 125, ..., 4555, 7622, 23],
[8195, 8195, 349, ..., 1984, 23, 5419],
[ 0, 5333, 2962, ..., 162, 2, 42]]), array([[ 349, 18, 308, ..., 227, 951, 0],
[ 101, 7984, 2, ..., 150, 223, 20],
[3163, 610, 288, ..., 1382, 2334, 895],
...,
[5191, 1227, 7, ..., 101, 2272, 53],
[ 39, 12, 3181, ..., 2117, 23, 262],
[ 227, 2380, 815, ..., 308, 0, 29]]), array([[1180, 21, 660, ..., 26, 3406, 10],
[ 829, 335, 223, ..., 365, 23, 3],
[6983, 2451, 2354, ..., 26, 12, 0],
...,
[7645, 8192, 148, ..., 2528, 0, 216],
[ 301, 1653, 485, ..., 2427, 227, 2],
[ 39, 141, 12, ..., 660, 2450, 240]]), array([[3627, 3107, 907, ..., 100, 266, 12],
[3285, 272, 2061, ..., 359, 10, 510],
[3196, 0, 5703, ..., 261, 50, 12],
...,
[2568, 81, 55, ..., 47, 102, 907],
[ 174, 301, 142, ..., 2, 731, 4494],
[6671, 6, 12, ..., 907, 223, 67]]), array([[ 62, 81, 224, ..., 50, 141, 100],
[ 272, 0, 16, ..., 0, 10, 42],
[ 0, 55, 81, ..., 101, 261, 1411],
...,
[ 29, 911, 705, ..., 2416, 18, 1191],
[ 29, 26, 1811, ..., 115, 18, 1807],
[ 337, 224, 102, ..., 224, 331, 2404]]), array([[ 118, 47, 2664, ..., 42, 88, 2475],
[ 761, 59, 129, ..., 2364, 2353, 2398],
[2377, 8200, 8206, ..., 0, 23, 0],
...,
[3286, 100, 219, ..., 29, 136, 5126],
[3286, 2759, 2404, ..., 2752, 2115, 735],
[3800, 624, 2, ..., 2664, 26, 2404]]), array([[ 344, 153, 4750, ..., 2, 136, 52],
[ 100, 102, 769, ..., 29, 12, 5126],
[ 465, 102, 227, ..., 761, 0, 3514],
...,
[ 179, 51, 1312, ..., 1187, 10, 3071],
[ 247, 85, 3509, ..., 136, 877, 159],
[ 161, 118, 100, ..., 4750, 12, 278]]), array([[5126, 10, 1164, ..., 4071, 10, 0],
[ 509, 4591, 7805, ..., 5882, 23, 3075],
[ 0, 100, 316, ..., 26, 0, 92],
...,
[8218, 29, 141, ..., 8220, 107, 29],
[ 18, 2681, 0, ..., 137, 779, 2],
[ 967, 8218, 540, ..., 1164, 118, 328]]), array([[ 29, 78, 274, ..., 1145, 149, 8218],
[1162, 224, 29, ..., 88, 638, 322],
[ 62, 8220, 97, ..., 23, 3163, 100],
...,
[ 0, 2145, 85, ..., 100, 906, 465],
[ 81, 27, 759, ..., 228, 421, 842],
[ 136, 12, 1857, ..., 274, 100, 738]]), array([[ 33, 100, 842, ..., 2288, 88, 526],
[2288, 7, 76, ..., 427, 10, 921],
[ 18, 2109, 23, ..., 721, 7647, 204],
...,
[ 465, 8222, 272, ..., 2719, 23, 542],
[ 55, 81, 162, ..., 1162, 26, 1541],
[ 691, 12, 890, ..., 842, 1583, 227]]), array([[ 74, 7, 224, ..., 62, 2555, 2447],
[8216, 349, 14, ..., 349, 6671, 81],
[8235, 124, 42, ..., 1063, 23, 49],
...,
[ 115, 55, 3630, ..., 12, 398, 2265],
[ 81, 692, 317, ..., 2290, 29, 62],
[ 23, 1531, 8218, ..., 224, 58, 0]]), array([[7647, 26, 227, ..., 12, 2377, 2398],
[2377, 2377, 540, ..., 53, 7682, 8118],
[3179, 295, 885, ..., 5947, 42, 3146],
...,
[2911, 274, 3357, ..., 3937, 23, 907],
[ 0, 1488, 111, ..., 53, 227, 270],
[ 20, 0, 51, ..., 227, 535, 36]]), array([[6934, 10, 223, ..., 0, 26, 51],
[ 0, 0, 85, ..., 1438, 2586, 8242],
[ 61, 907, 207, ..., 0, 2435, 387],
...,
[ 10, 12, 0, ..., 815, 20, 23],
[ 465, 815, 20, ..., 12, 0, 0],
[ 2, 911, 0, ..., 223, 23, 0]]), array([[ 975, 23, 1293, ..., 26, 262, 88],
[1807, 3269, 10, ..., 0, 535, 214],
[1315, 3269, 4760, ..., 51, 670, 154],
...,
[ 141, 136, 6366, ..., 2334, 224, 439],
[3089, 8005, 349, ..., 387, 907, 535],
[ 141, 154, 0, ..., 1293, 377, 47]]), array([[ 23, 908, 274, ..., 4527, 23, 100],
[1137, 1364, 85, ..., 6, 55, 50],
[ 241, 100, 990, ..., 253, 23, 101],
...,
[ 51, 1803, 2495, ..., 30, 36, 0],
[ 223, 8243, 270, ..., 12, 2681, 224],
[2418, 29, 50, ..., 274, 7667, 6]]), array([[ 204, 18, 1157, ..., 12, 2483, 2327],
[1840, 1475, 1808, ..., 735, 317, 11],
[ 417, 8243, 33, ..., 610, 107, 526],
...,
[ 23, 3131, 0, ..., 272, 1523, 1731],
[ 937, 10, 118, ..., 638, 2475, 761],
[ 13, 417, 6665, ..., 1157, 2532, 88]]), array([[ 272, 0, 0, ..., 12, 6220, 0],
[ 12, 0, 609, ..., 88, 432, 42],
[ 0, 100, 179, ..., 136, 4602, 3596],
...,
[ 228, 2617, 1023, ..., 18, 1676, 107],
[ 0, 4018, 2505, ..., 8250, 815, 3208],
[ 101, 2380, 8248, ..., 0, 0, 3049]]), array([[ 85, 68, 14, ..., 12, 2373, 10],
[3208, 111, 27, ..., 522, 101, 2380],
[8196, 12, 1685, ..., 118, 10, 305],
...,
[ 55, 873, 8256, ..., 2664, 761, 6435],
[2787, 10, 3436, ..., 160, 735, 0],
[ 61, 0, 890, ..., 14, 0, 26]]), array([[ 20, 12, 245, ..., 359, 5559, 150],
[ 967, 20, 0, ..., 23, 1869, 1422],
[8248, 296, 12, ..., 12, 6274, 1218],
...,
[3285, 23, 227, ..., 82, 0, 0],
[ 201, 50, 26, ..., 3737, 3404, 227],
[1163, 10, 118, ..., 245, 2451, 2354]]), array([[1297, 201, 47, ..., 23, 0, 23],
[ 12, 0, 1293, ..., 4601, 954, 241],
[ 33, 0, 107, ..., 761, 1112, 111],
...,
[2255, 8260, 23, ..., 272, 4907, 118],
[ 349, 2709, 593, ..., 115, 48, 6099],
[ 542, 0, 0, ..., 47, 148, 224]]), array([[1490, 3819, 3235, ..., 480, 6675, 101],
[ 0, 1346, 10, ..., 100, 179, 12],
[1238, 61, 0, ..., 2404, 8260, 97],
...,
[8259, 100, 2836, ..., 8259, 1004, 48],
[ 55, 17, 228, ..., 23, 0, 266],
[ 55, 815, 2144, ..., 3235, 12, 3177]]), array([[ 76, 88, 20, ..., 526, 346, 114],
[ 18, 1605, 2629, ..., 12, 1184, 18],
[1254, 2, 0, ..., 227, 272, 0],
...,
[ 0, 0, 6818, ..., 29, 62, 0],
[ 53, 870, 105, ..., 0, 2411, 2599],
[ 159, 0, 100, ..., 20, 2019, 50]]), array([[1805, 2292, 23, ..., 18, 4918, 23],
[3522, 590, 287, ..., 261, 772, 100],
[1307, 1295, 29, ..., 2411, 2599, 159],
...,
[ 0, 2725, 81, ..., 6204, 0, 12],
[6722, 101, 557, ..., 29, 2020, 643],
[ 23, 997, 29, ..., 23, 31, 42]]), array([[ 568, 67, 42, ..., 39, 322, 0],
[6479, 638, 5557, ..., 14, 284, 123],
[ 39, 223, 1621, ..., 554, 107, 284],
...,
[ 16, 0, 7, ..., 0, 178, 0],
[ 29, 830, 183, ..., 29, 101, 460],
[5249, 58, 21, ..., 42, 2107, 51]]), array([[ 900, 663, 0, ..., 21, 353, 23],
[ 0, 85, 798, ..., 0, 29, 0],
[1399, 23, 1749, ..., 2, 212, 1313],
...,
[ 124, 0, 1310, ..., 449, 51, 2659],
[ 85, 1063, 7458, ..., 2411, 2599, 159],
[ 0, 3939, 14, ..., 0, 618, 81]]), array([[ 437, 2, 8027, ..., 1234, 1996, 29],
[1576, 0, 1027, ..., 4199, 1945, 42],
[ 0, 0, 0, ..., 1811, 4815, 85],
...,
[ 465, 224, 0, ..., 0, 2816, 224],
[ 568, 343, 51, ..., 5325, 85, 42],
[3228, 0, 17, ..., 8027, 1183, 0]]), array([[ 842, 0, 51, ..., 10, 0, 295],
[ 0, 0, 85, ..., 0, 26, 81],
[7032, 111, 4080, ..., 667, 10, 4048],
...,
[ 29, 18, 4686, ..., 4985, 12, 1132],
[ 821, 0, 0, ..., 0, 10, 12],
[1530, 2587, 3455, ..., 51, 2207, 479]]), array([[ 42, 1239, 23, ..., 1207, 2503, 67],
[ 12, 1232, 1464, ..., 21, 483, 2204],
[7592, 26, 2854, ..., 112, 223, 94],
...,
[ 709, 4670, 8283, ..., 1132, 18, 5172],
[ 0, 0, 5024, ..., 911, 0, 125],
[2794, 12, 1334, ..., 23, 5007, 55]])]
100
WARNING:tensorflow:The following Variables were used in a Lambda layer's call (tf.compat.v1.nn.embedding_lookup_1), but are not present in its tracked objects: <tf.Variable 'embedding_mat:0' shape=(8286, 128) dtype=float32>. This is a strong indication that the Lambda layer should be rewritten as a subclassed Layer.
WARNING:tensorflow:The following Variables were used in a Lambda layer's call (tf.linalg.matmul_1), but are not present in its tracked objects: <tf.Variable 'W:0' shape=(128, 8286) dtype=float32>. This is a strong indication that the Lambda layer should be rewritten as a subclassed Layer.
WARNING:tensorflow:The following Variables were used in a Lambda layer's call (tf.__operators__.add_1), but are not present in its tracked objects: <tf.Variable 'b:0' shape=(8286,) dtype=float32>. This is a strong indication that the Lambda layer should be rewritten as a subclassed Layer.
[array([[ 0, 1, 2, ..., 39, 40, 41],
[ 42, 43, 44, ..., 66, 26, 67],
[ 68, 69, 70, ..., 7, 0, 88],
...,
[ 62, 932, 154, ..., 219, 895, 223],
[ 10, 51, 236, ..., 1129, 2, 12],
[ 0, 61, 81, ..., 1, 2, 3]]), array([[ 0, 81, 228, ..., 29, 119, 1207],
[ 23, 227, 2, ..., 557, 50, 227],
[ 17, 79, 79, ..., 18, 1235, 107],
...,
[ 688, 14, 20, ..., 7, 299, 510],
[ 12, 566, 29, ..., 536, 818, 47],
[ 398, 0, 0, ..., 81, 228, 943]]), array([[ 53, 431, 23, ..., 2, 141, 51],
[1788, 58, 555, ..., 269, 295, 337],
[ 214, 1644, 279, ..., 85, 735, 197],
...,
[ 124, 322, 2209, ..., 121, 41, 1085],
[ 376, 21, 517, ..., 21, 2217, 2218],
[2219, 279, 545, ..., 431, 23, 51]]), array([[ 517, 1104, 1279, ..., 409, 7, 121],
[ 369, 327, 23, ..., 62, 16, 107],
[ 7, 80, 151, ..., 0, 2235, 10],
...,
[ 496, 1407, 50, ..., 270, 27, 1742],
[ 596, 0, 20, ..., 228, 2389, 2674],
[2385, 1411, 100, ..., 1104, 1279, 23]]), array([[1521, 1508, 162, ..., 1014, 842, 27],
[1915, 26, 263, ..., 12, 82, 1925],
[2333, 29, 870, ..., 335, 125, 689],
...,
[ 29, 1921, 863, ..., 12, 1685, 247],
[ 61, 0, 81, ..., 343, 136, 3019],
[ 559, 0, 567, ..., 1508, 162, 1356]]), array([[ 578, 2524, 18, ..., 344, 470, 101],
[ 479, 2379, 535, ..., 100, 207, 273],
[ 16, 2625, 100, ..., 12, 0, 12],
...,
[ 227, 1972, 223, ..., 708, 51, 3145],
[ 125, 227, 578, ..., 224, 81, 0],
[ 12, 0, 29, ..., 2524, 18, 1541]]), array([[ 2, 51, 1391, ..., 0, 23, 10],
[ 47, 3327, 136, ..., 526, 478, 2378],
[ 540, 349, 2524, ..., 2816, 23, 10],
...,
[ 0, 224, 14, ..., 224, 2381, 3161],
[ 18, 1470, 2664, ..., 67, 224, 2794],
[ 12, 0, 498, ..., 51, 1391, 0]]), array([[ 141, 3557, 1132, ..., 1096, 227, 0],
[ 61, 0, 3558, ..., 498, 2479, 26],
[ 102, 227, 23, ..., 101, 2380, 2379],
...,
[1566, 51, 19, ..., 100, 179, 2388],
[ 27, 101, 274, ..., 1030, 228, 3134],
[ 136, 55, 1096, ..., 3557, 1132, 10]]), array([[1015, 474, 474, ..., 61, 100, 1590],
[ 16, 1308, 67, ..., 7, 21, 1733],
[ 23, 815, 769, ..., 1925, 186, 162],
...,
[3967, 907, 535, ..., 23, 12, 1056],
[ 81, 509, 101, ..., 53, 223, 3929],
[3338, 23, 0, ..., 474, 474, 1015]]), array([[1872, 150, 3974, ..., 136, 81, 82],
[1984, 26, 100, ..., 51, 0, 408],
[ 12, 239, 909, ..., 100, 738, 88],
...,
[1162, 136, 55, ..., 2, 3000, 0],
[4162, 337, 41, ..., 325, 12, 0],
[ 111, 12, 2568, ..., 150, 3974, 1703]]), array([[1893, 349, 29, ..., 100, 554, 118],
[2670, 20, 2, ..., 21, 1006, 100],
[ 174, 2977, 16, ..., 81, 1899, 61],
...,
[ 941, 1075, 97, ..., 1645, 23, 3950],
[4120, 23, 2465, ..., 1521, 71, 3781],
[ 36, 204, 3071, ..., 349, 29, 228]]), array([[3769, 0, 100, ..., 39, 761, 4334],
[ 23, 7, 165, ..., 12, 4336, 2664],
[ 761, 13, 582, ..., 1000, 23, 1523],
...,
[ 174, 0, 3788, ..., 1091, 0, 58],
[ 112, 122, 23, ..., 201, 10, 12],
[ 0, 4539, 2241, ..., 0, 100, 2809]]), array([[ 946, 101, 1812, ..., 117, 12, 3822],
[ 102, 11, 10, ..., 53, 51, 2716],
[ 12, 4544, 29, ..., 12, 1438, 100],
...,
[ 226, 2443, 2386, ..., 12, 3510, 29],
[ 0, 53, 2416, ..., 1419, 50, 100],
[ 262, 12, 2251, ..., 101, 1812, 53]]), array([[ 0, 3781, 36, ..., 4699, 136, 1872],
[4291, 4291, 274, ..., 534, 1068, 23],
[ 524, 101, 239, ..., 219, 61, 2105],
...,
[4764, 100, 382, ..., 105, 1364, 4786],
[ 97, 18, 274, ..., 265, 4764, 12],
[2377, 101, 264, ..., 3781, 36, 2427]]), array([[ 101, 1023, 4786, ..., 227, 85, 228],
[4842, 662, 23, ..., 894, 246, 85],
[ 118, 6, 85, ..., 174, 141, 2426],
...,
[ 90, 12, 3306, ..., 23, 0, 0],
[ 85, 5014, 67, ..., 0, 23, 2995],
[2053, 4975, 446, ..., 1023, 4786, 1162]]), array([[2377, 4730, 1276, ..., 1021, 7, 74],
[ 88, 818, 910, ..., 12, 2732, 0],
[ 21, 4590, 81, ..., 272, 0, 3425],
...,
[ 29, 223, 4928, ..., 29, 790, 0],
[ 151, 2, 62, ..., 266, 88, 0],
