In [1]:
'''An implementation of sequence to sequence learning for performing addition
Input: "535+61"
Output: "596"
Padding is handled by using a repeated sentinel character (space)
Input may optionally be inverted, shown to increase performance in many tasks in:
"Learning to Execute"
http://arxiv.org/abs/1410.4615 and
"Sequence to Sequence Learning with Neural Networks"
http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf
Theoretically it introduces shorter term dependencies between source and target.
Two digits inverted:
+ One layer LSTM (128 HN), 5k training examples = 99% train/test accuracy in 55 epochs
Three digits inverted:
+ One layer LSTM (128 HN), 50k training examples = 99% train/test accuracy in 100 epochs
Four digits inverted:
+ One layer LSTM (128 HN), 400k training examples = 99% train/test accuracy in 20 epochs
Five digits inverted:
+ One layer LSTM (128 HN), 550k training examples = 99% train/test accuracy in 30 epochs
'''
from __future__ import print_function
from keras.models import Sequential
from keras import layers
import numpy as np
from six.moves import range
Using TensorFlow backend.
In [2]:
class CharacterTable(object):
"""Given a set of characters:
+ Encode them to a one hot integer representation
+ Decode the one hot integer representation to their character output
+ Decode a vector of probabilities to their character output
"""
def __init__(self, chars):
"""Initialize character table.
# Arguments
chars: Characters that can appear in the input.
"""
self.chars = sorted(set(chars))
self.char_indices = dict((c, i) for i, c in enumerate(self.chars))
self.indices_char = dict((i, c) for i, c in enumerate(self.chars))
def encode(self, C, num_rows):
"""One hot encode given string C.
# Arguments
num_rows: Number of rows in the returned one hot encoding. This is
used to keep the # of rows for each data the same.
"""
x = np.zeros((num_rows, len(self.chars)))
for i, c in enumerate(C):
x[i, self.char_indices[c]] = 1
return x
def decode(self, x, calc_argmax=True):
if calc_argmax:
x = x.argmax(axis=-1)
return ''.join(self.indices_char[x] for x in x)
class colors:
ok = '\033[92m'
fail = '\033[91m'
close = '\033[0m'
# Parameters for the model and dataset.
TRAINING_SIZE = 50000
DIGITS = 3
INVERT = True
# Maximum length of input is 'int + int' (e.g., '345+678'). Maximum length of
# int is DIGITS.
MAXLEN = DIGITS + 1 + DIGITS
# All the numbers, plus sign and space for padding.
chars = '0123456789+ '
ctable = CharacterTable(chars)
questions = []
expected = []
In [3]:
seen = set()
print('Generating data...')
while len(questions) < TRAINING_SIZE:
f = lambda: int(''.join(np.random.choice(list('0123456789'))
for i in range(np.random.randint(1, DIGITS + 1))))
a, b = f(), f()
# Skip any addition questions we've already seen
# Also skip any such that x+Y == Y+x (hence the sorting).
key = tuple(sorted((a, b)))
if key in seen:
continue
seen.add(key)
# Pad the data with spaces such that it is always MAXLEN.
q = '{}+{}'.format(a, b)
query = q + ' ' * (MAXLEN - len(q))
ans = str(a + b)
# Answers can be of maximum size DIGITS + 1.
ans += ' ' * (DIGITS + 1 - len(ans))
if INVERT:
# Reverse the query, e.g., '12+345 ' becomes ' 543+21'. (Note the
# space used for padding.)
query = query[::-1]
questions.append(query)
expected.append(ans)
print('Total addition questions:', len(questions))
Generating data...
Total addition questions: 50000
Vectorization...
In [4]:
print('Vectorization...')
x = np.zeros((len(questions), MAXLEN, len(chars)), dtype=np.bool)
y = np.zeros((len(questions), DIGITS + 1, len(chars)), dtype=np.bool)
for i, sentence in enumerate(questions):
x[i] = ctable.encode(sentence, MAXLEN)
for i, sentence in enumerate(expected):
y[i] = ctable.encode(sentence, DIGITS + 1)
# Shuffle (x, y) in unison as the later parts of x will almost all be larger digits.
indices = np.arange(len(y))
np.random.shuffle(indices)
x = x[indices]
y = y[indices]
# Explicitly set apart 10% for validation data that we never train over.
split_at = len(x) - len(x) // 10
(x_train, x_val) = x[:split_at], x[split_at:]
(y_train, y_val) = y[:split_at], y[split_at:]
print('Training Data:')
print(x_train.shape)
print(y_train.shape)
print('Validation Data:')
print(x_val.shape)
print(y_val.shape)
Vectorization...
Training Data:
(45000, 7, 12)
(45000, 4, 12)
Validation Data:
(5000, 7, 12)
(5000, 4, 12)
In [5]:
# Try replacing GRU, or SimpleRNN.
RNN = layers.LSTM
HIDDEN_SIZE = 128
BATCH_SIZE = 128
LAYERS = 1
print('Build model...')