[1284, 12, 1466, ..., 4730, 1276, 251]]), array([[ 148, 88, 20, ..., 4896, 5155, 5156],
[ 349, 100, 174, ..., 349, 638, 12],
[ 864, 509, 421, ..., 534, 1128, 465],
...,
[1064, 100, 1064, ..., 1671, 129, 12],
[ 0, 29, 55, ..., 250, 23, 141],
[ 12, 4265, 26, ..., 88, 20, 21]]), array([[ 232, 1683, 101, ..., 0, 29, 18],
[3202, 4741, 2037, ..., 1093, 2513, 0],
[ 50, 12, 621, ..., 1973, 0, 1972],
...,
[ 88, 1346, 227, ..., 2243, 337, 272],
[ 227, 31, 12, ..., 118, 23, 5378],
[ 88, 337, 81, ..., 1683, 101, 4764]]), array([[ 102, 20, 3612, ..., 105, 136, 337],
[ 81, 12, 424, ..., 842, 50, 10],
[3316, 227, 124, ..., 29, 0, 1340],
...,
[ 967, 204, 106, ..., 1321, 227, 174],
[5465, 67, 509, ..., 0, 3385, 233],
[ 101, 644, 1475, ..., 20, 3612, 2416]]), array([[ 19, 29, 509, ..., 189, 12, 883],
[1328, 21, 823, ..., 61, 5296, 29],
[5295, 88, 2127, ..., 274, 10, 1032],
...,
[1752, 2398, 1847, ..., 47, 14, 227],
[5154, 118, 7, ..., 2498, 3249, 30],
[ 7, 922, 10, ..., 29, 509, 279]]), array([[5554, 23, 1593, ..., 328, 67, 16],
[4087, 341, 710, ..., 5296, 29, 5293],
[ 23, 5299, 29, ..., 228, 1733, 263],
...,
[ 729, 82, 2526, ..., 105, 219, 0],
[ 2, 228, 4029, ..., 295, 107, 701],
[ 498, 5643, 1133, ..., 23, 1593, 540]]), array([[ 12, 639, 6, ..., 101, 506, 100],
[ 14, 0, 0, ..., 1132, 17, 18],
[5416, 55, 197, ..., 5008, 0, 5643],
...,
[ 337, 1869, 102, ..., 335, 2398, 5699],
[5640, 85, 51, ..., 47, 100, 219],
[ 0, 107, 227, ..., 639, 6, 12]]), array([[ 10, 1180, 228, ..., 214, 0, 578],
[ 212, 744, 5631, ..., 228, 1132, 2701],
[5638, 100, 1590, ..., 23, 5761, 5631],
...,
[ 100, 148, 214, ..., 12, 3238, 61],
[ 232, 1683, 18, ..., 96, 5637, 27],
[2404, 2465, 1093, ..., 1180, 228, 0]]), array([[3085, 5637, 3085, ..., 272, 0, 1287],
[1807, 5643, 50, ..., 2671, 2971, 5643],
[ 227, 272, 3117, ..., 355, 26, 100],
...,
[ 85, 967, 863, ..., 2, 69, 0],
[ 81, 569, 23, ..., 1798, 856, 125],
[ 7, 710, 0, ..., 5637, 3085, 2404]]), array([[5861, 932, 4007, ..., 588, 0, 115],
[ 874, 898, 111, ..., 101, 0, 0],
[ 207, 0, 101, ..., 555, 118, 349],
...,
[ 208, 224, 1096, ..., 2404, 224, 2794],
[ 107, 78, 729, ..., 127, 214, 14],
[ 328, 29, 322, ..., 932, 4007, 107]]), array([[ 322, 1991, 1315, ..., 29, 3028, 1531],
[ 81, 18, 1521, ..., 29, 0, 498],
[5954, 1004, 23, ..., 18, 604, 5777],
...,
[ 51, 2387, 51, ..., 184, 12, 3697],
[ 174, 5451, 12, ..., 150, 55, 387],
[ 0, 376, 100, ..., 1991, 1315, 5954]]), array([[ 308, 505, 10, ..., 100, 534, 451],
[ 7, 30, 1207, ..., 0, 387, 2398],
[ 85, 967, 1869, ..., 29, 26, 5657],
...,
[ 227, 53, 3191, ..., 343, 0, 29],
[ 0, 23, 3670, ..., 101, 3894, 842],
[ 88, 3471, 961, ..., 505, 10, 0]]), array([[6124, 2, 604, ..., 2340, 294, 6125],
[ 23, 399, 0, ..., 6088, 932, 61],
[ 673, 0, 107, ..., 272, 818, 107],
...,
[ 973, 6201, 2398, ..., 2450, 1004, 10],
[ 38, 42, 3080, ..., 227, 1029, 328],
[ 417, 359, 0, ..., 2, 604, 125]]), array([[ 573, 81, 0, ..., 932, 1385, 6205],
[6107, 10, 973, ..., 359, 452, 2404],
[ 227, 555, 118, ..., 86, 227, 125],
...,
[3444, 317, 1607, ..., 101, 482, 554],
[ 88, 588, 4400, ..., 6092, 1162, 100],
[ 207, 11, 23, ..., 81, 0, 100]]), array([[ 0, 29, 12, ..., 6088, 26, 850],
[1207, 201, 101, ..., 540, 21, 0],
[ 204, 20, 0, ..., 3208, 23, 10],
...,
[ 0, 2278, 27, ..., 53, 6053, 2447],
[6075, 97, 7, ..., 819, 0, 115],
[ 223, 4013, 10, ..., 29, 12, 6065]]), array([[ 111, 47, 51, ..., 240, 55, 1071],
[3245, 6246, 81, ..., 2966, 81, 6081],
[2127, 2398, 6078, ..., 996, 29, 138],
...,
[ 236, 105, 911, ..., 4562, 4535, 6088],
[1686, 1033, 7, ..., 272, 596, 1354],
[ 23, 291, 216, ..., 47, 51, 434]]), array([[ 911, 0, 13, ..., 0, 6387, 102],
[ 20, 0, 6388, ..., 885, 111, 216],
[ 111, 2833, 571, ..., 12, 1541, 2404],
...,
[ 359, 951, 588, ..., 100, 738, 100],
[ 578, 295, 350, ..., 81, 6451, 465],
[6451, 18, 3861, ..., 0, 13, 18]]), array([[ 967, 542, 100, ..., 26, 535, 61],
[ 0, 233, 911, ..., 55, 3650, 4148],
[ 23, 1364, 12, ..., 6451, 82, 17],
...,
[ 88, 101, 2380, ..., 55, 3877, 227],
[ 63, 12, 5266, ..., 0, 135, 162],
[4012, 946, 34, ..., 542, 100, 272]]), array([[ 727, 725, 328, ..., 2241, 16, 2451],
[5622, 23, 6442, ..., 2451, 2354, 2361],
[ 18, 162, 1050, ..., 5622, 5622, 1921],
...,
[ 39, 12, 0, ..., 48, 421, 29],
[ 227, 6, 227, ..., 141, 101, 3836],
[ 0, 141, 0, ..., 725, 328, 23]]), array([[ 10, 118, 105, ..., 3966, 29, 0],
[ 23, 270, 10, ..., 3234, 88, 0],
[6538, 10, 738, ..., 118, 12, 0],
...,
[ 101, 2387, 568, ..., 731, 329, 37],
[ 960, 51, 4, ..., 12, 1765, 3791],
[ 223, 23, 0, ..., 118, 105, 18]]), array([[ 0, 2018, 2, ..., 0, 23, 5330],
[3843, 50, 3342, ..., 0, 141, 6492],
[ 14, 214, 273, ..., 911, 3752, 232],
...,
[1475, 224, 3497, ..., 208, 1703, 227],
[ 85, 238, 2692, ..., 6473, 729, 23],
[ 150, 295, 262, ..., 2018, 2, 12]]), array([[1358, 81, 997, ..., 101, 2380, 85],
[ 12, 778, 585, ..., 1944, 10, 20],
[ 0, 18, 0, ..., 17, 48, 5202],
...,
[ 26, 3140, 148, ..., 0, 2397, 498],
[2386, 81, 159, ..., 2156, 2, 42],
[ 369, 220, 1315, ..., 81, 997, 29]]), array([[4350, 0, 159, ..., 50, 6, 12],
[1063, 387, 10, ..., 136, 263, 88],
[1311, 18, 2389, ..., 0, 23, 0],
...,
[ 174, 16, 274, ..., 12, 2357, 10],
[ 980, 6442, 12, ..., 1685, 2738, 6471],
[ 224, 81, 3723, ..., 0, 159, 0]]), array([[1765, 1287, 227, ..., 7, 6754, 933],
[ 118, 23, 101, ..., 521, 4300, 694],
[ 0, 102, 120, ..., 85, 1088, 387],
...,
[ 23, 3105, 107, ..., 10, 5067, 23],
[ 150, 295, 6500, ..., 12, 3326, 29],
[ 12, 1234, 337, ..., 1287, 227, 26]]), array([[ 12, 28, 29, ..., 221, 51, 1358],
[ 224, 102, 88, ..., 291, 223, 33],
[ 224, 389, 2326, ..., 540, 10, 6096],
...,
[3596, 863, 4612, ..., 6893, 6786, 107],
[ 907, 142, 0, ..., 100, 534, 18],
[ 0, 29, 0, ..., 28, 29, 47]]), array([[ 100, 272, 770, ..., 47, 1073, 7],
[ 0, 50, 908, ..., 465, 142, 50],
[1073, 319, 349, ..., 417, 4381, 6784],
...,
[2450, 6771, 88, ..., 3571, 53, 21],
[ 0, 6, 7, ..., 856, 10, 1749],
[3109, 111, 20, ..., 272, 770, 908]]), array([[ 169, 23, 204, ..., 53, 907, 102],
[3133, 272, 1187, ..., 371, 26, 7],
[ 74, 1132, 0, ..., 3349, 29, 21],
...,
[ 10, 12, 3113, ..., 240, 223, 204],
[1425, 6783, 88, ..., 55, 328, 29],
[ 554, 23, 139, ..., 23, 204, 10]]), array([[ 150, 55, 20, ..., 911, 5526, 1984],
[ 0, 101, 2559, ..., 12, 0, 1720],
[ 0, 23, 1048, ..., 1685, 6, 227],
...,
[1117, 3248, 111, ..., 112, 0, 23],
[2556, 18, 437, ..., 55, 6821, 100],
[ 0, 223, 1810, ..., 55, 20, 818]]), array([[ 55, 85, 12, ..., 214, 266, 53],
[2849, 224, 26, ..., 6758, 6767, 6768],
[ 23, 64, 85, ..., 911, 898, 550],
...,
[ 209, 100, 1856, ..., 1695, 100, 272],
[ 12, 2528, 53, ..., 1163, 23, 987],
[ 911, 346, 23, ..., 85, 12, 0]]), array([[1580, 0, 46, ..., 29, 1692, 2380],
[6788, 12, 205, ..., 3748, 417, 0],
[ 907, 263, 51, ..., 85, 643, 6962],
...,
[ 23, 148, 863, ..., 23, 0, 12],
[1521, 160, 2522, ..., 81, 509, 3703],
[5463, 0, 2404, ..., 0, 46, 85]]), array([[2840, 842, 0, ..., 5349, 227, 2056],
[2056, 2411, 1096, ..., 0, 6, 42],
[1572, 1749, 552, ..., 1137, 4448, 540],
...,
[ 557, 2404, 100, ..., 398, 0, 1023],
[ 350, 0, 159, ..., 18, 434, 815],
[ 392, 246, 18, ..., 842, 0, 2329]]), array([[ 274, 2629, 5468, ..., 2639, 387, 2404],
[3331, 125, 1073, ..., 29, 227, 2639],
[2404, 3331, 2404, ..., 18, 491, 0],
...,
[ 88, 51, 2710, ..., 23, 7, 710],
[1823, 223, 6770, ..., 274, 1425, 29],
[ 51, 0, 1430, ..., 2629, 5468, 1411]]), array([[ 2, 12, 1229, ..., 85, 4818, 575],
[ 136, 6770, 23, ..., 0, 0, 111],
[3170, 0, 7009, ..., 4434, 1685, 82],
...,
[ 2, 5292, 33, ..., 4153, 29, 0],
[ 53, 227, 2639, ..., 48, 907, 102],
[ 20, 3086, 349, ..., 12, 1229, 29]]), array([[ 88, 129, 5395, ..., 12, 6530, 2670],
[4557, 18, 0, ..., 2639, 1162, 465],
[2418, 18, 1685, ..., 6784, 588, 61],
...,
[ 2, 2063, 1071, ..., 1346, 64, 17],
[4676, 2860, 4077, ..., 201, 12, 1394],
[ 12, 639, 0, ..., 129, 5395, 21]]), array([[2815, 387, 10, ..., 10, 2376, 101],
[2976, 1087, 228, ..., 930, 29, 0],
[ 23, 2009, 1685, ..., 111, 465, 2954],
...,
[ 0, 29, 0, ..., 227, 204, 0],
[1879, 23, 1376, ..., 17, 18, 3737],
[ 26, 6, 0, ..., 387, 10, 123]]), array([[ 778, 494, 127, ..., 907, 14, 305],
[ 29, 136, 2692, ..., 227, 112, 694],
[1096, 101, 1685, ..., 1315, 5091, 29],
...,
[ 10, 228, 2978, ..., 2451, 2354, 2367],
[ 12, 2383, 2366, ..., 12, 160, 1191],
[ 29, 6212, 6123, ..., 494, 127, 12]]), array([[ 88, 98, 101, ..., 742, 33, 224],
[ 391, 55, 12, ..., 442, 23, 1063],
[1093, 785, 0, ..., 17, 12, 2768],
...,
[ 55, 7185, 590, ..., 81, 2838, 12],
[1112, 29, 0, ..., 23, 266, 0],
[ 81, 2250, 0, ..., 98, 101, 1191]]), array([[ 51, 2904, 107, ..., 12, 13, 50],
[ 907, 2, 55, ..., 214, 142, 88],
[ 232, 23, 241, ..., 4071, 6, 911],
...,
[5654, 854, 7343, ..., 62, 55, 279],
[ 228, 1908, 23, ..., 7343, 7, 8],
[ 11, 7189, 227, ..., 2904, 107, 4427]]), array([[5281, 100, 2243, ..., 55, 81, 274],
[ 53, 228, 200, ..., 162, 3975, 10],
[ 228, 7311, 465, ..., 2243, 227, 1345],
...,
[ 0, 2398, 116, ..., 7327, 842, 4588],
[ 12, 5278, 815, ..., 10, 0, 51],
[ 317, 224, 2409, ..., 100, 2243, 227]]), array([[1250, 23, 5689, ..., 4219, 328, 5342],
[ 23, 0, 946, ..., 1720, 2089, 23],
[ 0, 0, 142, ..., 2202, 1364, 53],
...,
[ 852, 12, 585, ..., 112, 113, 1317],
[2763, 812, 3022, ..., 1836, 7054, 47],
[ 18, 5820, 224, ..., 23, 5689, 0]]), array([[4974, 6263, 67, ..., 23, 51, 0],
[ 33, 2613, 2, ..., 1745, 125, 29],
[ 136, 4635, 0, ..., 4670, 42, 639],
...,
[6312, 4758, 2250, ..., 125, 624, 0],
[ 379, 26, 42, ..., 2713, 4758, 12],
[ 0, 29, 911, ..., 6263, 67, 12]]), array([[ 174, 5807, 67, ..., 615, 29, 2376],
[2447, 48, 3412, ..., 69, 18, 3681],
[2465, 997, 29, ..., 150, 27, 642],
...,
[ 0, 29, 339, ..., 67, 101, 3184],
[1191, 23, 815, ..., 18, 1279, 29],
[ 118, 12, 13, ..., 5807, 67, 12]]), array([[ 10, 11, 3331, ..., 535, 1523, 3146],
[ 954, 849, 12, ..., 23, 1200, 149],
[ 232, 67, 101, ..., 50, 88, 10],
...,
[ 694, 26, 2, ..., 23, 2933, 1],
[ 7, 8, 20, ..., 0, 4758, 588],
[ 987, 1545, 26, ..., 11, 3331, 7327]]), array([[ 0, 125, 100, ..., 3100, 124, 911],
[7117, 88, 29, ..., 12, 297, 55],
[ 81, 228, 0, ..., 1132, 6095, 227],
...,
[ 0, 107, 159, ..., 0, 0, 159],
[ 14, 956, 10, ..., 907, 272, 1048],
[2377, 7010, 2, ..., 125, 100, 272]]), array([[7363, 7495, 7184, ..., 20, 3005, 29],
[ 12, 52, 150, ..., 108, 535, 21],
[4938, 7012, 7012, ..., 5180, 735, 535],
...,
[ 118, 100, 2243, ..., 21, 479, 36],
[7488, 4448, 100, ..., 112, 16, 85],
[ 18, 5142, 2069, ..., 7495, 7184, 6765]]), array([[ 2, 0, 856, ..., 297, 23, 6969],
[ 29, 136, 639, ..., 0, 1275, 85],
[ 51, 7110, 0, ..., 0, 3904, 236],
...,
[7329, 47, 0, ..., 0, 1749, 911],
[1770, 343, 18, ..., 2, 12, 0],
[ 0, 148, 88, ..., 0, 856, 7111]]), array([[ 2, 12, 4405, ..., 254, 101, 482],
[ 23, 319, 85, ..., 23, 3822, 118],
[ 107, 0, 0, ..., 7012, 7184, 23],
...,
[ 30, 7, 18, ..., 223, 85, 51],
[ 466, 23, 0, ..., 16, 1075, 224],
[ 102, 20, 0, ..., 12, 4405, 23]]), array([[2710, 85, 3145, ..., 1795, 542, 1612],
[ 111, 11, 7493, ..., 1, 18, 0],
[ 74, 7, 88, ..., 7493, 1004, 2278],
...,
[ 37, 11, 7495, ..., 68, 1107, 228],
[2978, 1685, 6758, ..., 1153, 946, 12],