model = Sequential()
# "Encode" the input sequence using an RNN, producing an output of HIDDEN_SIZE.
# Note: In a situation where your input sequences have a variable length,
# use input_shape=(None, num_feature).
model.add(RNN(HIDDEN_SIZE, input_shape=(MAXLEN, len(chars))))
# As the decoder RNN's input, repeatedly provide with the last hidden state of
# RNN for each time step. Repeat 'DIGITS + 1' times as that's the maximum
# length of output, e.g., when DIGITS=3, max output is 999+999=1998.
model.add(layers.RepeatVector(DIGITS + 1))
# The decoder RNN could be multiple layers stacked or a single layer.
for _ in range(LAYERS):
# By setting return_sequences to True, return not only the last output but
# all the outputs so far in the form of (num_samples, timesteps,
# output_dim). This is necessary as TimeDistributed in the below expects
# the first dimension to be the timesteps.
model.add(RNN(HIDDEN_SIZE, return_sequences=True))
# Apply a dense layer to the every temporal slice of an input. For each of step
# of the output sequence, decide which character should be chosen.
model.add(layers.TimeDistributed(layers.Dense(len(chars))))
model.add(layers.Activation('softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.summary()
# Train the model each generation and show predictions against the validation
# dataset.
for iteration in range(1, 200):
print()
print('-' * 50)
print('Iteration', iteration)
model.fit(x_train, y_train,
batch_size=BATCH_SIZE,
epochs=1,
validation_data=(x_val, y_val))
# Select 10 samples from the validation set at random so we can visualize
# errors.
for i in range(10):
ind = np.random.randint(0, len(x_val))
rowx, rowy = x_val[np.array([ind])], y_val[np.array([ind])]
preds = model.predict_classes(rowx, verbose=0)
q = ctable.decode(rowx[0])
correct = ctable.decode(rowy[0])
guess = ctable.decode(preds[0], calc_argmax=False)
print('Q', q[::-1] if INVERT else q)
print('T', correct)
if correct == guess:
print(colors.ok + '☑' + colors.close, end=" ")
else:
print(colors.fail + '☒' + colors.close, end=" ")
print(guess)
print('---')
Build model...
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
lstm_1 (LSTM) (None, 128) 72192
_________________________________________________________________
repeat_vector_1 (RepeatVecto (None, 4, 128) 0
_________________________________________________________________
lstm_2 (LSTM) (None, 4, 128) 131584
_________________________________________________________________
time_distributed_1 (TimeDist (None, 4, 12) 1548
_________________________________________________________________
activation_1 (Activation) (None, 4, 12) 0
=================================================================
Total params: 205,324
Trainable params: 205,324
Non-trainable params: 0
_________________________________________________________________
--------------------------------------------------
Iteration 1
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 36s - loss: 1.8867 - acc: 0.3226 - val_loss: 1.8139 - val_acc: 0.3405
Q 560+53
T 613
☒ 155
---
Q 572+952
T 1524
☒ 105
---
Q 43+661
T 704
☒ 155
---
Q 607+33
T 640
☒ 155
---
Q 894+814
T 1708
☒ 105
---
Q 200+92
T 292
☒ 125
---
Q 93+732
T 825
☒ 105
---
Q 396+85
T 481
☒ 105
---
Q 396+865
T 1261
☒ 101
---
Q 13+856
T 869
☒ 125
---
--------------------------------------------------
Iteration 2
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 1.7386 - acc: 0.3577 - val_loss: 1.6697 - val_acc: 0.3798
Q 5+969
T 974
☒ 104
---
Q 288+86
T 374
☒ 894
---
Q 197+1
T 198
☒ 112
---
Q 975+38
T 1013
☒ 904
---
Q 9+783
T 792
☒ 904
---
Q 97+80
T 177
☒ 197
---
Q 416+34
T 450
☒ 449
---
Q 385+8
T 393
☒ 189
---
Q 410+34
T 444
☒ 449
---
Q 597+364
T 961
☒ 104
---
--------------------------------------------------
Iteration 3
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 1.5944 - acc: 0.4035 - val_loss: 1.5124 - val_acc: 0.4328
Q 92+17
T 109
☒ 111
---
Q 63+55
T 118
☒ 669
---
Q 76+204
T 280
☒ 371
---
Q 919+78
T 997
☒ 901
---
Q 52+617
T 669
☒ 671
---
Q 806+157
T 963
☒ 101
---
Q 475+5
T 480
☒ 551
---
Q 937+93
T 1030
☒ 1041
---
Q 118+423
T 541
☒ 796
---
Q 613+47
T 660
☒ 674
---
--------------------------------------------------
Iteration 4
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 1.4221 - acc: 0.4697 - val_loss: 1.3347 - val_acc: 0.4982
Q 750+47
T 797
☒ 782
---
Q 190+569
T 759
☒ 765
---
Q 195+74
T 269
☒ 255
---
Q 681+860
T 1541
☒ 1471
---
Q 675+2
T 677
☒ 678
---
Q 528+875
T 1403
☒ 1311
---
Q 4+105
T 109
☒ 111
---
Q 60+314
T 374
☒ 368
---
Q 32+42
T 74
☒ 37
---
Q 464+7
T 471
☑ 471
---
--------------------------------------------------
Iteration 5
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 1.2639 - acc: 0.5319 - val_loss: 1.1940 - val_acc: 0.5631
Q 728+675
T 1403
☒ 1422
---
Q 468+32
T 500
☒ 499
---
Q 5+718
T 723
☒ 722
---
Q 32+446
T 478
☒ 479
---
Q 0+776
T 776
☒ 777
---
Q 41+886
T 927
☒ 999
---
Q 560+39
T 599
☒ 691
---
Q 32+50
T 82
☒ 60
---
Q 595+1
T 596
☒ 599
---
Q 19+293
T 312
☒ 219
---
--------------------------------------------------
Iteration 6
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 1.1322 - acc: 0.5852 - val_loss: 1.0745 - val_acc: 0.6079
Q 23+800
T 823
☒ 834
---
Q 8+27
T 35
☒ 27
---
Q 894+814
T 1708
☒ 1700
---
Q 721+88
T 809
☒ 800
---
Q 515+98
T 613
☒ 600
---
Q 314+0
T 314
☒ 313
---
Q 40+240
T 280
☒ 362
---
Q 892+396
T 1288
☒ 1256
---
Q 927+862
T 1789
☒ 1710
---
Q 119+363
T 482
☒ 502
---
--------------------------------------------------
Iteration 7
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 1.0067 - acc: 0.6363 - val_loss: 0.9651 - val_acc: 0.6488
Q 862+106
T 968
☒ 909
---
Q 252+740
T 992
☒ 900
---
Q 408+96
T 504
☒ 596
---
Q 32+19
T 51
☒ 44
---
Q 48+679
T 727
☒ 719
---
Q 5+529
T 534
☒ 539
---
Q 1+762
T 763
☒ 764
---
Q 464+5
T 469
☒ 474
---
Q 1+714
T 715
☑ 715
---
Q 178+43
T 221
☒ 229
---
--------------------------------------------------
Iteration 8
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 29s - loss: 0.9057 - acc: 0.6756 - val_loss: 0.8744 - val_acc: 0.6818
Q 20+729
T 749
☒ 759
---
Q 451+37
T 488
☒ 489
---
Q 48+890
T 938
☒ 939
---
Q 908+456
T 1364
☒ 1455
---
Q 315+96
T 411
☒ 410
---
Q 764+17
T 781
☒ 777
---
Q 229+432
T 661
☒ 662
---
Q 12+262
T 274
☒ 272
---
Q 992+214
T 1206
☒ 1200
---
Q 38+14
T 52
☑ 52
---
--------------------------------------------------
Iteration 9
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 29s - loss: 0.8201 - acc: 0.7100 - val_loss: 0.8091 - val_acc: 0.7077
Q 37+307
T 344
☒ 341
---
Q 602+12
T 614
☒ 615
---
Q 949+685
T 1634
☒ 1636
---
Q 798+16
T 814
☒ 810
---
Q 92+901
T 993
☒ 990
---
Q 834+972
T 1806
☒ 1800
---
Q 314+16
T 330
☑ 330
---
Q 575+22
T 597
☒ 699
---
Q 61+916
T 977
☒ 976
---
Q 289+52
T 341
☒ 340
---
--------------------------------------------------
Iteration 10
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.7416 - acc: 0.7404 - val_loss: 0.7110 - val_acc: 0.7510
Q 491+1
T 492
☒ 493
---
Q 650+7
T 657
☑ 657
---
Q 505+259
T 764
☒ 756
---
Q 623+296
T 919
☒ 921
---
Q 602+456
T 1058
☒ 1053
---
Q 97+954
T 1051
☒ 1046
---
Q 29+83
T 112
☒ 119
---
Q 667+549
T 1216
☒ 1212
---
Q 3+752
T 755
☒ 754
---
Q 71+36
T 107
☒ 108
---
--------------------------------------------------
Iteration 11
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.6478 - acc: 0.7678 - val_loss: 0.5834 - val_acc: 0.7879
Q 37+877
T 914
☒ 918
---
Q 17+767
T 784
☒ 786
---
Q 99+475
T 574
☒ 579
---
Q 51+279
T 330
☒ 320
---
Q 476+58
T 534
☑ 534
---
Q 135+53
T 188
☑ 188
---
Q 843+255
T 1098
☑ 1098
---
Q 386+18
T 404
☑ 404
---
Q 9+120
T 129
☒ 119
---
Q 426+375
T 801
☒ 800
---
--------------------------------------------------
Iteration 12
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 33s - loss: 0.4853 - acc: 0.8297 - val_loss: 0.4348 - val_acc: 0.8463
Q 855+35
T 890
☑ 890
---
Q 282+4
T 286
☑ 286
---
Q 215+213
T 428
☒ 328
---
Q 493+59
T 552
☒ 551
---
Q 533+543
T 1076
☑ 1076
---
Q 589+9
T 598
☒ 596
---
Q 764+17
T 781
☒ 782
---
Q 52+44
T 96
☒ 87
---
Q 59+738
T 797
☒ 786
---
Q 927+862
T 1789
☒ 1799
---
--------------------------------------------------
Iteration 13
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 40s - loss: 0.3459 - acc: 0.8937 - val_loss: 0.3122 - val_acc: 0.9039
Q 181+227
T 408
☒ 308
---
Q 829+366
T 1195
☒ 1185
---
Q 72+140
T 212
☑ 212
---
Q 312+211