[ 108, 29, 18, ..., 85, 3145, 23]]), array([[3623, 722, 273, ..., 7495, 61, 709],
[ 55, 227, 101, ..., 69, 18, 166],
[ 23, 1093, 120, ..., 223, 10, 51],
...,
[ 7, 0, 21, ..., 295, 613, 23],
[ 613, 214, 102, ..., 359, 1545, 2427],
[ 16, 791, 1685, ..., 722, 273, 118]]), array([[ 88, 1709, 694, ..., 23, 17, 48],
[4400, 0, 67, ..., 2355, 6670, 0],
[7153, 6348, 23, ..., 3894, 540, 4974],
...,
[1133, 10, 0, ..., 227, 3730, 6946],
[ 10, 911, 1795, ..., 23, 2, 26],
[3894, 510, 55, ..., 1709, 694, 2451]]), array([[ 809, 3168, 1880, ..., 280, 1685, 6758],
[1162, 2529, 101, ..., 7598, 7599, 0],
[7153, 349, 2118, ..., 7153, 100, 534],
...,
[ 432, 322, 2401, ..., 5700, 6348, 23],
[7104, 350, 2203, ..., 1685, 7153, 204],
[2427, 228, 43, ..., 3168, 1880, 223]]), array([[ 118, 6, 100, ..., 2480, 2450, 2149],
[1162, 204, 100, ..., 101, 1498, 1685],
[7153, 48, 1896, ..., 81, 154, 159],
...,
[1004, 2, 472, ..., 85, 2383, 2396],
[7012, 561, 118, ..., 106, 7009, 1276],
[1107, 7012, 23, ..., 6, 100, 240]]), array([[ 20, 121, 23, ..., 107, 7645, 23],
[1397, 0, 0, ..., 3319, 223, 227],
[ 26, 14, 2241, ..., 10, 1160, 12],
...,
[ 12, 1765, 124, ..., 118, 88, 53],
[2710, 6, 7, ..., 0, 118, 10],
[ 101, 2481, 2710, ..., 121, 23, 349]]), array([[ 23, 221, 2489, ..., 0, 1685, 7153],
[ 694, 673, 911, ..., 151, 2268, 26],
[ 12, 0, 2310, ..., 7422, 88, 18],
...,
[7673, 247, 954, ..., 26, 12, 0],
[ 0, 23, 2376, ..., 50, 33, 12],
[ 856, 842, 0, ..., 221, 2489, 53]]), array([[ 369, 1425, 7598, ..., 228, 1827, 5518],
[6294, 55, 5518, ..., 534, 0, 179],
[ 227, 4782, 124, ..., 3010, 97, 101],
...,
[2377, 23, 3782, ..., 251, 986, 105],
[ 136, 498, 3177, ..., 100, 534, 2855],
[ 227, 102, 2404, ..., 1425, 7598, 100]]), array([[6026, 151, 0, ..., 274, 1765, 84],
[ 223, 85, 18, ..., 136, 81, 1710],
[1315, 3177, 100, ..., 2354, 2355, 48],
...,
[1508, 0, 29, ..., 114, 61, 50],
[ 540, 10, 115, ..., 377, 0, 53],
[ 69, 317, 111, ..., 151, 0, 1444]]), array([[1388, 228, 2021, ..., 945, 1490, 2672],
[ 101, 729, 214, ..., 2404, 7688, 555],
[ 228, 1334, 1163, ..., 356, 53, 885],
...,
[5189, 10, 228, ..., 0, 0, 337],
[ 12, 4802, 1029, ..., 630, 10, 0],
[ 337, 159, 1527, ..., 228, 2021, 23]]), array([[5981, 1839, 0, ..., 12, 5834, 0],
[ 85, 12, 1955, ..., 660, 0, 0],
[ 0, 18, 198, ..., 12, 4459, 3782],
...,
[ 102, 262, 78, ..., 100, 179, 228],
[ 59, 588, 101, ..., 715, 993, 100],
[ 382, 266, 162, ..., 1839, 0, 7340]]), array([[ 228, 274, 603, ..., 174, 88, 100],
[ 262, 227, 53, ..., 2055, 4, 417],
[7603, 136, 81, ..., 2357, 2692, 0],
...,
[ 0, 10, 0, ..., 369, 1026, 165],
[4229, 509, 253, ..., 81, 791, 204],
[ 274, 101, 2387, ..., 274, 603, 417]]), array([[ 842, 0, 115, ..., 88, 356, 18],
[ 811, 264, 238, ..., 279, 38, 51],
[4635, 482, 124, ..., 10, 1310, 387],
...,
[1184, 6532, 136, ..., 50, 53, 1021],
[ 224, 58, 88, ..., 266, 465, 81],
[ 27, 1359, 50, ..., 0, 115, 1254]]), array([[7728, 7073, 23, ..., 242, 55, 954],
[ 20, 7, 710, ..., 0, 118, 53],
[ 100, 534, 1583, ..., 14, 6213, 23],
...,
[2333, 475, 7247, ..., 2109, 12, 1991],
[ 29, 0, 98, ..., 6053, 6, 50],
[ 18, 3619, 0, ..., 7073, 23, 7184]]), array([[ 322, 2070, 349, ..., 6445, 2398, 7721],
[ 23, 908, 7730, ..., 643, 228, 2919],
[ 14, 246, 328, ..., 3596, 107, 37],
...,
[ 101, 1239, 26, ..., 10, 12, 7386],
[ 208, 100, 10, ..., 81, 50, 4762],
[2398, 12, 1442, ..., 2070, 349, 26]]), array([[7034, 308, 385, ..., 4782, 149, 1685],
[3331, 26, 4087, ..., 0, 12, 1071],
[ 29, 18, 1964, ..., 0, 17, 12],
...,
[7788, 18, 610, ..., 1175, 3802, 10],
[2333, 7784, 53, ..., 1285, 34, 3082],
[ 20, 24, 1531, ..., 308, 385, 29]]), array([[4119, 18, 3805, ..., 81, 18, 0],
[ 150, 967, 973, ..., 150, 118, 88],
[3333, 4120, 228, ..., 4119, 4120, 20],
...,
[ 111, 911, 1163, ..., 2137, 223, 100],
[ 738, 224, 14, ..., 51, 2832, 5456],
[ 911, 705, 911, ..., 18, 3805, 1114]]), array([[ 88, 2472, 7786, ..., 295, 37, 36],
[2761, 61, 0, ..., 4771, 29, 3338],
[ 150, 967, 20, ..., 23, 106, 729],
...,
[ 0, 1307, 118, ..., 111, 102, 907],
[ 67, 23, 88, ..., 4119, 111, 301],
[ 142, 136, 18, ..., 2472, 7786, 102]]), array([[2040, 18, 772, ..., 26, 125, 224],
[ 14, 3715, 4119, ..., 23, 900, 7312],
[ 55, 102, 1425, ..., 3338, 23, 266],
...,
[1068, 247, 359, ..., 240, 118, 228],
[ 478, 4119, 23, ..., 3477, 738, 228],
[2387, 4419, 23, ..., 18, 772, 863]]), array([[ 50, 434, 102, ..., 0, 348, 4119],
[2427, 227, 226, ..., 1285, 12, 0],
[ 10, 3261, 322, ..., 1713, 4120, 29],
...,
[ 26, 0, 2, ..., 136, 475, 5957],
[2387, 382, 490, ..., 39, 3111, 29],
[3141, 238, 147, ..., 434, 102, 332]]), array([[2713, 3177, 6775, ..., 958, 996, 23],
[ 149, 224, 102, ..., 1440, 465, 262],
[ 26, 907, 272, ..., 18, 294, 14],
...,
[ 55, 7829, 272, ..., 908, 0, 10],
[ 18, 2054, 6866, ..., 359, 12, 7499],
[ 29, 51, 0, ..., 3177, 6775, 6775]]), array([[ 52, 223, 232, ..., 0, 6866, 136],
[ 81, 88, 3471, ..., 23, 815, 240],
[ 16, 0, 7812, ..., 552, 189, 12],
...,
[ 725, 228, 265, ..., 6522, 4270, 392],
[ 595, 12, 1201, ..., 2392, 6866, 85],
[ 12, 3248, 2404, ..., 223, 232, 39]]), array([[ 205, 7, 979, ..., 2529, 5805, 150],
[ 208, 21, 241, ..., 55, 209, 18],
[1291, 439, 55, ..., 26, 2235, 149],
...,
[ 929, 12, 2629, ..., 6076, 491, 2451],
[2354, 2361, 18, ..., 842, 88, 3471],
[ 228, 4775, 0, ..., 7, 979, 36]]), array([[ 29, 2376, 97, ..., 21, 264, 81],
[ 26, 224, 37, ..., 16, 23, 7],
[ 8, 291, 18, ..., 14, 88, 1306],
...,
[ 97, 2446, 223, ..., 407, 111, 778],
[2882, 227, 2404, ..., 710, 438, 30],
[1040, 943, 0, ..., 2376, 97, 3697]]), array([[ 12, 0, 739, ..., 201, 61, 540],
[ 966, 1137, 227, ..., 4345, 224, 263],
[ 18, 622, 6230, ..., 860, 2922, 23],
...,
[ 399, 2, 127, ..., 41, 6775, 7],
[ 30, 3128, 1091, ..., 272, 227, 758],
[ 231, 540, 272, ..., 0, 739, 61]]), array([[ 963, 29, 434, ..., 6369, 223, 124],
[1806, 1093, 4084, ..., 1532, 908, 4236],
[ 29, 481, 609, ..., 4071, 10, 4704],
...,
[ 223, 201, 7868, ..., 272, 818, 238],
[ 102, 179, 7868, ..., 20, 695, 2451],
[7868, 23, 7852, ..., 29, 434, 0]]), array([[ 125, 81, 2293, ..., 5192, 23, 542],
[ 417, 359, 4067, ..., 0, 81, 2],
[ 62, 978, 224, ..., 12, 4802, 29],
...,
[2416, 7870, 227, ..., 1885, 107, 5405],
[ 12, 5465, 55, ..., 491, 7871, 48],
[ 100, 954, 954, ..., 81, 2293, 0]]), array([[2450, 150, 12, ..., 3817, 228, 478],
[ 81, 2, 7852, ..., 2451, 7871, 23],
[7870, 7852, 39, ..., 12, 123, 1098],
...,
[ 0, 0, 0, ..., 0, 10, 115],
[5552, 5537, 7858, ..., 2404, 2045, 7868],
[2203, 10, 7852, ..., 150, 12, 1468]]), array([[ 0, 7, 74, ..., 0, 82, 6371],
[5033, 85, 18, ..., 7752, 349, 39],
[ 12, 2719, 5753, ..., 7, 0, 17],
...,
[ 33, 2975, 1687, ..., 10, 7871, 23],
[ 254, 88, 0, ..., 208, 227, 535],
[6117, 11, 33, ..., 7, 74, 7749]]), array([[1276, 1475, 581, ..., 81, 958, 7852],
[ 88, 61, 2404, ..., 7860, 39, 3737],
[ 100, 1544, 1106, ..., 534, 107, 214],
...,
[ 12, 7567, 29, ..., 29, 295, 3087],
[ 535, 214, 6345, ..., 20, 748, 7909],
[ 227, 102, 20, ..., 1475, 581, 7]]), array([[ 12, 0, 621, ..., 2916, 107, 0],
[3612, 85, 3612, ..., 986, 253, 224],
[2824, 118, 124, ..., 50, 1123, 1040],
...,
[ 12, 1052, 29, ..., 12, 610, 478],
[ 29, 1293, 100, ..., 174, 3246, 88],
[5370, 85, 295, ..., 0, 621, 51]]), array([[7906, 136, 6750, ..., 1184, 135, 12],
[6445, 2398, 7912, ..., 731, 2318, 6999],
[ 51, 344, 311, ..., 67, 7030, 1438],
...,
[ 389, 23, 1033, ..., 88, 2780, 6374],
[ 20, 0, 517, ..., 0, 274, 4914],
[ 660, 1817, 1093, ..., 136, 6750, 7107]]), array([[ 141, 1164, 10, ..., 23, 764, 51],
[ 482, 387, 17, ..., 239, 0, 463],
[ 81, 17, 12, ..., 873, 18, 0],
...,
[6308, 997, 85, ..., 2759, 3889, 2],
[ 136, 1712, 1192, ..., 204, 81, 2061],
[ 27, 162, 55, ..., 1164, 10, 262]]), array([[3208, 7908, 36, ..., 179, 55, 234],
[ 100, 266, 18, ..., 12, 5514, 26],
[ 389, 17, 297, ..., 761, 2831, 2664],
...,
[2291, 4038, 272, ..., 907, 174, 88],
[ 179, 907, 3067, ..., 224, 207, 11],
[2398, 7936, 3288, ..., 7908, 36, 266]]), array([[7936, 3288, 36, ..., 149, 6, 735],
[ 20, 274, 3801, ..., 6982, 100, 174],
[1645, 343, 3015, ..., 29, 23, 7293],
...,
[ 214, 115, 4655, ..., 1290, 907, 535],
[ 154, 10, 20, ..., 0, 2915, 67],
[ 12, 0, 3618, ..., 3288, 36, 290]]), array([[ 88, 7203, 6, ..., 23, 82, 5610],
[ 506, 1430, 1430, ..., 227, 23, 101],
[ 52, 2475, 761, ..., 214, 2175, 53],
...,
[ 53, 118, 232, ..., 100, 14, 129],
[ 343, 227, 826, ..., 26, 0, 81],
[ 18, 0, 0, ..., 7203, 6, 227]]), array([[ 292, 291, 136, ..., 1132, 18, 93],
[2475, 761, 1036, ..., 270, 154, 987],
[ 10, 0, 1541, ..., 174, 23, 272],
...,
[ 107, 17, 107, ..., 224, 263, 61],
[2727, 224, 148, ..., 23, 85, 0],
[ 0, 12, 275, ..., 291, 136, 856]]), array([[ 223, 61, 1356, ..., 18, 0, 7682],
[ 100, 174, 88, ..., 136, 7682, 20],
[1028, 7934, 50, ..., 1414, 5669, 228],
...,
[ 29, 101, 0, ..., 159, 81, 249],
[ 23, 103, 105, ..., 42, 0, 0],
[ 67, 42, 5919, ..., 61, 1356, 967]]), array([[ 0, 100, 94, ..., 10, 7949, 10],
[ 249, 7785, 208, ..., 308, 585, 81],
[ 0, 29, 136, ..., 542, 10, 20],
...,
[ 735, 2222, 1882, ..., 7958, 6, 7],
[ 38, 851, 100, ..., 272, 88, 154],
[ 274, 4238, 7954, ..., 100, 94, 0]]), array([[1731, 12, 2208, ..., 7968, 39, 228],
[ 973, 2404, 7958, ..., 53, 136, 7762],
[3022, 100, 534, ..., 249, 7971, 7958],
...,
[ 326, 270, 343, ..., 516, 295, 0],
[ 26, 326, 82, ..., 3105, 1056, 12],
[ 91, 0, 48, ..., 12, 2208, 7968]]), array([[ 7, 7558, 1009, ..., 97, 62, 20],
[2433, 6026, 21, ..., 939, 6098, 67],
[ 12, 3081, 29, ..., 42, 41, 4795],
...,
[ 0, 1653, 136, ..., 153, 81, 12],
[2155, 227, 2241, ..., 3502, 7963, 67],
[ 47, 3323, 207, ..., 7558, 1009, 125]]), array([[1764, 2477, 811, ..., 0, 10, 1293],
[ 68, 23, 394, ..., 879, 29, 2259],
[ 100, 272, 2418, ..., 88, 1660, 10],
...,
[ 51, 434, 29, ..., 23, 907, 14],
[1741, 141, 521, ..., 0, 100, 142],
[ 0, 85, 12, ..., 2477, 811, 105]]), array([[2354, 2360, 18, ..., 2, 7990, 250],
[2354, 2360, 18, ..., 2, 12, 3054],
[5328, 2354, 2365, ..., 1892, 10, 0],
...,
[ 349, 18, 945, ..., 100, 3942, 3942],
[ 204, 2278, 162, ..., 62, 118, 39],
[ 118, 121, 369, ..., 2360, 18, 1254]]), array([[ 18, 475, 3291, ..., 983, 118, 1162],
[ 0, 18, 5132, ..., 1892, 23, 561],
[ 118, 100, 842, ..., 12, 1362, 97],
...,
[ 227, 53, 7351, ..., 150, 967, 6646],
[ 204, 4147, 387, ..., 866, 1419, 2488],
[2404, 12, 0, ..., 475, 3291, 47]]), array([[ 29, 45, 100, ..., 0, 29, 0],
[ 18, 622, 1750, ..., 7225, 7991, 1368],
[1276, 742, 10, ..., 3055, 2398, 1892],
...,
[ 61, 2404, 197, ..., 5291, 23, 112],
[ 51, 3228, 18, ..., 227, 102, 578],
[ 107, 274, 276, ..., 45, 100, 0]]), array([[ 0, 2020, 6535, ..., 0, 2, 12],
[4691, 18, 0, ..., 322, 4691, 100],
[ 0, 0, 925, ..., 498, 48, 0],
...,
[2387, 319, 874, ..., 10, 12, 2807],
[ 349, 694, 55, ..., 214, 207, 141],
[ 20, 846, 23, ..., 2020, 6535, 4681]]), array([[ 125, 346, 159, ..., 7131, 564, 3301],
[ 36, 1733, 228, ..., 6784, 3819, 27],
[ 162, 0, 208, ..., 2427, 227, 18],
...,
[1885, 62, 81, ..., 3146, 204, 10],
[ 12, 2103, 14, ..., 8012, 8013, 3326],
[8014, 8015, 23, ..., 346, 159, 10]]), array([[2377, 23, 7486, ..., 18, 1521, 274],
[3861, 29, 669, ..., 1075, 53, 8016],