T 523
☒ 423
---
Q 3+530
T 533
☒ 433
---
Q 334+694
T 1028
☑ 1028
---
Q 3+31
T 34
☑ 34
---
Q 64+933
T 997
☒ 998
---
Q 8+969
T 977
☑ 977
---
Q 231+244
T 475
☒ 476
---
--------------------------------------------------
Iteration 14
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 41s - loss: 0.2491 - acc: 0.9356 - val_loss: 0.2204 - val_acc: 0.9428
Q 237+540
T 777
☒ 776
---
Q 659+513
T 1172
☑ 1172
---
Q 16+632
T 648
☑ 648
---
Q 603+7
T 610
☒ 600
---
Q 85+582
T 667
☑ 667
---
Q 65+946
T 1011
☑ 1011
---
Q 359+41
T 400
☒ 300
---
Q 68+12
T 80
☒ 70
---
Q 569+48
T 617
☑ 617
---
Q 67+17
T 84
☑ 84
---
--------------------------------------------------
Iteration 15
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 46s - loss: 0.1786 - acc: 0.9610 - val_loss: 0.1489 - val_acc: 0.9688
Q 221+460
T 681
☑ 681
---
Q 67+50
T 117
☑ 117
---
Q 113+480
T 593
☒ 693
---
Q 1+860
T 861
☑ 861
---
Q 58+733
T 791
☑ 791
---
Q 947+4
T 951
☑ 951
---
Q 525+39
T 564
☑ 564
---
Q 820+673
T 1493
☒ 1593
---
Q 94+806
T 900
☒ 991
---
Q 14+20
T 34
☑ 34
---
--------------------------------------------------
Iteration 16
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 49s - loss: 0.1303 - acc: 0.9736 - val_loss: 0.1196 - val_acc: 0.9748
Q 821+707
T 1528
☑ 1528
---
Q 557+159
T 716
☑ 716
---
Q 594+9
T 603
☑ 603
---
Q 355+13
T 368
☑ 368
---
Q 5+718
T 723
☑ 723
---
Q 539+59
T 598
☑ 598
---
Q 418+516
T 934
☑ 934
---
Q 190+784
T 974
☑ 974
---
Q 158+35
T 193
☑ 193
---
Q 9+52
T 61
☒ 51
---
--------------------------------------------------
Iteration 17
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 49s - loss: 0.0954 - acc: 0.9832 - val_loss: 0.0942 - val_acc: 0.9802
Q 849+332
T 1181
☑ 1181
---
Q 128+554
T 682
☑ 682
---
Q 163+11
T 174
☑ 174
---
Q 89+118
T 207
☑ 207
---
Q 682+392
T 1074
☑ 1074
---
Q 56+944
T 1000
☑ 1000
---
Q 438+7
T 445
☑ 445
---
Q 16+997
T 1013
☑ 1013
---
Q 162+3
T 165
☑ 165
---
Q 74+400
T 474
☑ 474
---
--------------------------------------------------
Iteration 18
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 50s - loss: 0.0861 - acc: 0.9823 - val_loss: 0.0737 - val_acc: 0.9859
Q 6+646
T 652
☑ 652
---
Q 519+73
T 592
☑ 592
---
Q 85+506
T 591
☑ 591
---
Q 67+18
T 85
☑ 85
---
Q 809+160
T 969
☒ 979
---
Q 57+396
T 453
☑ 453
---
Q 797+545
T 1342
☑ 1342
---
Q 870+741
T 1611
☑ 1611
---
Q 673+777
T 1450
☑ 1450
---
Q 42+292
T 334
☑ 334
---
--------------------------------------------------
Iteration 19
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 50s - loss: 0.0609 - acc: 0.9903 - val_loss: 0.0592 - val_acc: 0.9896
Q 746+41
T 787
☑ 787
---
Q 140+73
T 213
☑ 213
---
Q 91+28
T 119
☑ 119
---
Q 14+20
T 34
☑ 34
---
Q 477+426
T 903
☑ 903
---
Q 575+46
T 621
☑ 621
---
Q 48+34
T 82
☑ 82
---
Q 736+77
T 813
☑ 813
---
Q 283+7
T 290
☑ 290
---
Q 333+276
T 609
☒ 509
---
--------------------------------------------------
Iteration 20
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 48s - loss: 0.0734 - acc: 0.9828 - val_loss: 0.0674 - val_acc: 0.9841
Q 51+810
T 861
☑ 861
---
Q 207+86
T 293
☑ 293
---
Q 4+671
T 675
☑ 675
---
Q 138+939
T 1077
☑ 1077
---
Q 797+587
T 1384
☑ 1384
---
Q 73+967
T 1040
☑ 1040
---
Q 49+19
T 68
☒ 58
---
Q 135+486
T 621
☑ 621
---
Q 718+623
T 1341
☑ 1341
---
Q 12+600
T 612
☑ 612
---
--------------------------------------------------
Iteration 21
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 0.0517 - acc: 0.9899 - val_loss: 0.0930 - val_acc: 0.9689
Q 98+224
T 322
☑ 322
---
Q 68+29
T 97
☑ 97
---
Q 39+288
T 327
☑ 327
---
Q 3+707
T 710
☑ 710
---
Q 68+29
T 97
☑ 97
---
Q 91+633
T 724
☑ 724
---
Q 952+31
T 983
☑ 983
---
Q 162+287
T 449
☑ 449
---
Q 692+796
T 1488
☒ 1588
---
Q 3+609
T 612
☑ 612
---
--------------------------------------------------
Iteration 22
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 33s - loss: 0.0412 - acc: 0.9927 - val_loss: 0.0392 - val_acc: 0.9922
Q 624+598
T 1222
☑ 1222
---
Q 889+26
T 915
☑ 915
---
Q 10+69
T 79
☑ 79
---
Q 959+16
T 975
☑ 975
---
Q 650+7
T 657
☑ 657
---
Q 333+829
T 1162
☑ 1162
---
Q 185+820
T 1005
☒ 9005
---
Q 221+66
T 287
☑ 287
---
Q 317+8
T 325
☑ 325
---
Q 395+786
T 1181
☑ 1181
---
--------------------------------------------------
Iteration 23
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0310 - acc: 0.9955 - val_loss: 0.0412 - val_acc: 0.9903
Q 7+120
T 127
☒ 137
---
Q 828+776
T 1604
☑ 1604
---
Q 357+290
T 647
☑ 647
---
Q 18+102
T 120
☑ 120
---
Q 73+796
T 869
☑ 869
---
Q 143+182
T 325
☑ 325
---
Q 0+177
T 177
☑ 177
---
Q 820+36
T 856
☑ 856
---
Q 32+267
T 299
☑ 299
---
Q 309+120
T 429
☑ 429
---
--------------------------------------------------
Iteration 24
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0406 - acc: 0.9907 - val_loss: 0.0426 - val_acc: 0.9897
Q 28+48
T 76
☑ 76
---
Q 97+770
T 867
☑ 867
---
Q 19+881
T 900
☑ 900
---
Q 221+460
T 681
☑ 681
---
Q 67+469
T 536
☑ 536
---
Q 0+871
T 871
☑ 871
---
Q 936+12
T 948
☑ 948
---
Q 74+925
T 999
☑ 999
---
Q 566+389
T 955
☑ 955
---
Q 53+937
T 990
☑ 990
---
--------------------------------------------------
Iteration 25
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0218 - acc: 0.9972 - val_loss: 0.0228 - val_acc: 0.9969
Q 867+803
T 1670
☑ 1670
---
Q 40+245
T 285
☑ 285
---
Q 417+259
T 676
☑ 676
---
Q 852+9
T 861
☑ 861
---
Q 663+469
T 1132
☑ 1132
---
Q 66+58
T 124
☑ 124
---
Q 113+51
T 164
☑ 164
---
Q 967+927
T 1894
☑ 1894
---
Q 0+602
T 602
☑ 602
---
Q 221+84
T 305
☑ 305
---
--------------------------------------------------
Iteration 26
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0180 - acc: 0.9979 - val_loss: 0.0231 - val_acc: 0.9949
Q 670+88
T 758
☑ 758
---
Q 510+25
T 535
☑ 535
---
Q 622+86
T 708
☑ 708
---
Q 3+887
T 890
☑ 890
---
Q 240+11
T 251
☑ 251
---
Q 71+2
T 73
☑ 73
---
Q 371+24
T 395
☑ 395
---
Q 1+293
T 294
☑ 294
---
Q 3+908
T 911
☑ 911
---
Q 79+151
T 230
☑ 230
---
--------------------------------------------------
Iteration 27
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0489 - acc: 0.9864 - val_loss: 0.0233 - val_acc: 0.9952
Q 661+5
T 666
☑ 666
---
Q 201+58
T 259
☑ 259
---
Q 985+905
T 1890
☑ 1890
---
Q 94+17
T 111
☑ 111
---
Q 531+79
T 610
☑ 610
---
Q 45+759
T 804
☑ 804
---
Q 30+481
T 511
☑ 511
---
Q 895+8
T 903
☑ 903
---
Q 315+835
T 1150
☑ 1150
---
Q 645+6
T 651
☑ 651
---
--------------------------------------------------
Iteration 28
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0126 - acc: 0.9990 - val_loss: 0.0179 - val_acc: 0.9968
Q 371+24
T 395
☑ 395
---
Q 188+83
T 271
☑ 271
---
Q 61+916
T 977
☑ 977
---
Q 904+854
T 1758
☑ 1758
---
Q 629+530
T 1159
☑ 1159
---
Q 662+765
T 1427
☑ 1427
---
Q 981+225
T 1206
☑ 1206
---
Q 568+7
T 575
☑ 575
---
Q 829+68
T 897
☑ 897
---
Q 258+9
T 267
☑ 267
---
--------------------------------------------------
Iteration 29
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 29s - loss: 0.0187 - acc: 0.9962 - val_loss: 0.0305 - val_acc: 0.9922
Q 143+194
T 337
☑ 337
---
Q 945+1
T 946
☑ 946
---
Q 72+341
T 413
☑ 413
---
Q 655+680
T 1335
☑ 1335
---
Q 249+2
T 251
☑ 251
---
Q 402+209
T 611
☑ 611
---
Q 99+94
T 193
☑ 193
---
Q 225+99
T 324
☑ 324
---
Q 4+753
T 757
☑ 757
---
Q 25+344
T 369
☑ 369
---
--------------------------------------------------
Iteration 30
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0418 - acc: 0.9880 - val_loss: 0.0308 - val_acc: 0.9916
Q 353+47
T 400
☑ 400
---
Q 50+517
T 567
☑ 567
---
Q 75+5
T 80
☑ 80
---
Q 902+6
T 908
☑ 908
---
Q 2+889
T 891
☑ 891
---
Q 799+940
T 1739
☒ 1749
---
Q 352+802
T 1154
☑ 1154
---
Q 57+583
T 640
☑ 640
---
Q 9+858
T 867
☑ 867
---
Q 969+262
T 1231
☑ 1231
---
--------------------------------------------------
Iteration 31
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0109 - acc: 0.9989 - val_loss: 0.0126 - val_acc: 0.9980
Q 190+569
T 759
☑ 759
---
Q 44+359
T 403
☑ 403
---
Q 845+0
T 845
☑ 845
---
Q 236+9
T 245
☑ 245
---
Q 23+249
T 272
☑ 272
---
Q 117+550
T 667
☑ 667
---
Q 661+63
T 724
☑ 724
---
Q 738+465
T 1203
☑ 1203
---
Q 92+750
T 842
☑ 842
---
Q 787+99
T 886
☑ 886
---
--------------------------------------------------
Iteration 32
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0084 - acc: 0.9992 - val_loss: 0.0184 - val_acc: 0.9956
Q 79+842
T 921
☑ 921
---
Q 99+94
T 193
☑ 193
---
Q 746+41
T 787
☑ 787
---
Q 941+64
T 1005
☑ 1005
---
Q 1+639
T 640
☑ 640
---
Q 68+65
T 133