[3326, 47, 81, ..., 0, 1461, 10],
...,
[ 228, 6581, 81, ..., 4448, 1570, 4448],
[ 915, 2451, 0, ..., 17, 1191, 5516],
[7844, 246, 1068, ..., 23, 7486, 0]]), array([[ 228, 369, 174, ..., 219, 3106, 2115],
[ 201, 23, 1075, ..., 663, 3326, 742],
[ 12, 0, 12, ..., 61, 8020, 100],
...,
[ 118, 23, 42, ..., 37, 141, 10],
[3764, 552, 242, ..., 2328, 889, 189],
[3159, 1393, 58, ..., 369, 174, 227]]), array([[ 41, 174, 0, ..., 597, 8019, 2137],
[1839, 24, 1839, ..., 29, 4947, 790],
[ 0, 85, 8005, ..., 911, 3146, 273],
...,
[8039, 4833, 10, ..., 7952, 1683, 136],
[6845, 3759, 2706, ..., 0, 746, 1346],
[ 0, 100, 291, ..., 174, 0, 51]]), array([[ 29, 18, 3202, ..., 61, 359, 26],
[ 609, 382, 88, ..., 105, 10, 609],
[ 0, 8039, 100, ..., 7980, 2706, 97],
...,
[3555, 55, 81, ..., 582, 12, 557],
[ 29, 2450, 1595, ..., 223, 18, 4608],
[ 0, 2158, 111, ..., 18, 3202, 224]]), array([[ 76, 7, 115, ..., 929, 55, 272],
[3664, 51, 0, ..., 1084, 42, 159],
[ 81, 359, 3925, ..., 100, 842, 12],
...,
[ 64, 266, 7, ..., 2335, 101, 2380],
[ 6, 0, 118, ..., 660, 10, 12],
[ 919, 29, 51, ..., 7, 115, 18]]), array([[8033, 6897, 100, ..., 4654, 3089, 8033],
[ 100, 272, 12, ..., 2794, 55, 6691],
[ 270, 266, 100, ..., 124, 0, 3379],
...,
[ 10, 42, 0, ..., 29, 526, 491],
[ 0, 26, 125, ..., 81, 238, 1220],
[1682, 2, 12, ..., 6897, 100, 534]]), array([[ 297, 29, 42, ..., 279, 101, 1439],
[ 4, 5350, 118, ..., 136, 1167, 228],
[2392, 232, 12, ..., 136, 47, 14],
...,
[ 50, 2020, 1239, ..., 100, 14, 3595],
[ 223, 18, 1525, ..., 53, 125, 29],
[ 101, 274, 381, ..., 29, 42, 735]]), array([[ 14, 917, 55, ..., 8039, 26, 1441],
[ 2, 12, 178, ..., 5767, 23, 18],
[4449, 2, 4222, ..., 23, 349, 273],
...,
[ 157, 534, 100, ..., 100, 863, 162],
[ 105, 0, 10, ..., 69, 3100, 100],
[ 534, 1480, 2334, ..., 917, 55, 53]]), array([[ 55, 81, 268, ..., 0, 10, 136],
[ 920, 224, 501, ..., 6678, 1908, 111],
[2176, 55, 39, ..., 174, 241, 29],
...,
[ 174, 1469, 12, ..., 1350, 61, 0],
[ 268, 954, 1930, ..., 417, 115, 12],
[6651, 1590, 118, ..., 81, 268, 0]]), array([[ 55, 81, 8046, ..., 2208, 55, 81],
[ 12, 7704, 29, ..., 5292, 2, 12],
[6445, 2398, 8045, ..., 6779, 274, 183],
...,
[ 89, 233, 21, ..., 890, 26, 535],
[ 88, 4554, 228, ..., 47, 710, 7],
[2568, 8049, 274, ..., 81, 8046, 508]]), array([[ 118, 29, 26, ..., 12, 0, 4790],
[ 125, 49, 0, ..., 50, 1679, 0],
[ 81, 107, 639, ..., 10, 20, 624],
...,
[1167, 81, 811, ..., 8049, 350, 227],
[3843, 4362, 1641, ..., 12, 125, 224],
[2945, 174, 50, ..., 29, 26, 125]]), array([[ 228, 19, 100, ..., 2529, 88, 892],
[ 50, 270, 38, ..., 123, 224, 33],
[ 224, 3270, 29, ..., 227, 240, 118],
...,
[ 915, 2882, 956, ..., 535, 0, 21],
[ 663, 0, 102, ..., 18, 1040, 183],
[ 735, 37, 20, ..., 19, 100, 266]]), array([[3082, 81, 136, ..., 2629, 8049, 47],
[ 535, 227, 232, ..., 8058, 23, 7959],
[ 47, 535, 227, ..., 576, 81, 136],
...,
[ 107, 735, 335, ..., 100, 534, 27],
[ 0, 270, 100, ..., 227, 14, 120],
[5072, 55, 227, ..., 81, 136, 26]]), array([[ 382, 24, 225, ..., 23, 228, 896],
[ 12, 4334, 247, ..., 343, 21, 4],
[ 53, 2529, 48, ..., 18, 625, 29],
...,
[4189, 2472, 55, ..., 2282, 509, 253],
[ 815, 4350, 12, ..., 12, 1541, 0],
[ 0, 0, 0, ..., 24, 225, 241]]), array([[ 873, 343, 51, ..., 51, 4781, 18],
[7807, 29, 6983, ..., 58, 51, 1391],
[ 23, 14, 125, ..., 5013, 2681, 8059],
...,
[1254, 2, 0, ..., 5083, 178, 50],
[ 939, 0, 39, ..., 88, 6527, 673],
[ 337, 227, 37, ..., 343, 51, 0]]), array([[8061, 0, 23, ..., 691, 42, 885],
[ 12, 482, 23, ..., 1984, 2, 911],
[1648, 0, 474, ..., 24, 0, 85],
...,
[5047, 232, 907, ..., 4567, 0, 1112],
[ 10, 38, 124, ..., 102, 20, 0],
[ 709, 227, 941, ..., 0, 23, 1157]]), array([[ 239, 10, 12, ..., 81, 228, 14],
[8066, 26, 224, ..., 908, 5336, 6842],
[ 23, 208, 67, ..., 960, 12, 138],
...,
[ 0, 864, 101, ..., 50, 10, 2403],
[ 125, 209, 907, ..., 6983, 2380, 6657],
[2403, 911, 0, ..., 10, 12, 4041]]), array([[2408, 233, 12, ..., 1718, 0, 2],
[ 16, 27, 6254, ..., 151, 6388, 39],
[ 12, 4803, 1371, ..., 23, 7563, 344],
...,
[ 23, 61, 49, ..., 174, 2480, 238],
[2272, 1199, 911, ..., 35, 993, 279],
[ 12, 7209, 29, ..., 233, 12, 5155]]), array([[ 842, 1093, 3202, ..., 233, 51, 729],
[ 51, 2713, 0, ..., 148, 409, 3116],
[1685, 6348, 1162, ..., 88, 7125, 120],
...,
[ 88, 12, 2357, ..., 50, 247, 1683],
[ 232, 2398, 2404, ..., 47, 869, 81],
[ 55, 10, 20, ..., 1093, 3202, 0]]), array([[ 36, 107, 967, ..., 12, 13, 142],
[ 141, 0, 10, ..., 3839, 0, 3055],
[ 233, 21, 1879, ..., 3838, 61, 548],
...,
[ 118, 61, 7668, ..., 224, 23, 270],
[1658, 6, 290, ..., 232, 2559, 3414],
[ 12, 1879, 232, ..., 107, 967, 1405]]), array([[1075, 23, 997, ..., 101, 1713, 24],
[ 534, 100, 1685, ..., 1000, 12, 3064],
[ 100, 240, 100, ..., 540, 100, 14],
...,
[ 118, 51, 0, ..., 2145, 125, 3078],
[ 343, 101, 482, ..., 55, 272, 5492],
[5105, 10, 322, ..., 23, 997, 29]]), array([[6208, 3954, 2593, ..., 21, 3075, 1685],
[ 33, 7, 497, ..., 61, 423, 30],
[ 0, 26, 1191, ..., 101, 2593, 478],
...,
[ 50, 869, 29, ..., 29, 6348, 7011],
[ 18, 491, 26, ..., 29, 7495, 23],
[8091, 7495, 274, ..., 3954, 2593, 3596]]), array([[ 88, 118, 20, ..., 27, 0, 3308],
[1765, 7596, 1632, ..., 197, 227, 6313],
[ 85, 223, 7495, ..., 81, 112, 12],
...,
[ 10, 7428, 81, ..., 7390, 238, 1921],
[ 2, 21, 568, ..., 174, 815, 755],
[ 227, 2, 12, ..., 118, 20, 227]]), array([[3697, 12, 2377, ..., 100, 208, 1525],
[ 107, 7, 74, ..., 12, 4785, 1685],
[7153, 1583, 1765, ..., 102, 557, 10],
...,
[ 272, 55, 61, ..., 3596, 48, 6],
[ 214, 120, 100, ..., 88, 5766, 39],
[ 51, 4854, 0, ..., 12, 2377, 102]]), array([[6175, 10, 920, ..., 2413, 4261, 8100],
[ 224, 53, 51, ..., 8100, 23, 107],
[ 55, 142, 673, ..., 139, 5330, 20],
...,
[ 115, 27, 2255, ..., 1594, 535, 3625],
[ 23, 3670, 141, ..., 1685, 29, 2376],
[ 735, 885, 555, ..., 10, 920, 47]]), array([[7851, 0, 39, ..., 697, 29, 1748],
[ 6, 88, 10, ..., 75, 322, 900],
[2155, 6348, 1981, ..., 12, 406, 228],
...,
[3105, 2753, 29, ..., 1558, 106, 2450],
[1765, 7596, 201, ..., 0, 10, 526],
[ 406, 29, 509, ..., 0, 39, 42]]), array([[ 925, 26, 12, ..., 101, 2392, 124],
[ 21, 1358, 61, ..., 115, 42, 1765],
[ 29, 4767, 1765, ..., 6348, 26, 148],
...,
[1629, 2, 284, ..., 29, 141, 26],
[ 100, 263, 0, ..., 7036, 67, 322],
[4450, 1685, 6348, ..., 26, 12, 1852]]), array([[ 12, 0, 0, ..., 2568, 10, 4869],
[ 124, 118, 2451, ..., 474, 5704, 2],
[ 18, 7305, 0, ..., 1745, 343, 12],
...,
[3483, 101, 2392, ..., 47, 81, 228],
[ 14, 2450, 8115, ..., 8115, 2975, 88],
[2974, 546, 815, ..., 0, 0, 1038]]), array([[ 147, 387, 0, ..., 102, 159, 2488],
[ 100, 1492, 55, ..., 101, 2380, 23],
[ 227, 142, 204, ..., 27, 1187, 100],
...,
[3394, 0, 100, ..., 24, 350, 465],
[ 0, 540, 100, ..., 478, 17, 18],
[ 639, 5101, 2, ..., 387, 0, 7866]]), array([[ 69, 236, 0, ..., 261, 9, 10],
[ 273, 2447, 2354, ..., 12, 518, 1580],
[ 51, 5803, 421, ..., 1558, 29, 5085],
...,
[8117, 559, 0, ..., 39, 23, 39],
[1683, 552, 10, ..., 81, 18, 3309],
[ 10, 12, 7599, ..., 236, 0, 100]]), array([[8106, 3242, 223, ..., 100, 272, 48],
[ 784, 2, 228, ..., 542, 510, 79],
[ 150, 8106, 226, ..., 5802, 4906, 69],
...,
[ 238, 938, 546, ..., 55, 160, 227],
[1616, 85, 12, ..., 111, 6, 55],
[ 197, 88, 228, ..., 3242, 223, 224]]), array([[2460, 118, 5531, ..., 1359, 10, 356],
[ 118, 694, 1412, ..., 10, 11, 2447],
[2318, 2369, 100, ..., 3605, 45, 6797],
...,
[ 937, 3952, 29, ..., 249, 1954, 812],
[3548, 232, 81, ..., 207, 2416, 23],
[ 542, 2176, 100, ..., 118, 5531, 359]]), array([[ 62, 16, 811, ..., 112, 16, 1885],
[ 214, 621, 1892, ..., 47, 1014, 101],
[ 491, 33, 101, ..., 21, 478, 123],
...,
[ 23, 136, 2577, ..., 0, 23, 12],
[ 0, 251, 10, ..., 5950, 23, 929],
[ 18, 4906, 2472, ..., 16, 811, 105]]), array([[ 53, 540, 100, ..., 228, 508, 8134],
[ 10, 5055, 42, ..., 227, 142, 29],
[5857, 0, 5908, ..., 17, 18, 1291],
...,
[1419, 3346, 23, ..., 227, 535, 1521],
[1276, 2404, 10, ..., 1286, 85, 8135],
[8121, 23, 8132, ..., 540, 100, 7549]]), array([[ 101, 264, 36, ..., 380, 29, 101],
[5027, 23, 2, ..., 33, 12, 1213],
[ 505, 81, 36, ..., 376, 308, 1068],
...,
[ 20, 8133, 150, ..., 2404, 214, 20],
[4071, 12, 0, ..., 815, 88, 20],
[ 791, 500, 100, ..., 264, 36, 23]]), array([[ 332, 101, 972, ..., 3112, 227, 26],
[1064, 67, 42, ..., 29, 47, 81],
[ 509, 369, 159, ..., 7980, 8137, 464],
...,
[ 227, 23, 53, ..., 4071, 23, 0],
[ 123, 704, 10, ..., 0, 62, 101],
[2392, 23, 159, ..., 101, 972, 8134]]), array([[ 102, 272, 101, ..., 8134, 81, 0],
[ 24, 23, 3611, ..., 471, 81, 136],
[ 26, 112, 61, ..., 17, 10, 20],
...,
[ 0, 1093, 3468, ..., 1240, 29, 6041],
[ 2, 16, 100, ..., 272, 0, 10],
[ 273, 118, 47, ..., 272, 101, 2392]]), array([[ 174, 88, 738, ..., 105, 48, 0],
[ 101, 750, 0, ..., 540, 7, 2880],
[ 232, 7, 128, ..., 101, 2392, 23],
...,
[ 510, 29, 3327, ..., 0, 3916, 111],
[4522, 2313, 0, ..., 2640, 8145, 100],
[ 148, 85, 69, ..., 88, 738, 7]]), array([[ 10, 2840, 3852, ..., 47, 18, 2069],
[ 842, 465, 1326, ..., 208, 0, 3286],
[1490, 274, 101, ..., 2326, 100, 356],
...,
[ 208, 27, 2692, ..., 319, 232, 100],
[ 14, 555, 708, ..., 53, 123, 0],
[ 0, 12, 0, ..., 2840, 3852, 0]]), array([[3286, 100, 266, ..., 729, 3245, 8145],
[5531, 236, 1839, ..., 2196, 387, 10],
[ 118, 23, 815, ..., 214, 535, 29],
...,
[ 10, 2677, 266, ..., 5250, 0, 4647],
[ 23, 0, 0, ..., 142, 1048, 0],
[2673, 8147, 2203, ..., 100, 266, 3022]]), array([[ 292, 8143, 2404, ..., 2203, 10, 8147],
[ 387, 2673, 1267, ..., 491, 3120, 53],
[ 141, 12, 627, ..., 81, 100, 534],
...,
[ 815, 5218, 85, ..., 136, 10, 638],
[ 223, 47, 18, ..., 10, 322, 4876],
[ 36, 148, 100, ..., 8143, 2404, 101]]), array([[ 228, 369, 2224, ..., 0, 100, 6245],
[ 67, 588, 230, ..., 273, 227, 401],
[ 815, 129, 10, ..., 1683, 2, 6053],
...,
[ 555, 2, 349, ..., 482, 2, 3519],
[5699, 509, 3513, ..., 100, 316, 911],
[4448, 37, 1939, ..., 369, 2224, 232]]), array([[ 94, 20, 61, ..., 465, 81, 88],
[ 61, 359, 31, ..., 8155, 4243, 295],
[ 0, 498, 5695, ..., 100, 534, 18],
...,
[ 16, 47, 30, ..., 2624, 23, 1941],
[8154, 74, 7, ..., 12, 2178, 4],
[ 29, 3764, 142, ..., 20, 61, 7780]]), array([[ 55, 81, 50, ..., 1124, 53, 232],
[ 55, 3673, 23, ..., 635, 55, 7888],
[ 10, 3975, 21, ..., 16, 1810, 55],
...,
[ 23, 1405, 29, ..., 2354, 2355, 3756],
[ 18, 1254, 2, ..., 1508, 4192, 29],
[3756, 1974, 0, ..., 81, 50, 0]]), array([[ 265, 10, 0, ..., 2395, 2396, 23],
[3773, 3756, 23, ..., 3015, 29, 101],
[1163, 85, 3055, ..., 729, 4434, 0],
...,
[ 142, 4179, 3776, ..., 88, 118, 3776],
[ 279, 118, 61, ..., 118, 8141, 842],
[ 88, 162, 0, ..., 10, 0, 265]]), array([[5952, 465, 0, ..., 1522, 14, 907],
[2687, 85, 141, ..., 12, 7590, 535],
[7483, 3181, 723, ..., 136, 196, 18],
...,
[ 20, 3163, 101, ..., 79, 29, 885],
[ 50, 535, 29, ..., 4149, 101, 478],
[ 102, 208, 3837, ..., 465, 0, 39]]), array([[ 53, 911, 2401, ..., 815, 976, 295],
[ 885, 1222, 118, ..., 5628, 708, 8169],
[ 478, 2398, 3837, ..., 53, 101, 2963],
...,
[ 227, 232, 7302, ..., 100, 272, 636],
[ 10, 920, 2278, ..., 2854, 18, 5720],
[4303, 12, 519, ..., 911, 2401, 1023]]), array([[ 18, 0, 1075, ..., 609, 2398, 12],