☑ 133
---
Q 57+390
T 447
☑ 447
---
Q 559+805
T 1364
☑ 1364
---
Q 256+70
T 326
☑ 326
---
Q 775+975
T 1750
☑ 1750
---
--------------------------------------------------
Iteration 33
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0285 - acc: 0.9919 - val_loss: 0.1233 - val_acc: 0.9611
Q 80+139
T 219
☑ 219
---
Q 59+738
T 797
☑ 797
---
Q 62+329
T 391
☑ 391
---
Q 799+55
T 854
☒ 844
---
Q 178+851
T 1029
☑ 1029
---
Q 15+119
T 134
☑ 134
---
Q 352+240
T 592
☑ 592
---
Q 696+618
T 1314
☑ 1314
---
Q 480+804
T 1284
☑ 1284
---
Q 819+182
T 1001
☑ 1001
---
--------------------------------------------------
Iteration 34
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0235 - acc: 0.9939 - val_loss: 0.0112 - val_acc: 0.9979
Q 3+970
T 973
☑ 973
---
Q 6+690
T 696
☑ 696
---
Q 20+12
T 32
☑ 32
---
Q 67+333
T 400
☑ 400
---
Q 630+543
T 1173
☑ 1173
---
Q 205+2
T 207
☑ 207
---
Q 618+39
T 657
☑ 657
---
Q 184+739
T 923
☑ 923
---
Q 188+832
T 1020
☑ 1020
---
Q 12+121
T 133
☑ 133
---
--------------------------------------------------
Iteration 35
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0057 - acc: 0.9996 - val_loss: 0.0091 - val_acc: 0.9982
Q 205+60
T 265
☑ 265
---
Q 589+83
T 672
☑ 672
---
Q 31+211
T 242
☑ 242
---
Q 1+274
T 275
☑ 275
---
Q 151+74
T 225
☑ 225
---
Q 48+452
T 500
☑ 500
---
Q 92+480
T 572
☑ 572
---
Q 551+55
T 606
☑ 606
---
Q 755+71
T 826
☑ 826
---
Q 207+396
T 603
☑ 603
---
--------------------------------------------------
Iteration 36
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0048 - acc: 0.9998 - val_loss: 0.0085 - val_acc: 0.9986
Q 237+540
T 777
☑ 777
---
Q 92+878
T 970
☑ 970
---
Q 20+901
T 921
☑ 921
---
Q 3+765
T 768
☑ 768
---
Q 4+899
T 903
☑ 903
---
Q 62+248
T 310
☑ 310
---
Q 751+17
T 768
☑ 768
---
Q 19+881
T 900
☑ 900
---
Q 846+388
T 1234
☑ 1234
---
Q 97+999
T 1096
☑ 1096
---
--------------------------------------------------
Iteration 37
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 0.0182 - acc: 0.9951 - val_loss: 0.1158 - val_acc: 0.9597
Q 273+98
T 371
☑ 371
---
Q 787+76
T 863
☑ 863
---
Q 598+7
T 605
☑ 605
---
Q 143+1
T 144
☑ 144
---
Q 140+73
T 213
☑ 213
---
Q 94+68
T 162
☑ 162
---
Q 184+739
T 923
☑ 923
---
Q 175+16
T 191
☑ 191
---
Q 21+89
T 110
☑ 110
---
Q 31+496
T 527
☑ 527
---
--------------------------------------------------
Iteration 38
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0273 - acc: 0.9923 - val_loss: 0.0110 - val_acc: 0.9976
Q 5+128
T 133
☑ 133
---
Q 174+15
T 189
☑ 189
---
Q 231+51
T 282
☑ 282
---
Q 994+506
T 1500
☑ 1500
---
Q 360+157
T 517
☑ 517
---
Q 444+640
T 1084
☑ 1084
---
Q 996+810
T 1806
☑ 1806
---
Q 43+5
T 48
☑ 48
---
Q 28+807
T 835
☑ 835
---
Q 358+923
T 1281
☑ 1281
---
--------------------------------------------------
Iteration 39
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0043 - acc: 0.9998 - val_loss: 0.0066 - val_acc: 0.9990
Q 205+2
T 207
☑ 207
---
Q 847+913
T 1760
☑ 1760
---
Q 88+303
T 391
☑ 391
---
Q 34+1
T 35
☑ 35
---
Q 423+135
T 558
☑ 558
---
Q 733+3
T 736
☑ 736
---
Q 65+721
T 786
☑ 786
---
Q 118+137
T 255
☑ 255
---
Q 34+65
T 99
☑ 99
---
Q 845+411
T 1256
☑ 1256
---
--------------------------------------------------
Iteration 40
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0032 - acc: 0.9999 - val_loss: 0.0062 - val_acc: 0.9991
Q 160+416
T 576
☑ 576
---
Q 314+25
T 339
☑ 339
---
Q 7+970
T 977
☑ 977
---
Q 72+24
T 96
☑ 96
---
Q 86+840
T 926
☑ 926
---
Q 9+505
T 514
☑ 514
---
Q 1+891
T 892
☑ 892
---
Q 763+15
T 778
☑ 778
---
Q 61+88
T 149
☑ 149
---
Q 220+319
T 539
☑ 539
---
--------------------------------------------------
Iteration 41
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0029 - acc: 0.9999 - val_loss: 0.0062 - val_acc: 0.9990
Q 408+511
T 919
☑ 919
---
Q 6+133
T 139
☑ 139
---
Q 30+204
T 234
☑ 234
---
Q 140+386
T 526
☑ 526
---
Q 84+19
T 103
☑ 103
---
Q 96+595
T 691
☑ 691
---
Q 40+729
T 769
☑ 769
---
Q 40+69
T 109
☑ 109
---
Q 238+39
T 277
☑ 277
---
Q 841+225
T 1066
☑ 1066
---
--------------------------------------------------
Iteration 42
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0292 - acc: 0.9915 - val_loss: 0.1390 - val_acc: 0.9573
Q 158+35
T 193
☑ 193
---
Q 935+12
T 947
☑ 947
---
Q 556+0
T 556
☑ 556
---
Q 590+237
T 827
☑ 827
---
Q 487+230
T 717
☑ 717
---
Q 16+656
T 672
☑ 672
---
Q 80+64
T 144
☑ 144
---
Q 449+902
T 1351
☑ 1351
---
Q 989+742
T 1731
☒ 1721
---
Q 19+862
T 881
☑ 881
---
--------------------------------------------------
Iteration 43
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0205 - acc: 0.9941 - val_loss: 0.0164 - val_acc: 0.9954
Q 725+789
T 1514
☑ 1514
---
Q 563+18
T 581
☑ 581
---
Q 1+274
T 275
☑ 275
---
Q 190+138
T 328
☑ 328
---
Q 2+373
T 375
☑ 375
---
Q 0+221
T 221
☑ 221
---
Q 14+20
T 34
☑ 34
---
Q 28+970
T 998
☑ 998
---
Q 37+877
T 914
☑ 914
---
Q 720+660
T 1380
☑ 1380
---
--------------------------------------------------
Iteration 44
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0049 - acc: 0.9994 - val_loss: 0.0067 - val_acc: 0.9987
Q 672+990
T 1662
☑ 1662
---
Q 56+18
T 74
☑ 74
---
Q 98+842
T 940
☑ 940
---
Q 65+946
T 1011
☑ 1011
---
Q 47+823
T 870
☑ 870
---
Q 6+819
T 825
☑ 825
---
Q 844+396
T 1240
☑ 1240
---
Q 462+915
T 1377
☑ 1377
---
Q 156+64
T 220
☑ 220
---
Q 774+619
T 1393
☑ 1393
---
--------------------------------------------------
Iteration 45
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0025 - acc: 0.9999 - val_loss: 0.0053 - val_acc: 0.9990
Q 32+267
T 299
☑ 299
---
Q 983+65
T 1048
☑ 1048
---
Q 722+49
T 771
☑ 771
---
Q 2+372
T 374
☑ 374
---
Q 420+3
T 423
☑ 423
---
Q 113+6
T 119
☑ 119
---
Q 691+490
T 1181
☑ 1181
---
Q 3+845
T 848
☑ 848
---
Q 80+439
T 519
☑ 519
---
Q 75+5
T 80
☑ 80
---
--------------------------------------------------
Iteration 46
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0034 - acc: 0.9995 - val_loss: 0.0122 - val_acc: 0.9963
Q 603+113
T 716
☑ 716
---
Q 57+72
T 129
☑ 129
---
Q 11+670
T 681
☑ 681
---
Q 273+11
T 284
☑ 284
---
Q 706+38
T 744
☑ 744
---
Q 3+362
T 365
☒ 366
---
Q 35+127
T 162
☑ 162
---
Q 62+329
T 391
☑ 391
---
Q 28+361
T 389
☑ 389
---
Q 5+718
T 723
☑ 723
---
--------------------------------------------------
Iteration 47
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0588 - acc: 0.9823 - val_loss: 0.0106 - val_acc: 0.9974
Q 622+86
T 708
☑ 708
---
Q 7+435
T 442
☑ 442
---
Q 193+5
T 198
☑ 198
---
Q 15+933
T 948
☑ 948
---
Q 58+83
T 141
☑ 141
---
Q 511+4
T 515
☑ 515
---
Q 3+977
T 980
☑ 980
---
Q 416+34
T 450
☑ 450
---
Q 401+86
T 487
☑ 487
---
Q 83+413
T 496
☑ 496
---
--------------------------------------------------
Iteration 48
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0035 - acc: 0.9998 - val_loss: 0.0067 - val_acc: 0.9985
Q 271+22
T 293
☑ 293
---
Q 556+800
T 1356
☑ 1356
---
Q 267+0
T 267
☑ 267
---
Q 68+840
T 908
☑ 908
---
Q 75+446
T 521
☑ 521
---
Q 663+4
T 667
☑ 667
---
Q 288+107
T 395
☑ 395
---
Q 943+79
T 1022
☑ 1022
---
Q 6+989
T 995
☑ 995
---
Q 5+310
T 315
☑ 315
---
--------------------------------------------------
Iteration 49
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0022 - acc: 1.0000 - val_loss: 0.0050 - val_acc: 0.9990
Q 374+730
T 1104
☑ 1104
---
Q 9+34
T 43
☑ 43
---
Q 8+635
T 643
☑ 643
---
Q 797+2
T 799
☑ 799
---
Q 89+198
T 287
☑ 287
---
Q 2+469
T 471
☑ 471
---
Q 325+804
T 1129
☑ 1129
---
Q 551+55
T 606
☑ 606
---
Q 469+846
T 1315
☑ 1315
---
Q 196+43
T 239
☑ 239
---
--------------------------------------------------
Iteration 50
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0019 - acc: 1.0000 - val_loss: 0.0045 - val_acc: 0.9990
Q 25+0
T 25
☑ 25
---
Q 992+90
T 1082
☑ 1082
---
Q 23+984
T 1007
☑ 1007
---
Q 198+566
T 764
☑ 764
---
Q 71+402
T 473
☑ 473
---
Q 464+5
T 469
☑ 469
---
Q 51+480
T 531
☑ 531
---
Q 257+37
T 294
☑ 294
---
Q 278+59
T 337
☑ 337
---
Q 693+811
T 1504
☑ 1504
---
--------------------------------------------------
Iteration 51
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0016 - acc: 1.0000 - val_loss: 0.0043 - val_acc: 0.9990
Q 13+723
T 736
☑ 736
---
Q 468+32
T 500
☑ 500
---
Q 2+469
T 471
☑ 471
---
Q 88+962
T 1050
☑ 1050
---
Q 233+5
T 238
☑ 238
---
Q 897+78
T 975
☑ 975
---
Q 594+530
T 1124
☑ 1124
---
Q 21+362
T 383
☑ 383
---
Q 109+375
T 484
☑ 484
---
Q 37+99
T 136
☑ 136
---
--------------------------------------------------
Iteration 52