[2386, 85, 18, ..., 207, 88, 20],
[4204, 500, 12, ..., 850, 7, 88],
...,
[2028, 5699, 4815, ..., 4093, 709, 227],
[1810, 4093, 709, ..., 3133, 5699, 1162],
[ 465, 214, 535, ..., 1075, 502, 885]]), array([[5699, 3837, 219, ..., 18, 3146, 29],
[ 0, 39, 413, ..., 2287, 0, 174],
[3672, 5807, 67, ..., 0, 1648, 29],
...,
[1253, 2332, 197, ..., 0, 1862, 2],
[ 317, 12, 0, ..., 1245, 3210, 0],
[ 112, 141, 0, ..., 219, 12, 2617]]), array([[1056, 932, 3903, ..., 204, 12, 1599],
[1604, 559, 872, ..., 12, 0, 0],
[ 0, 12, 5165, ..., 911, 384, 1358],
...,
[ 12, 1733, 6, ..., 0, 55, 81],
[ 987, 159, 0, ..., 38, 2525, 24],
[ 53, 588, 18, ..., 3903, 540, 78]]), array([[7343, 0, 162, ..., 0, 334, 1425],
[ 29, 18, 2945, ..., 0, 322, 610],
[1720, 1635, 607, ..., 4066, 118, 23],
...,
[ 18, 663, 125, ..., 4555, 7622, 23],
[8195, 8195, 349, ..., 1984, 23, 5419],
[ 0, 5333, 2962, ..., 162, 2, 42]]), array([[ 349, 18, 308, ..., 227, 951, 0],
[ 101, 7984, 2, ..., 150, 223, 20],
[3163, 610, 288, ..., 1382, 2334, 895],
...,
[5191, 1227, 7, ..., 101, 2272, 53],
[ 39, 12, 3181, ..., 2117, 23, 262],
[ 227, 2380, 815, ..., 308, 0, 29]]), array([[1180, 21, 660, ..., 26, 3406, 10],
[ 829, 335, 223, ..., 365, 23, 3],
[6983, 2451, 2354, ..., 26, 12, 0],
...,
[7645, 8192, 148, ..., 2528, 0, 216],
[ 301, 1653, 485, ..., 2427, 227, 2],
[ 39, 141, 12, ..., 660, 2450, 240]]), array([[3627, 3107, 907, ..., 100, 266, 12],
[3285, 272, 2061, ..., 359, 10, 510],
[3196, 0, 5703, ..., 261, 50, 12],
...,
[2568, 81, 55, ..., 47, 102, 907],
[ 174, 301, 142, ..., 2, 731, 4494],
[6671, 6, 12, ..., 907, 223, 67]]), array([[ 62, 81, 224, ..., 50, 141, 100],
[ 272, 0, 16, ..., 0, 10, 42],
[ 0, 55, 81, ..., 101, 261, 1411],
...,
[ 29, 911, 705, ..., 2416, 18, 1191],
[ 29, 26, 1811, ..., 115, 18, 1807],
[ 337, 224, 102, ..., 224, 331, 2404]]), array([[ 118, 47, 2664, ..., 42, 88, 2475],
[ 761, 59, 129, ..., 2364, 2353, 2398],
[2377, 8200, 8206, ..., 0, 23, 0],
...,
[3286, 100, 219, ..., 29, 136, 5126],
[3286, 2759, 2404, ..., 2752, 2115, 735],
[3800, 624, 2, ..., 2664, 26, 2404]]), array([[ 344, 153, 4750, ..., 2, 136, 52],
[ 100, 102, 769, ..., 29, 12, 5126],
[ 465, 102, 227, ..., 761, 0, 3514],
...,
[ 179, 51, 1312, ..., 1187, 10, 3071],
[ 247, 85, 3509, ..., 136, 877, 159],
[ 161, 118, 100, ..., 4750, 12, 278]]), array([[5126, 10, 1164, ..., 4071, 10, 0],
[ 509, 4591, 7805, ..., 5882, 23, 3075],
[ 0, 100, 316, ..., 26, 0, 92],
...,
[8218, 29, 141, ..., 8220, 107, 29],
[ 18, 2681, 0, ..., 137, 779, 2],
[ 967, 8218, 540, ..., 1164, 118, 328]]), array([[ 29, 78, 274, ..., 1145, 149, 8218],
[1162, 224, 29, ..., 88, 638, 322],
[ 62, 8220, 97, ..., 23, 3163, 100],
...,
[ 0, 2145, 85, ..., 100, 906, 465],
[ 81, 27, 759, ..., 228, 421, 842],
[ 136, 12, 1857, ..., 274, 100, 738]]), array([[ 33, 100, 842, ..., 2288, 88, 526],
[2288, 7, 76, ..., 427, 10, 921],
[ 18, 2109, 23, ..., 721, 7647, 204],
...,
[ 465, 8222, 272, ..., 2719, 23, 542],
[ 55, 81, 162, ..., 1162, 26, 1541],
[ 691, 12, 890, ..., 842, 1583, 227]]), array([[ 74, 7, 224, ..., 62, 2555, 2447],
[8216, 349, 14, ..., 349, 6671, 81],
[8235, 124, 42, ..., 1063, 23, 49],
...,
[ 115, 55, 3630, ..., 12, 398, 2265],
[ 81, 692, 317, ..., 2290, 29, 62],
[ 23, 1531, 8218, ..., 224, 58, 0]]), array([[7647, 26, 227, ..., 12, 2377, 2398],
[2377, 2377, 540, ..., 53, 7682, 8118],
[3179, 295, 885, ..., 5947, 42, 3146],
...,
[2911, 274, 3357, ..., 3937, 23, 907],
[ 0, 1488, 111, ..., 53, 227, 270],
[ 20, 0, 51, ..., 227, 535, 36]]), array([[6934, 10, 223, ..., 0, 26, 51],
[ 0, 0, 85, ..., 1438, 2586, 8242],
[ 61, 907, 207, ..., 0, 2435, 387],
...,
[ 10, 12, 0, ..., 815, 20, 23],
[ 465, 815, 20, ..., 12, 0, 0],
[ 2, 911, 0, ..., 223, 23, 0]]), array([[ 975, 23, 1293, ..., 26, 262, 88],
[1807, 3269, 10, ..., 0, 535, 214],
[1315, 3269, 4760, ..., 51, 670, 154],
...,
[ 141, 136, 6366, ..., 2334, 224, 439],
[3089, 8005, 349, ..., 387, 907, 535],
[ 141, 154, 0, ..., 1293, 377, 47]]), array([[ 23, 908, 274, ..., 4527, 23, 100],
[1137, 1364, 85, ..., 6, 55, 50],
[ 241, 100, 990, ..., 253, 23, 101],
...,
[ 51, 1803, 2495, ..., 30, 36, 0],
[ 223, 8243, 270, ..., 12, 2681, 224],
[2418, 29, 50, ..., 274, 7667, 6]]), array([[ 204, 18, 1157, ..., 12, 2483, 2327],
[1840, 1475, 1808, ..., 735, 317, 11],
[ 417, 8243, 33, ..., 610, 107, 526],
...,
[ 23, 3131, 0, ..., 272, 1523, 1731],
[ 937, 10, 118, ..., 638, 2475, 761],
[ 13, 417, 6665, ..., 1157, 2532, 88]]), array([[ 272, 0, 0, ..., 12, 6220, 0],
[ 12, 0, 609, ..., 88, 432, 42],
[ 0, 100, 179, ..., 136, 4602, 3596],
...,
[ 228, 2617, 1023, ..., 18, 1676, 107],
[ 0, 4018, 2505, ..., 8250, 815, 3208],
[ 101, 2380, 8248, ..., 0, 0, 3049]]), array([[ 85, 68, 14, ..., 12, 2373, 10],
[3208, 111, 27, ..., 522, 101, 2380],
[8196, 12, 1685, ..., 118, 10, 305],
...,
[ 55, 873, 8256, ..., 2664, 761, 6435],
[2787, 10, 3436, ..., 160, 735, 0],
[ 61, 0, 890, ..., 14, 0, 26]]), array([[ 20, 12, 245, ..., 359, 5559, 150],
[ 967, 20, 0, ..., 23, 1869, 1422],
[8248, 296, 12, ..., 12, 6274, 1218],
...,
[3285, 23, 227, ..., 82, 0, 0],
[ 201, 50, 26, ..., 3737, 3404, 227],
[1163, 10, 118, ..., 245, 2451, 2354]]), array([[1297, 201, 47, ..., 23, 0, 23],
[ 12, 0, 1293, ..., 4601, 954, 241],
[ 33, 0, 107, ..., 761, 1112, 111],
...,
[2255, 8260, 23, ..., 272, 4907, 118],
[ 349, 2709, 593, ..., 115, 48, 6099],
[ 542, 0, 0, ..., 47, 148, 224]]), array([[1490, 3819, 3235, ..., 480, 6675, 101],
[ 0, 1346, 10, ..., 100, 179, 12],
[1238, 61, 0, ..., 2404, 8260, 97],
...,
[8259, 100, 2836, ..., 8259, 1004, 48],
[ 55, 17, 228, ..., 23, 0, 266],
[ 55, 815, 2144, ..., 3235, 12, 3177]]), array([[ 76, 88, 20, ..., 526, 346, 114],
[ 18, 1605, 2629, ..., 12, 1184, 18],
[1254, 2, 0, ..., 227, 272, 0],
...,
[ 0, 0, 6818, ..., 29, 62, 0],
[ 53, 870, 105, ..., 0, 2411, 2599],
[ 159, 0, 100, ..., 20, 2019, 50]]), array([[1805, 2292, 23, ..., 18, 4918, 23],
[3522, 590, 287, ..., 261, 772, 100],
[1307, 1295, 29, ..., 2411, 2599, 159],
...,
[ 0, 2725, 81, ..., 6204, 0, 12],
[6722, 101, 557, ..., 29, 2020, 643],
[ 23, 997, 29, ..., 23, 31, 42]]), array([[ 568, 67, 42, ..., 39, 322, 0],
[6479, 638, 5557, ..., 14, 284, 123],
[ 39, 223, 1621, ..., 554, 107, 284],
...,
[ 16, 0, 7, ..., 0, 178, 0],
[ 29, 830, 183, ..., 29, 101, 460],
[5249, 58, 21, ..., 42, 2107, 51]]), array([[ 900, 663, 0, ..., 21, 353, 23],
[ 0, 85, 798, ..., 0, 29, 0],
[1399, 23, 1749, ..., 2, 212, 1313],
...,
[ 124, 0, 1310, ..., 449, 51, 2659],
[ 85, 1063, 7458, ..., 2411, 2599, 159],
[ 0, 3939, 14, ..., 0, 618, 81]]), array([[ 437, 2, 8027, ..., 1234, 1996, 29],
[1576, 0, 1027, ..., 4199, 1945, 42],
[ 0, 0, 0, ..., 1811, 4815, 85],
...,
[ 465, 224, 0, ..., 0, 2816, 224],
[ 568, 343, 51, ..., 5325, 85, 42],
[3228, 0, 17, ..., 8027, 1183, 0]]), array([[ 842, 0, 51, ..., 10, 0, 295],
[ 0, 0, 85, ..., 0, 26, 81],
[7032, 111, 4080, ..., 667, 10, 4048],
...,
[ 29, 18, 4686, ..., 4985, 12, 1132],
[ 821, 0, 0, ..., 0, 10, 12],
[1530, 2587, 3455, ..., 51, 2207, 479]]), array([[ 42, 1239, 23, ..., 1207, 2503, 67],
[ 12, 1232, 1464, ..., 21, 483, 2204],
[7592, 26, 2854, ..., 112, 223, 94],
...,
[ 709, 4670, 8283, ..., 1132, 18, 5172],
[ 0, 0, 5024, ..., 911, 0, 125],
[2794, 12, 1334, ..., 23, 5007, 55]])]
100
Starting Epoch #1 of 10.
Starting Epoch #1 of 10.
Loss = 81098.984375
Loss = 81180.53125
Loss = 80351.40625
Loss = 79704.5390625
Loss = 79948.578125
Loss = 80354.546875
Loss = 79260.296875
Loss = 78573.0625
Loss = 78911.984375
Loss = 80180.671875
Loss = 78855.625
Loss = 78319.5859375
Loss = 77332.09375
Loss = 77847.59375
Loss = 77584.78125
Loss = 76921.0
Loss = 78775.859375
Loss = 77531.140625
Loss = 76006.703125
Loss = 77455.3125
Loss = 78466.6796875
Loss = 77259.4140625
Loss = 76701.046875
Loss = 75929.0546875
Loss = 78008.4453125
Loss = 76219.7109375
Loss = 75837.0546875
Loss = 76074.515625
Loss = 76193.3984375
Loss = 76968.234375
Loss = 75572.28125
Loss = 77019.40625
Loss = 76605.140625
Loss = 76536.4921875
Loss = 73645.078125
Loss = 74703.46875
Loss = 75555.125
Loss = 76150.734375
Loss = 77419.984375
Loss = 74360.21875
Loss = 75860.96875
Loss = 77016.3515625
Loss = 74354.15625
Loss = 74569.6640625
Loss = 76349.109375
Loss = 74382.7578125
Loss = 75181.0859375
Loss = 77506.234375
Loss = 75453.671875
Loss = 75727.734375
Loss = 77064.7890625
Loss = 72568.5390625
Loss = 74763.953125
Loss = 75226.40625
Loss = 71977.1953125
Loss = 73886.984375
Loss = 74310.609375
Loss = 73779.8125
Loss = 73041.4453125
Loss = 73372.890625
Loss = 74170.0234375
Loss = 71625.921875
Loss = 72991.03125
Loss = 74306.0859375
Loss = 71995.15625
Loss = 73914.84375
Loss = 71469.625
Loss = 72108.8515625
Loss = 72035.921875
Loss = 73183.25
Loss = 71817.359375
Loss = 69037.375
Loss = 72115.546875
Loss = 69831.5703125
Loss = 71537.0625
Loss = 70760.640625
Loss = 73167.8515625
Loss = 70633.375
Loss = 69261.3125
Loss = 70935.3359375
Loss = 69500.84375
Loss = 70282.9921875
Loss = 70884.2890625
Loss = 69378.609375
Loss = 71130.8671875
Loss = 70429.234375
Loss = 69399.3515625
Loss = 68076.734375
Loss = 69318.328125
Loss = 70698.0859375
Loss = 70584.546875
Loss = 68269.203125
Loss = 68969.046875
Loss = 69411.796875
Loss = 69764.6171875
Loss = 67131.671875
Loss = 68557.546875
Loss = 69400.078125
Loss = 67843.234375
Loss = 69779.5625
Loss = 68201.140625
Loss = 68141.703125
Loss = 68617.15625
Loss = 67021.828125
Loss = 67374.578125
Loss = 69211.2109375
Loss = 67953.3125
Loss = 68849.2890625
Loss = 67434.2890625
Loss = 67225.8046875
Loss = 68796.0234375
Loss = 69178.484375
Loss = 66623.3125
Loss = 67912.3828125
Loss = 65492.421875
Loss = 66840.3203125
Loss = 64568.546875
Loss = 66845.578125
Loss = 67550.171875
Loss = 65334.90625
Loss = 69456.109375
Loss = 66369.578125
Loss = 67000.546875
Loss = 66022.421875
Loss = 65443.734375
Loss = 65480.77734375
Loss = 65962.109375
Loss = 65555.0
Loss = 65949.8359375
Loss = 66327.5234375
Loss = 64681.421875
Loss = 66977.078125
Loss = 64438.5234375
Loss = 66098.21875
Loss = 63803.78125
Loss = 65793.6953125
Loss = 65380.0078125
Loss = 65746.765625
Loss = 64206.0
Loss = 63481.68359375
Loss = 63608.44921875
Loss = 63262.3984375
Loss = 63960.03125
Loss = 64243.0
Loss = 63339.640625
Loss = 63940.125
Loss = 66036.453125
Loss = 64497.27734375
Loss = 63655.3203125
Loss = 63204.328125
Loss = 64851.65625
Loss = 62084.9765625
Loss = 65347.53125
Loss = 63119.6640625
Loss = 62860.01171875
Loss = 65611.6328125
Loss = 65526.88671875
Loss = 62037.4375
Loss = 63851.8828125
Loss = 63637.796875
Loss = 63759.76953125
Loss = 64300.625
Loss = 63603.41796875
Loss = 62134.31640625
Loss = 63022.2265625
Loss = 63752.0390625
Loss = 61122.546875
Loss = 61965.40625
Loss = 60764.82421875
Loss = 64073.7578125
Loss = 63792.375
Loss = 62891.09375
Loss = 60925.6484375
Loss = 64671.63671875
Loss = 59842.62890625
Loss = 59981.17578125
Loss = 62107.078125
Loss = 62110.8828125
Loss = 62046.98828125
Loss = 62419.12109375
Loss = 62055.87109375
Loss = 62066.6171875
Loss = 61205.171875
Loss = 61622.203125
Loss = 61501.8828125
Loss = 58952.484375
Loss = 61216.21875
Starting Epoch #2 of 10.
Starting Epoch #2 of 10.
Loss = 60550.77734375
Loss = 63197.34765625
Loss = 61630.73828125
Loss = 60523.0625
Loss = 61516.5703125
Loss = 60744.14453125
Loss = 63256.34375
Loss = 62374.984375
Loss = 63169.14453125
Loss = 60239.390625
Loss = 60028.96484375
Loss = 62405.5390625
Loss = 61760.3984375
Loss = 60122.90625
Loss = 60863.37890625
Loss = 61547.921875
Loss = 62740.82421875
Loss = 61204.44921875
Loss = 60851.01953125
Loss = 60409.74609375
Loss = 59250.19140625
Loss = 58761.71875
Loss = 60045.171875
Loss = 62712.6796875
Loss = 61905.8515625
Loss = 57789.0703125
Loss = 62993.4921875
Loss = 59210.3203125
Loss = 60733.25390625
Loss = 59171.12890625
Loss = 60850.58984375
Loss = 61184.421875
Loss = 59512.5390625
Loss = 59493.109375
Loss = 60192.84375
Loss = 60465.046875
Loss = 60522.546875
Loss = 59970.421875
Loss = 58810.56640625
Loss = 61351.69140625
Loss = 60116.1875
Loss = 58978.234375
Loss = 60970.50390625
Loss = 60321.72265625
Loss = 59886.28515625
Loss = 59257.40625
Loss = 61238.078125
Loss = 56919.765625
Loss = 59880.12890625
Loss = 58565.046875
Loss = 59115.0
Loss = 58941.6796875
Loss = 58800.2734375
Loss = 59756.3984375
Loss = 62329.109375
Loss = 59229.76171875
Loss = 58829.36328125
Loss = 57196.48046875
Loss = 58585.69921875
Loss = 60320.078125
Loss = 57690.3984375
Loss = 58986.15625
Loss = 58526.4296875
Loss = 58651.109375
Loss = 57597.10546875
Loss = 58310.78515625
Loss = 60349.8984375
Loss = 59248.53515625
Loss = 58023.19921875
Loss = 59823.71875
Loss = 57560.2734375
Loss = 59080.078125
Loss = 59432.2109375
Loss = 60306.30078125
Loss = 59421.1953125
Loss = 58516.19140625
Loss = 58294.8671875
Loss = 57395.6328125
Loss = 58768.765625
Loss = 57290.953125
Loss = 57654.703125
Loss = 59026.16796875
Loss = 60744.765625
Loss = 57593.0390625
Loss = 57652.96484375
Loss = 57553.0703125
Loss = 55487.3515625
Loss = 59146.83203125
Loss = 58195.546875
Loss = 58730.3046875
Loss = 57669.1875
Loss = 59337.6875
Loss = 59139.34765625
Loss = 58936.6953125
Loss = 57391.4765625
Loss = 55981.6328125
Loss = 59529.3828125
Loss = 56596.546875
Loss = 57961.2734375
Loss = 57909.90234375
Loss = 60623.2421875
Loss = 56057.07421875
Loss = 56576.7890625
Loss = 57942.421875
Loss = 57467.78125
Loss = 58330.5546875
Loss = 58019.484375
Loss = 58957.80078125
Loss = 59566.1484375
Loss = 57570.19921875
Loss = 58197.21875
Loss = 56574.8125
Loss = 57595.546875
Loss = 56660.19140625
Loss = 58525.75
Loss = 57299.07421875
Loss = 55168.15625
Loss = 57415.34375
Loss = 56837.3046875
Loss = 56895.796875
Loss = 58042.38671875
Loss = 58946.31640625
Loss = 57693.4765625
Loss = 56806.93359375
Loss = 57417.578125
Loss = 57929.96875
Loss = 59524.90234375
Loss = 57110.484375
Loss = 57799.8203125
Loss = 56435.58984375
Loss = 58468.296875
Loss = 58001.921875
Loss = 57819.70703125
Loss = 55635.1875
Loss = 58611.6171875
Loss = 54865.703125
Loss = 56247.01171875
Loss = 56466.046875
Loss = 56431.640625
Loss = 60904.3984375
Loss = 55187.390625
Loss = 59334.71484375
Loss = 58454.4375
Loss = 55550.13671875
Loss = 55649.6171875
Loss = 55281.3984375
Loss = 57161.1328125
Loss = 55268.69921875
Loss = 57084.09375
Loss = 56171.94921875
Loss = 57840.296875
Loss = 58110.06640625
Loss = 57268.80078125
Loss = 57993.984375
Loss = 57547.5
Loss = 58172.1875
Loss = 59432.66015625
Loss = 56699.84375
Loss = 57070.76953125
Loss = 56740.4453125
Loss = 53924.125
Loss = 56721.26953125
Loss = 57143.66796875
Loss = 57841.578125
Loss = 57704.4140625
Loss = 57060.03125
Loss = 56308.0078125
Loss = 56424.4296875
Loss = 57852.8203125
Loss = 56771.2734375
Loss = 57294.9453125
Loss = 55029.3125
Loss = 56993.06640625
Loss = 55670.46875
Loss = 54640.92578125
Loss = 57987.265625
Loss = 55636.765625
Loss = 56342.41015625
Loss = 58860.7265625
Loss = 59617.67578125
Loss = 54880.6015625
Loss = 57033.20703125
Loss = 54495.80078125
Loss = 56116.078125
Loss = 55666.7265625
Loss = 57006.375
Loss = 55246.89453125
Starting Epoch #3 of 10.
Starting Epoch #3 of 10.
Loss = 54832.5390625
Loss = 57242.0546875
Loss = 54945.7890625
Loss = 56454.96484375
Loss = 55491.75
Loss = 57685.7421875
Loss = 57679.5546875
Loss = 57026.6875
Loss = 55010.328125
Loss = 54570.83984375
Loss = 55978.0625
Loss = 55255.69921875
Loss = 58520.44140625
Loss = 54988.078125
Loss = 54094.93359375
Loss = 56261.34765625
Loss = 55888.88671875
Loss = 55713.5625
Loss = 55415.46484375
Loss = 53849.984375
Loss = 57115.71484375
Loss = 55703.859375
Loss = 55598.078125
Loss = 52752.1015625
Loss = 54330.453125
Loss = 57418.35546875
Loss = 56646.828125
Loss = 56510.78515625
Loss = 53993.79296875
Loss = 54210.1875
Loss = 57508.94921875
Loss = 54221.5703125
Loss = 54536.984375
Loss = 55501.4765625
Loss = 52981.484375
Loss = 54167.0546875
Loss = 55613.9921875
Loss = 56212.50390625
Loss = 56435.06640625
Loss = 55666.4921875
Loss = 55758.11328125
Loss = 56558.4453125
Loss = 53315.08984375
Loss = 57163.9296875
Loss = 56394.875
Loss = 55253.5703125
Loss = 56303.83203125
Loss = 57250.140625
Loss = 54596.8203125
Loss = 55284.96875
Loss = 55799.078125
Loss = 55866.609375
Loss = 56116.6484375
Loss = 54497.34375
Loss = 56244.234375
Loss = 57297.3515625
Loss = 56504.0546875
Loss = 56777.8125
Loss = 54789.609375
Loss = 56526.91015625
Loss = 54752.234375
Loss = 54996.67578125
Loss = 54196.4375
Loss = 55030.1953125
Loss = 56163.34765625
Loss = 52373.70703125
Loss = 55276.53125
Loss = 55867.9765625
Loss = 54526.82421875
Loss = 55567.7890625
Loss = 56148.09375
Loss = 55454.140625
Loss = 56226.359375
Loss = 58379.703125
Loss = 51589.01171875
Loss = 56306.76171875
Loss = 54396.48046875
Loss = 55606.9375
Loss = 56852.453125
Loss = 55127.53125
Loss = 56918.08203125
Loss = 58164.3828125
Loss = 56190.375
Loss = 55035.90234375
Loss = 56102.546875
Loss = 58799.515625
Loss = 53798.453125
Loss = 56090.8671875
Loss = 57098.90625
Loss = 56790.49609375
Loss = 57276.5
Loss = 55161.8984375
Loss = 55748.94140625
Loss = 56886.359375
Loss = 55976.06640625
Loss = 56474.6953125
Loss = 57172.11328125
Loss = 57489.1796875
Loss = 55662.88671875
Loss = 56499.04296875
Loss = 54898.9140625
Loss = 55851.66796875
Loss = 57744.5
Loss = 57498.734375
Loss = 53738.62109375
Loss = 56447.734375
Loss = 55054.0
Loss = 58149.828125
Loss = 56039.15625
Loss = 55978.28125
Loss = 57401.65234375
Loss = 54980.09765625
Loss = 55212.8828125
Loss = 55220.80078125
Loss = 56376.7734375
Loss = 56255.8515625
Loss = 56045.91796875
Loss = 55556.6953125
Loss = 54351.65234375
Loss = 54422.328125
Loss = 54931.21875
Loss = 57538.796875
Loss = 54976.03515625
Loss = 56647.34375
Loss = 55737.2265625
Loss = 56125.8828125
Loss = 56390.359375
Loss = 53276.5
Loss = 58380.3125
Loss = 56729.96875
Loss = 54769.953125
Loss = 54383.7734375
Loss = 59670.40625
Loss = 58494.1171875
Loss = 55373.59765625
Loss = 56135.046875
Loss = 53299.4296875
Loss = 54846.796875
Loss = 54969.171875
Loss = 53109.29296875
Loss = 55727.3671875
Loss = 54603.39453125
Loss = 52828.12890625
Loss = 55653.375
Loss = 54395.6640625
Loss = 57328.453125
Loss = 54979.4140625
Loss = 53913.53515625
Loss = 55570.5078125
Loss = 54014.2109375
Loss = 53944.34765625
Loss = 56544.40234375
Loss = 55359.671875
Loss = 53563.6640625
Loss = 54174.296875
Loss = 54808.9921875
Loss = 55330.90625
Loss = 57554.3515625
Loss = 54573.671875
Loss = 56755.84375
Loss = 54055.46875
Loss = 55433.8671875
Loss = 56137.6484375
Loss = 54998.34375
Loss = 54972.56640625
Loss = 55103.453125
Loss = 57389.6015625
Loss = 53200.734375
Loss = 56546.21875
Loss = 54725.9765625
Loss = 56152.9609375
Loss = 57556.046875
Loss = 55812.05859375
Loss = 57260.8203125
Loss = 56526.703125
Loss = 55697.34765625
Loss = 54230.53125
Loss = 55029.015625
Loss = 54311.25
Loss = 53971.703125
Loss = 58581.9140625
Loss = 58260.7109375
Loss = 53426.67578125
Loss = 55191.4921875
Loss = 55870.71875
Loss = 53401.75390625
Loss = 60144.89453125
Starting Epoch #4 of 10.
Starting Epoch #4 of 10.
Loss = 54697.4921875
Loss = 53166.28125
Loss = 57147.0234375
Loss = 53765.1015625
Loss = 54663.1171875
Loss = 55549.3984375
Loss = 53301.203125
Loss = 52938.77734375
Loss = 56922.93359375
Loss = 55386.38671875
Loss = 55236.390625
Loss = 53883.36328125
Loss = 55124.03125
Loss = 54284.375
Loss = 52245.3515625
Loss = 57153.15234375
Loss = 55164.80859375
Loss = 55701.078125
Loss = 53617.015625
Loss = 54338.5703125
Loss = 54582.0234375
Loss = 56035.625
Loss = 56997.4375
Loss = 55553.296875
Loss = 54554.27734375
Loss = 57123.7109375
Loss = 54947.6484375
Loss = 54389.8984375
Loss = 53210.890625
Loss = 56396.4140625
Loss = 52742.1484375
Loss = 56538.9296875
Loss = 54346.60546875
Loss = 53655.37109375
Loss = 56065.875
Loss = 54136.0546875
Loss = 53726.64453125
Loss = 53912.01171875
Loss = 55782.8671875
Loss = 54445.41796875
Loss = 53866.546875
Loss = 56639.7890625
Loss = 52987.7578125
Loss = 53224.18359375
Loss = 54507.0703125
Loss = 55547.8359375
Loss = 53154.9140625
Loss = 54142.7265625
Loss = 55100.9765625
Loss = 55994.2890625
Loss = 54834.41796875
Loss = 54226.57421875
Loss = 55902.3203125
Loss = 53222.26171875
Loss = 54969.2421875
Loss = 55081.9375
Loss = 54184.58984375
Loss = 53388.9765625
Loss = 55100.7578125
Loss = 53409.0625
Loss = 53783.8203125
Loss = 54421.9453125
Loss = 54927.41796875
Loss = 53428.40234375
Loss = 53265.984375
Loss = 52574.75
Loss = 54699.3359375
Loss = 51449.35546875
Loss = 53570.3984375
Loss = 55844.7421875
Loss = 53249.8359375
Loss = 55259.171875
Loss = 57307.15625
Loss = 54738.7734375
Loss = 54266.92578125
Loss = 55526.41796875
Loss = 52460.609375
Loss = 53912.0078125
Loss = 59854.1484375
Loss = 55017.421875
Loss = 52837.08984375
Loss = 54300.1796875
Loss = 57166.265625
Loss = 53243.62109375
Loss = 54040.9609375
Loss = 56335.5078125
Loss = 51312.796875
Loss = 54300.984375
Loss = 56139.5859375
Loss = 54279.0390625
Loss = 55231.4921875
Loss = 54174.15234375
Loss = 55142.3203125
Loss = 52980.36328125
Loss = 54575.734375
Loss = 53259.75
Loss = 55637.9609375
Loss = 54524.98046875
Loss = 54179.56640625
Loss = 56508.96875
Loss = 55366.4296875
Loss = 53818.046875
Loss = 54914.75
Loss = 52658.546875
Loss = 53438.61328125
Loss = 55329.37890625
Loss = 52912.3828125
Loss = 56770.3359375
Loss = 55428.8125
Loss = 53393.9453125
Loss = 56115.29296875
Loss = 52442.8125
Loss = 53749.8203125
Loss = 54970.2734375
Loss = 55200.015625
Loss = 54427.578125
Loss = 56928.8671875
Loss = 53018.36328125
Loss = 53938.66015625
Loss = 54454.7421875
Loss = 54397.4765625
Loss = 54086.7734375
Loss = 56550.31640625
Loss = 53363.7890625
Loss = 54317.3984375
Loss = 54283.71875
Loss = 53295.5078125
Loss = 55348.8828125
Loss = 54062.8046875
Loss = 54739.5234375
Loss = 54334.9296875
Loss = 55066.65234375
Loss = 56276.1640625
Loss = 54440.2734375
Loss = 54998.7109375
Loss = 54136.4296875
Loss = 54944.0859375
Loss = 54571.84375
Loss = 53747.90234375
Loss = 51946.890625
Loss = 55788.859375
Loss = 53652.0703125
Loss = 53597.3125
Loss = 55053.32421875
Loss = 54593.359375
Loss = 56262.3046875
Loss = 57542.34765625
Loss = 49972.828125
Loss = 53849.8046875
Loss = 53441.7421875
Loss = 50783.7421875
Loss = 55668.41015625
Loss = 52845.2421875
Loss = 53474.28125
Loss = 57110.203125
Loss = 54667.0078125
Loss = 51688.2734375
Loss = 55204.796875
Loss = 58078.0859375
Loss = 50728.4921875
Loss = 54337.8984375
Loss = 54630.43359375
Loss = 53161.8125
Loss = 54054.4453125
Loss = 59345.953125
Loss = 52272.45703125
Loss = 52680.28515625
Loss = 54055.0625
Loss = 54534.9375
Loss = 52689.171875
Loss = 55083.0390625
Loss = 54810.6484375
Loss = 55782.60546875
Loss = 54589.0078125
Loss = 54731.28125
Loss = 53594.25
Loss = 52743.26953125
Loss = 53556.5703125
Loss = 51867.484375
Loss = 52709.0625
Loss = 54434.6953125
Loss = 52610.7421875
Loss = 51941.3828125
Loss = 55181.1171875
Loss = 53693.60546875
Loss = 55557.90234375
Loss = 53441.671875
Starting Epoch #5 of 10.
Starting Epoch #5 of 10.
Loss = 54679.625
Loss = 52066.78125
Loss = 53593.85546875
Loss = 53364.55078125
Loss = 54205.546875
Loss = 53458.8984375
Loss = 53807.65625
Loss = 55737.3828125
Loss = 54833.05078125
Loss = 52939.59375
Loss = 53536.14453125
Loss = 56381.890625
Loss = 54165.7734375
Loss = 52967.22265625
Loss = 54501.65625
Loss = 53004.765625
Loss = 54442.7890625
Loss = 55666.6171875
Loss = 54789.38671875
Loss = 52474.046875
Loss = 54564.359375
Loss = 56125.3671875
Loss = 52603.0546875
Loss = 52833.07421875
Loss = 55563.5703125
Loss = 55523.9921875
Loss = 53668.890625
Loss = 53279.125
Loss = 55895.6171875
Loss = 52954.8203125
Loss = 53911.640625
Loss = 54966.546875
Loss = 53295.203125
Loss = 59564.984375
Loss = 51600.51953125
Loss = 57637.796875
Loss = 54394.23046875
Loss = 54142.890625
Loss = 51564.0
Loss = 54440.171875
Loss = 54302.6796875
Loss = 54683.43359375
Loss = 57157.35546875
Loss = 50467.06640625
Loss = 54359.0078125
Loss = 53891.81640625
Loss = 52171.15234375
Loss = 53897.0546875
Loss = 55656.140625
Loss = 52587.8515625
Loss = 51378.5546875
Loss = 53427.34375
Loss = 52155.51953125
Loss = 54527.265625
Loss = 56823.5390625
Loss = 52771.8828125
Loss = 54970.2890625
Loss = 53811.52734375
Loss = 56805.9375
Loss = 52679.90234375
Loss = 52694.58203125
Loss = 55531.0703125
Loss = 53255.4453125
Loss = 54921.9609375
Loss = 53672.3515625
Loss = 53551.8828125
Loss = 54671.56640625
Loss = 54423.453125
Loss = 54202.55078125
Loss = 56231.40234375
Loss = 56060.2890625
Loss = 54288.7109375
Loss = 53392.75
Loss = 56624.3984375
Loss = 55706.8984375
Loss = 54824.3046875
Loss = 50735.2421875
Loss = 53531.1953125
Loss = 52110.9296875
Loss = 52018.984375
Loss = 49416.65234375
Loss = 53465.2890625
Loss = 52935.09765625
Loss = 54984.81640625
Loss = 55107.13671875
Loss = 55989.578125
Loss = 52326.40625
Loss = 53732.4375
Loss = 54866.71875
Loss = 53179.11328125
Loss = 53955.28125
Loss = 53635.328125
Loss = 52934.3125
Loss = 52266.49609375
Loss = 53491.3671875
Loss = 55620.79296875
Loss = 52600.94921875
Loss = 55062.8828125
Loss = 52489.59375
Loss = 54171.578125
Loss = 54670.2578125
Loss = 53587.84375
Loss = 54121.39453125
Loss = 52442.49609375
Loss = 53617.234375
Loss = 52988.296875
Loss = 51969.2421875
Loss = 53944.41015625
Loss = 52084.90625
Loss = 57046.04296875
Loss = 52567.66015625
Loss = 52347.328125
Loss = 52594.734375
Loss = 51445.08984375
Loss = 54444.46875
Loss = 52364.734375
Loss = 54349.14453125
Loss = 53411.9453125
Loss = 53580.5
Loss = 53908.8515625
Loss = 53389.93359375
Loss = 53183.3828125
Loss = 52428.9140625
Loss = 55126.3203125
Loss = 51615.828125
Loss = 52359.1328125
Loss = 54306.78125
Loss = 53782.84375
Loss = 54810.1796875
Loss = 54878.26953125
Loss = 54283.703125
Loss = 52690.8359375
Loss = 53762.52734375
Loss = 52683.328125
Loss = 54997.9375
Loss = 54784.80859375
Loss = 54614.9375
Loss = 53243.70703125
Loss = 53927.11328125
Loss = 55592.8984375
Loss = 53788.8828125
Loss = 52957.6953125
Loss = 53865.953125
Loss = 55225.3125
Loss = 55364.59375
Loss = 52975.92578125
Loss = 52005.2109375
Loss = 56812.1015625
Loss = 55761.921875
Loss = 53892.8671875
Loss = 52473.55078125
Loss = 56544.171875
Loss = 53238.41015625
Loss = 55896.64453125
Loss = 54004.73828125
Loss = 53474.76953125
Loss = 57013.015625
Loss = 53036.8125
Loss = 54672.55859375
Loss = 54027.67578125
Loss = 52893.984375
Loss = 51211.10546875
Loss = 54283.81640625
Loss = 55071.13671875
Loss = 52795.33203125
Loss = 53428.43359375
Loss = 53529.44140625
Loss = 54273.2109375
Loss = 52282.7578125
Loss = 53061.78125
Loss = 58840.359375
Loss = 55040.265625
Loss = 54869.171875
Loss = 53826.87890625
Loss = 54351.30078125
Loss = 53306.671875
Loss = 54457.0859375
Loss = 55186.7734375
Loss = 52886.828125
Loss = 54495.59375
Loss = 54961.88671875
Loss = 50325.09375
Loss = 54556.64453125
Loss = 52205.1640625
Loss = 54658.390625
Loss = 53860.328125
Loss = 55662.05859375
Starting Epoch #6 of 10.
Starting Epoch #6 of 10.
Loss = 52422.40625
Loss = 54842.9296875
Loss = 54318.0390625
Loss = 53857.1640625
Loss = 53563.2109375
Loss = 56636.41796875
Loss = 54662.7578125
Loss = 54068.4609375
Loss = 53829.99609375
Loss = 52096.9609375
Loss = 56015.59375
Loss = 58716.890625
Loss = 53879.75
Loss = 55158.6171875
Loss = 54134.9921875
Loss = 52310.890625
Loss = 53715.0
Loss = 56471.60546875
Loss = 53382.09375
Loss = 54789.78515625
Loss = 54119.6484375
Loss = 52743.6484375
Loss = 51915.078125
Loss = 54229.1328125
Loss = 54958.2890625
Loss = 55265.0625
Loss = 51375.09375
Loss = 57323.8203125
Loss = 51729.3828125
Loss = 52553.796875
Loss = 54155.8203125
Loss = 54253.8046875
Loss = 53450.09375
Loss = 52056.7421875
Loss = 55250.52734375
Loss = 52213.9375
Loss = 52970.59375
Loss = 51863.9296875
Loss = 54470.1640625
Loss = 54276.4609375
Loss = 53967.5078125
Loss = 52577.21484375
Loss = 52440.2890625
Loss = 53478.85546875
Loss = 53427.05078125
Loss = 55074.5234375
Loss = 52226.484375
Loss = 53052.3828125
Loss = 55426.140625
Loss = 53071.40625
Loss = 53508.75
Loss = 50273.4921875
Loss = 55481.1796875
Loss = 58994.6171875
Loss = 52218.06640625
Loss = 56637.703125
Loss = 53976.28515625
Loss = 54530.0859375
Loss = 52037.5625
Loss = 51747.07421875
Loss = 54112.61328125
Loss = 56949.390625
Loss = 54189.8359375
Loss = 52969.7734375
Loss = 54641.3515625
Loss = 53262.203125
Loss = 55310.6953125
Loss = 52841.328125
Loss = 56735.0390625
Loss = 52693.62890625
Loss = 51095.81640625
Loss = 53071.84375
Loss = 53037.8671875
Loss = 52049.140625
Loss = 54750.04296875
Loss = 54331.85546875
Loss = 55290.4921875
Loss = 51559.03515625
Loss = 53826.8046875
Loss = 51665.234375
Loss = 53494.5234375
Loss = 54663.66015625
Loss = 53027.8125
Loss = 52957.125
Loss = 53760.46875
Loss = 53066.8359375
Loss = 52169.484375
Loss = 54848.62890625
Loss = 55552.296875
Loss = 52763.0390625
Loss = 53468.71875
Loss = 52855.82421875
Loss = 51267.6328125
Loss = 51944.5234375
Loss = 54390.9296875
Loss = 52331.27734375
Loss = 53589.90625
Loss = 54971.67578125
Loss = 52308.3828125
Loss = 56120.609375
Loss = 53048.0078125
Loss = 54095.53125
Loss = 54898.15625
Loss = 53068.30859375
Loss = 54765.84375
Loss = 53663.73046875
Loss = 54376.078125
Loss = 52783.30859375
Loss = 50732.37109375
Loss = 52819.6328125
Loss = 52244.703125
Loss = 53387.0390625
Loss = 51289.5078125
Loss = 54336.24609375
Loss = 53358.50390625
Loss = 52833.90625
Loss = 53351.421875
Loss = 51382.93359375
Loss = 53259.9765625
Loss = 51425.6953125
Loss = 53691.71875
Loss = 51956.6484375
Loss = 54474.9609375
Loss = 51777.359375
Loss = 52534.484375
Loss = 55120.79296875
Loss = 56427.49609375
Loss = 49834.8515625
Loss = 52720.2421875
Loss = 52996.390625
Loss = 53352.65625
Loss = 56220.0703125
Loss = 54383.75390625
Loss = 53786.75
Loss = 53774.578125
Loss = 54261.90625
Loss = 53018.6171875
Loss = 53157.921875
Loss = 55209.38671875
Loss = 53987.1328125
Loss = 53675.96875
Loss = 51634.3046875
Loss = 52945.34765625
Loss = 51772.7265625
Loss = 52996.48828125
Loss = 51563.46484375
Loss = 51907.61328125
Loss = 48542.30859375
Loss = 52278.4765625
Loss = 54232.203125
Loss = 54559.8203125
Loss = 55995.56640625
Loss = 53855.91015625
Loss = 54470.609375
Loss = 52744.54296875
Loss = 51498.859375
Loss = 54044.109375
Loss = 52392.59375
Loss = 54524.3984375
Loss = 52496.53125
Loss = 53518.7890625
Loss = 51358.3046875
Loss = 52769.26953125
Loss = 52063.171875
Loss = 49847.2734375
Loss = 55559.21484375
Loss = 53553.234375
Loss = 53521.8046875
Loss = 52537.7890625
Loss = 54366.8984375
Loss = 54152.80078125
Loss = 54598.03125
Loss = 54877.2265625
Loss = 54545.17578125
Loss = 52109.4296875
Loss = 54485.8984375
Loss = 53699.73828125
Loss = 53281.046875
Loss = 55623.55078125
Loss = 54146.7421875
Loss = 55287.0078125
Loss = 53237.77734375
Loss = 52389.68359375
Loss = 52748.18359375
Loss = 53570.18359375
Loss = 55381.3828125
Loss = 52299.4375
Starting Epoch #7 of 10.
Starting Epoch #7 of 10.
Loss = 54710.125
Loss = 53957.42578125
Loss = 54332.75
Loss = 53607.16015625
Loss = 51379.91015625
Loss = 53437.9609375
Loss = 54216.83203125
Loss = 51606.0859375
Loss = 50531.0234375
Loss = 53719.125
Loss = 52452.9921875
Loss = 52516.6171875
Loss = 53106.1328125
Loss = 51655.10546875
Loss = 55086.53125
Loss = 52115.3125
Loss = 52610.37890625
Loss = 49914.98046875
Loss = 53965.35546875
Loss = 52422.5859375
Loss = 53346.40625
Loss = 52065.37890625
Loss = 53907.828125
Loss = 53606.96875
Loss = 53979.8984375
Loss = 53165.70703125
Loss = 53105.9765625
Loss = 54294.80078125
Loss = 52429.52734375
Loss = 53334.0703125
Loss = 56217.03515625
Loss = 52112.2890625
Loss = 55110.2890625
Loss = 51407.359375
Loss = 52939.39453125
Loss = 52579.42578125
Loss = 52314.73828125
Loss = 51935.578125
Loss = 58702.73046875
Loss = 53607.921875
Loss = 53090.6171875
Loss = 53013.19140625
Loss = 54587.61328125
Loss = 54905.44140625
Loss = 56791.07421875
Loss = 55072.2109375
Loss = 52672.0625
Loss = 51406.8984375
Loss = 51750.390625
Loss = 52836.734375
Loss = 52214.515625
Loss = 52777.5
Loss = 51918.2734375
Loss = 54888.484375
Loss = 52692.69921875
Loss = 51385.171875
Loss = 52641.296875
Loss = 53661.21875
Loss = 58137.60546875
Loss = 52700.390625
Loss = 53027.515625
Loss = 51770.9609375
Loss = 51173.34375
Loss = 53246.1484375
Loss = 53728.3359375
Loss = 50343.921875
Loss = 52998.2734375
Loss = 53842.046875
Loss = 54479.4140625
Loss = 51262.57421875
Loss = 54498.7421875
Loss = 54456.140625
Loss = 55264.453125
Loss = 51533.1640625
Loss = 53616.79296875
Loss = 54273.32421875
Loss = 54737.55859375
Loss = 50654.765625
Loss = 53517.015625
Loss = 53797.265625
Loss = 53872.7265625
Loss = 54186.4453125
Loss = 54364.06640625
Loss = 55830.2109375
Loss = 49017.703125
Loss = 53245.8515625
Loss = 51865.921875
Loss = 52299.2109375
Loss = 53130.22265625
Loss = 53413.21484375
Loss = 54676.2109375
Loss = 52904.8359375
Loss = 54519.80859375
Loss = 54434.9609375
Loss = 52647.3046875
Loss = 51687.4453125
Loss = 52539.48828125
Loss = 51786.125
Loss = 52733.85546875
Loss = 53870.5625
Loss = 54655.4140625
Loss = 53946.09375
Loss = 51839.9921875
Loss = 52505.1015625
Loss = 53380.7421875
Loss = 50859.296875
Loss = 51304.62109375
Loss = 55078.9140625
Loss = 52839.390625
Loss = 51985.9609375
Loss = 55060.5
Loss = 53292.43359375
Loss = 53353.859375
Loss = 54359.0625
Loss = 53060.94921875
Loss = 51879.37109375
Loss = 53299.0234375
Loss = 54693.953125
Loss = 51010.25
Loss = 54097.6484375
Loss = 51559.5
Loss = 51259.4921875
Loss = 54221.5390625
Loss = 52225.3203125
Loss = 54693.859375
Loss = 51517.31640625
Loss = 54538.32421875
Loss = 52317.4140625
Loss = 53768.29296875
Loss = 54236.65625
Loss = 52244.421875
Loss = 53458.4453125
Loss = 52771.15625
Loss = 55135.90234375
Loss = 54213.15625
Loss = 56649.62890625
Loss = 55801.37890625
Loss = 53430.625
Loss = 51694.7265625
Loss = 52680.125
Loss = 54584.28125
Loss = 55200.421875
Loss = 52877.4296875
Loss = 55846.671875
Loss = 54595.203125
Loss = 55231.859375
Loss = 53214.3515625
Loss = 53574.46875
Loss = 57228.015625
Loss = 51843.890625
Loss = 53110.515625
Loss = 55867.3984375
Loss = 53324.20703125
Loss = 54303.0390625
Loss = 53771.37890625
Loss = 53366.609375
Loss = 51676.52734375
Loss = 53356.3203125
Loss = 53006.421875
Loss = 52738.4140625
Loss = 53673.34375
Loss = 54095.375
Loss = 52516.9375
Loss = 52847.9375
Loss = 52706.859375
Loss = 50636.01171875
Loss = 54177.046875
Loss = 54407.609375
Loss = 52906.3125
Loss = 55057.7109375
Loss = 52558.2109375
Loss = 55988.53515625
Loss = 56090.234375
Loss = 53709.5078125
Loss = 53965.1640625
Loss = 52412.91015625
Loss = 54718.578125
Loss = 52350.0703125
Loss = 53819.6796875
Loss = 51974.02734375
Loss = 54659.328125
Loss = 49719.0703125
Loss = 50641.171875
Loss = 55031.58203125
Loss = 54398.3828125
Loss = 52495.85546875
Loss = 56352.109375
Starting Epoch #8 of 10.
Starting Epoch #8 of 10.
Loss = 51212.7109375
Loss = 52707.734375
Loss = 49663.75
Loss = 55912.0078125
Loss = 51775.53125
Loss = 52920.84765625
Loss = 49984.3828125
Loss = 52833.26953125
Loss = 52246.609375
Loss = 53255.375
Loss = 53101.3671875
Loss = 51743.2890625
Loss = 55884.83203125
Loss = 51622.40625
Loss = 53094.1875
Loss = 51847.546875
Loss = 55116.9296875
Loss = 54647.44140625
Loss = 54135.078125
Loss = 51981.90625
Loss = 52906.4453125
Loss = 51241.953125
Loss = 51610.6875
Loss = 53747.140625
Loss = 52853.57421875
Loss = 54156.80078125
Loss = 53334.28125
Loss = 52300.03515625
Loss = 53396.3984375
Loss = 52524.90234375
Loss = 52914.3515625
Loss = 50751.6796875
Loss = 53696.6953125
Loss = 53159.203125
Loss = 53538.09375
Loss = 52490.9921875
Loss = 53028.8828125
Loss = 51368.4765625
Loss = 54527.109375
Loss = 51390.5546875
Loss = 50177.5234375
Loss = 53190.51953125
Loss = 55535.3828125
Loss = 53687.734375
Loss = 54770.40625
Loss = 51408.0625
Loss = 53772.6640625
Loss = 52120.8671875
Loss = 52658.765625
Loss = 54031.61328125
Loss = 52097.01171875
Loss = 52216.18359375
Loss = 53566.4296875
Loss = 52628.28125
Loss = 53321.56640625
Loss = 54583.7734375
Loss = 54949.0625
Loss = 51187.375
Loss = 51610.734375
Loss = 53662.9609375
Loss = 53062.03515625
Loss = 53991.70703125
Loss = 52432.15234375
Loss = 51323.8671875
Loss = 55288.671875
Loss = 53814.046875
Loss = 58023.5
Loss = 53657.296875
Loss = 53627.578125
Loss = 55954.109375
Loss = 52590.2734375
Loss = 54854.05078125
Loss = 53495.15234375
Loss = 53751.203125
Loss = 52117.08203125
Loss = 53757.6484375
Loss = 52247.81640625
Loss = 54243.4375
Loss = 55012.3203125
Loss = 56012.984375
Loss = 51886.921875
Loss = 58615.8828125
Loss = 54782.82421875
Loss = 55183.70703125
Loss = 54219.40234375
Loss = 52297.49609375
Loss = 52448.48828125
Loss = 51654.41015625
Loss = 53202.27734375
Loss = 54658.2421875
Loss = 54567.3125
Loss = 54406.05859375
Loss = 48909.3515625
Loss = 51471.1328125
Loss = 51635.0234375
Loss = 52156.10546875
Loss = 52335.78125
Loss = 53324.5625
Loss = 55161.1015625
Loss = 51948.03515625
Loss = 53192.91015625
Loss = 54388.7578125
Loss = 55179.65234375
Loss = 54085.6875
Loss = 52951.9453125
Loss = 53103.3125
Loss = 55355.8515625
Loss = 53079.91796875
Loss = 51311.125
Loss = 53470.375
Loss = 51393.91796875
Loss = 53370.34375
Loss = 53430.7578125
Loss = 57214.75390625
Loss = 55408.359375
Loss = 56245.15625
Loss = 51870.078125
Loss = 54636.5234375
Loss = 51524.75
Loss = 54930.56640625
Loss = 53995.22265625
Loss = 51392.453125
Loss = 49971.0
Loss = 55892.3125
Loss = 51011.41796875
Loss = 56159.9140625
Loss = 53028.4375
Loss = 54473.25
Loss = 52339.546875
Loss = 53850.359375
Loss = 55609.359375
Loss = 55024.171875
Loss = 53989.0078125
Loss = 54501.703125
Loss = 53255.96875
Loss = 52541.4765625
Loss = 53923.421875
Loss = 53712.21875
Loss = 54211.078125
Loss = 54005.3046875
Loss = 52764.69921875
Loss = 52888.85546875
Loss = 52717.33984375
Loss = 51542.2109375
Loss = 54504.578125
Loss = 53341.05859375
Loss = 53421.15234375
Loss = 53588.7421875
Loss = 53087.2265625
Loss = 57336.3984375
Loss = 55350.35546875
Loss = 52941.8125
Loss = 54244.703125
Loss = 56509.875
Loss = 52606.35546875
Loss = 52421.5
Loss = 53712.2734375
Loss = 52800.09765625
Loss = 54705.86328125
Loss = 56069.25
Loss = 52661.390625
Loss = 51391.6875
Loss = 55527.20703125
Loss = 56127.4296875
Loss = 53349.109375
Loss = 52839.4453125
Loss = 53393.5546875
Loss = 53697.68359375
Loss = 54188.96484375
Loss = 54211.68359375
Loss = 52183.5
Loss = 53392.46484375
Loss = 51551.5546875
Loss = 53628.4375
Loss = 53789.7109375
Loss = 52890.7265625
Loss = 55978.56640625
Loss = 52765.66796875
Loss = 50966.6875
Loss = 54504.0546875
Loss = 53986.8046875
Loss = 52957.28125
Loss = 54501.10546875
Loss = 51691.765625
Loss = 54527.84765625
Loss = 52952.671875
Loss = 54534.953125
Starting Epoch #9 of 10.
Starting Epoch #9 of 10.
Loss = 54142.3828125
Loss = 54958.07421875
Loss = 53849.89453125
Loss = 53301.375
Loss = 51594.3046875
Loss = 54798.34375
Loss = 53674.4609375
Loss = 52840.79296875
Loss = 53788.421875
Loss = 51445.83203125
Loss = 51070.3984375
Loss = 54439.73046875
Loss = 52972.1875
Loss = 53837.2265625
Loss = 55265.96484375
Loss = 54972.24609375
Loss = 54222.81640625
Loss = 52805.140625
Loss = 52691.6796875
Loss = 53184.29296875
Loss = 52778.4375
Loss = 53952.484375
Loss = 53450.2421875
Loss = 50910.3515625
Loss = 53520.140625
Loss = 54335.79296875
Loss = 53108.484375
Loss = 52581.90625
Loss = 53036.63671875
Loss = 52812.17578125
Loss = 54228.203125
Loss = 53812.58984375
Loss = 55957.0859375
Loss = 55329.99609375
Loss = 53025.07421875
Loss = 55234.421875
Loss = 53462.2421875
Loss = 52800.9921875
Loss = 54941.859375
Loss = 56058.65625
Loss = 51564.69921875
Loss = 51896.515625
Loss = 51525.1875
Loss = 51734.44921875
Loss = 52436.05859375
Loss = 52116.59765625
Loss = 54370.7734375
Loss = 54001.375
Loss = 55846.60546875
Loss = 49529.546875
Loss = 53560.65625
Loss = 51832.4921875
Loss = 52678.25390625
Loss = 51612.75
Loss = 52113.9140625
Loss = 55731.828125
Loss = 53198.9375
Loss = 48965.8671875
Loss = 52749.7890625
Loss = 54171.62109375
Loss = 56098.953125
Loss = 54589.94140625
Loss = 54494.3359375
Loss = 54394.015625
Loss = 55034.8359375
Loss = 51101.375
Loss = 57178.015625
Loss = 53551.72265625
Loss = 51633.328125
Loss = 54925.21875
Loss = 51288.4765625
Loss = 54034.1640625
Loss = 54421.984375
Loss = 52358.03515625
Loss = 53255.8984375
Loss = 51714.359375
Loss = 53482.1015625
Loss = 53947.390625
Loss = 54516.625
Loss = 52223.15625
Loss = 51443.3203125
Loss = 53081.80859375
Loss = 52444.015625
Loss = 51043.01953125
Loss = 52356.4765625
Loss = 54505.62890625
Loss = 53595.171875
Loss = 54010.3125
Loss = 52650.5390625
Loss = 52791.92578125
Loss = 51409.12890625
Loss = 55086.87109375
Loss = 53403.42578125
Loss = 54282.58203125
Loss = 53151.0390625
Loss = 53859.8359375
Loss = 49763.8203125
Loss = 52463.99609375
Loss = 51851.328125
Loss = 51818.73046875
Loss = 55621.15234375
Loss = 51470.9375
Loss = 52774.640625
Loss = 53584.6015625
Loss = 53630.328125
Loss = 52922.734375
Loss = 59114.078125
Loss = 52776.203125
Loss = 49960.578125
Loss = 52142.9765625
Loss = 51891.3671875
Loss = 52541.6328125
Loss = 54605.6875
Loss = 52285.1796875
Loss = 54381.05078125
Loss = 52750.83984375
Loss = 52333.3984375
Loss = 53129.20703125
Loss = 52298.1640625
Loss = 51527.2265625
Loss = 58177.9765625
Loss = 52602.42578125
Loss = 53248.828125
Loss = 54491.28125
Loss = 52920.2265625
Loss = 51565.5546875
Loss = 52153.9921875
Loss = 54634.5234375
Loss = 54311.90625
Loss = 52081.06640625
Loss = 55056.03515625
Loss = 56267.359375
Loss = 52564.2265625
Loss = 51895.984375
Loss = 53123.03125
Loss = 50159.7890625
Loss = 54958.375
Loss = 52737.296875
Loss = 56119.421875
Loss = 52907.4453125
Loss = 52492.609375
Loss = 52939.1953125
Loss = 50832.1875
Loss = 53899.8515625
Loss = 56521.875
Loss = 52317.15234375
Loss = 49791.91015625
Loss = 52361.296875
Loss = 52962.984375
Loss = 53159.046875
Loss = 53587.8828125
Loss = 51556.4609375
Loss = 51716.6171875
Loss = 52946.234375
Loss = 53513.0390625
Loss = 53391.16015625
Loss = 53863.59375
Loss = 50334.6171875
Loss = 56062.19921875
Loss = 54540.2109375
Loss = 53295.8984375
Loss = 50596.546875
Loss = 52666.45703125
Loss = 55241.5078125
Loss = 54789.32421875
Loss = 56048.93359375
Loss = 53778.6015625
Loss = 54841.82421875
Loss = 53014.46484375
Loss = 55546.51953125
Loss = 52770.40625
Loss = 51742.2578125
Loss = 53597.53515625
Loss = 53706.7578125
Loss = 57085.27734375
Loss = 53287.0234375
Loss = 53974.0
Loss = 50510.6015625
Loss = 53593.890625
Loss = 51955.7890625
Loss = 55010.9765625
Loss = 50949.09375
Loss = 51402.89453125
Loss = 52999.33984375
Loss = 53038.6484375
Loss = 51721.859375
Loss = 53256.23046875
Starting Epoch #10 of 10.
Starting Epoch #10 of 10.
Loss = 54717.96875
Loss = 54843.4609375
Loss = 54284.43359375
Loss = 55477.046875
Loss = 52286.5546875
Loss = 50114.84375
Loss = 51461.8828125
Loss = 51533.39453125
Loss = 53686.0625
Loss = 52561.51953125
Loss = 54507.546875
Loss = 54447.4765625
Loss = 55910.265625
Loss = 51249.9765625
Loss = 53077.484375
Loss = 54461.6875
Loss = 49981.5859375
Loss = 51673.9765625
Loss = 53360.78515625
Loss = 53894.9375
Loss = 51206.71875
Loss = 54158.671875
Loss = 52963.29296875
Loss = 52427.578125
Loss = 55881.74609375
Loss = 56858.3359375
Loss = 54509.1875
Loss = 53146.609375
Loss = 55309.70703125
Loss = 50797.90625
Loss = 51133.2421875
Loss = 53227.828125
Loss = 52303.390625
Loss = 52207.44140625
Loss = 52934.84375
Loss = 52004.71875
Loss = 52602.03515625
Loss = 53282.7421875
Loss = 52408.6875
Loss = 52653.65625
Loss = 51171.00390625
Loss = 55547.2265625
Loss = 52862.5234375
Loss = 58832.1796875
Loss = 51874.453125
Loss = 54090.41796875
Loss = 51853.78125
Loss = 52596.421875
Loss = 53645.39453125
Loss = 52447.328125
Loss = 54464.6796875
Loss = 54230.4609375
Loss = 52976.0625
Loss = 52150.1484375
Loss = 53217.28125
Loss = 52861.9140625
Loss = 51912.99609375
Loss = 53557.62890625
Loss = 52176.5
Loss = 53076.296875
Loss = 52826.046875
Loss = 55149.6484375
Loss = 52742.046875
Loss = 48817.734375
Loss = 52934.45703125
Loss = 53642.08203125
Loss = 52353.46875
Loss = 54155.4765625
Loss = 53108.96875
Loss = 53475.48046875
Loss = 51027.85546875
Loss = 53249.30859375
Loss = 52426.56640625
Loss = 53079.9609375
Loss = 54808.078125
Loss = 55761.30078125
Loss = 53871.94140625
Loss = 54293.0625
Loss = 52182.7109375
Loss = 52863.90625
Loss = 53849.47265625
Loss = 51047.60546875
Loss = 52686.984375
Loss = 52610.359375
Loss = 53879.91015625
Loss = 53354.09375
Loss = 52524.99609375
Loss = 52242.0546875
Loss = 52952.3203125
Loss = 54236.546875
Loss = 53360.1640625
Loss = 50774.19921875
Loss = 52383.515625
Loss = 50784.828125
Loss = 51398.2734375
Loss = 56242.109375
Loss = 51587.3671875
Loss = 54497.203125
Loss = 56093.65234375
Loss = 52569.765625
Loss = 55142.28515625
Loss = 50562.54296875
Loss = 51543.5234375
Loss = 52346.09375
Loss = 53919.296875
Loss = 49974.69140625
Loss = 51716.59375
Loss = 49381.2421875
Loss = 51212.0234375
Loss = 49050.5234375
Loss = 53571.0
Loss = 52965.6953125
Loss = 51356.39453125
Loss = 54974.70703125
Loss = 51636.125
Loss = 53106.625
Loss = 52916.3828125
Loss = 56113.5859375
Loss = 54528.51171875
Loss = 52618.65625
Loss = 55087.76171875
Loss = 50363.24609375
Loss = 51367.71875
Loss = 53428.4765625
Loss = 56982.7109375
Loss = 52351.1015625
Loss = 52138.7265625
Loss = 55012.06640625
Loss = 53134.01171875
Loss = 52528.640625
Loss = 52457.04296875
Loss = 50982.6875
Loss = 56244.0859375
Loss = 54803.3984375
Loss = 51537.03515625
Loss = 53351.85546875
Loss = 51950.9375
Loss = 53296.875
Loss = 52796.46875
Loss = 53913.0
Loss = 53606.83203125
Loss = 53769.81640625
Loss = 52329.5625
Loss = 54035.9375
Loss = 57916.49609375
Loss = 55077.2890625
Loss = 50755.25
Loss = 53488.390625
Loss = 54676.015625
Loss = 51492.625
Loss = 52518.1953125
Loss = 52850.4609375
Loss = 53430.171875
Loss = 54836.5625
Loss = 51540.515625
Loss = 53333.2109375
Loss = 52914.078125
Loss = 51078.1484375
Loss = 52440.625
Loss = 52717.0703125
Loss = 54330.13671875
Loss = 51784.02734375
Loss = 54128.4921875
Loss = 52564.7734375
Loss = 52358.40625
Loss = 53189.97265625
Loss = 52478.11328125
Loss = 52080.03125
Loss = 52572.34765625
Loss = 52141.3984375
Loss = 52969.359375
Loss = 51985.16796875
Loss = 53566.5703125
Loss = 51135.5
Loss = 52771.25
Loss = 53729.62890625
Loss = 55716.203125
Loss = 53748.421875
Loss = 54063.4765625
Loss = 52385.7578125
Loss = 51167.2421875
Loss = 55236.32421875
Loss = 54621.06640625
Loss = 49752.40234375
Loss = 51112.8125
Loss = 53975.3515625
Loss = 54715.58984375
oh
tf.Tensor([[6482]], shape=(1, 1), dtype=int32)
oh my
Plot loss over time.
x = range(len(train_loss))
plt.plot(x, train_loss, 'k-')
plt.xlabel('Generation')
plt.ylabel('Loss')
plt.title('Sequence to Sequence Loss')
plt.show()
24.1.1.3. Your turn! 🚀#
Assignment - Bitcoin lstm model with tweet volume and sentiment
24.1.1.4. Acknowledgments#
Thanks to Nick for creating the open-source project tensorflow_cookbook and Sebastian Raschka for creating the open-source project stat453-deep-learning-ss20. They inspire the majority of the content in this chapter.