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0016 - acc: 1.0000 - val_loss: 0.0040 - val_acc: 0.9992
Q 17+876
T 893
☑ 893
---
Q 257+4
T 261
☑ 261
---
Q 329+795
T 1124
☑ 1124
---
Q 9+312
T 321
☑ 321
---
Q 172+15
T 187
☑ 187
---
Q 43+925
T 968
☑ 968
---
Q 16+760
T 776
☑ 776
---
Q 9+605
T 614
☑ 614
---
Q 567+647
T 1214
☑ 1214
---
Q 72+171
T 243
☑ 243
---
--------------------------------------------------
Iteration 53
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0013 - acc: 1.0000 - val_loss: 0.0038 - val_acc: 0.9993
Q 650+7
T 657
☑ 657
---
Q 223+145
T 368
☑ 368
---
Q 489+197
T 686
☑ 686
---
Q 672+8
T 680
☑ 680
---
Q 951+4
T 955
☑ 955
---
Q 28+4
T 32
☑ 32
---
Q 38+993
T 1031
☑ 1031
---
Q 110+0
T 110
☑ 110
---
Q 998+704
T 1702
☑ 1702
---
Q 79+140
T 219
☑ 219
---
--------------------------------------------------
Iteration 54
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0319 - acc: 0.9904 - val_loss: 0.1253 - val_acc: 0.9572
Q 382+47
T 429
☑ 429
---
Q 9+929
T 938
☑ 938
---
Q 185+820
T 1005
☒ 995
---
Q 396+71
T 467
☑ 467
---
Q 0+62
T 62
☑ 62
---
Q 46+821
T 867
☒ 857
---
Q 50+404
T 454
☑ 454
---
Q 8+396
T 404
☑ 404
---
Q 410+227
T 637
☑ 637
---
Q 23+984
T 1007
☑ 1007
---
--------------------------------------------------
Iteration 55
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0179 - acc: 0.9948 - val_loss: 0.0065 - val_acc: 0.9984
Q 210+114
T 324
☑ 324
---
Q 41+886
T 927
☑ 927
---
Q 801+29
T 830
☑ 830
---
Q 52+669
T 721
☑ 721
---
Q 31+131
T 162
☑ 162
---
Q 873+27
T 900
☑ 900
---
Q 718+77
T 795
☑ 795
---
Q 34+174
T 208
☑ 208
---
Q 99+298
T 397
☑ 397
---
Q 315+823
T 1138
☑ 1138
---
--------------------------------------------------
Iteration 56
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0020 - acc: 0.9999 - val_loss: 0.0049 - val_acc: 0.9990
Q 704+14
T 718
☑ 718
---
Q 892+964
T 1856
☑ 1856
---
Q 888+74
T 962
☑ 962
---
Q 82+211
T 293
☑ 293
---
Q 67+17
T 84
☑ 84
---
Q 72+628
T 700
☑ 700
---
Q 93+786
T 879
☑ 879
---
Q 8+450
T 458
☑ 458
---
Q 25+73
T 98
☑ 98
---
Q 51+630
T 681
☑ 681
---
--------------------------------------------------
Iteration 57
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0015 - acc: 1.0000 - val_loss: 0.0035 - val_acc: 0.9992
Q 529+82
T 611
☑ 611
---
Q 190+12
T 202
☑ 202
---
Q 9+34
T 43
☑ 43
---
Q 93+104
T 197
☑ 197
---
Q 40+97
T 137
☑ 137
---
Q 269+731
T 1000
☑ 1000
---
Q 39+850
T 889
☑ 889
---
Q 195+139
T 334
☑ 334
---
Q 74+551
T 625
☑ 625
---
Q 5+529
T 534
☑ 534
---
--------------------------------------------------
Iteration 58
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 29s - loss: 0.0012 - acc: 1.0000 - val_loss: 0.0031 - val_acc: 0.9996
Q 24+869
T 893
☑ 893
---
Q 268+53
T 321
☑ 321
---
Q 965+0
T 965
☑ 965
---
Q 80+139
T 219
☑ 219
---
Q 2+819
T 821
☑ 821
---
Q 181+144
T 325
☑ 325
---
Q 949+567
T 1516
☑ 1516
---
Q 318+801
T 1119
☑ 1119
---
Q 71+212
T 283
☑ 283
---
Q 529+631
T 1160
☑ 1160
---
--------------------------------------------------
Iteration 59
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0010 - acc: 1.0000 - val_loss: 0.0033 - val_acc: 0.9994
Q 8+650
T 658
☑ 658
---
Q 39+340
T 379
☑ 379
---
Q 0+130
T 130
☑ 130
---
Q 634+13
T 647
☑ 647
---
Q 38+133
T 171
☑ 171
---
Q 58+587
T 645
☑ 645
---
Q 86+302
T 388
☑ 388
---
Q 836+148
T 984
☑ 984
---
Q 767+34
T 801
☑ 801
---
Q 73+336
T 409
☑ 409
---
--------------------------------------------------
Iteration 60
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0011 - acc: 1.0000 - val_loss: 0.0050 - val_acc: 0.9987
Q 241+67
T 308
☑ 308
---
Q 807+0
T 807
☑ 807
---
Q 59+282
T 341
☑ 341
---
Q 966+94
T 1060
☑ 1060
---
Q 127+646
T 773
☑ 773
---
Q 35+98
T 133
☑ 133
---
Q 704+47
T 751
☑ 751
---
Q 71+661
T 732
☑ 732
---
Q 681+7
T 688
☑ 688
---
Q 5+125
T 130
☑ 130
---
--------------------------------------------------
Iteration 61
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0486 - acc: 0.9855 - val_loss: 0.0062 - val_acc: 0.9986
Q 47+333
T 380
☑ 380
---
Q 822+500
T 1322
☑ 1322
---
Q 25+17
T 42
☑ 42
---
Q 117+12
T 129
☑ 129
---
Q 366+290
T 656
☑ 656
---
Q 873+924
T 1797
☑ 1797
---
Q 14+20
T 34
☑ 34
---
Q 29+386
T 415
☑ 415
---
Q 417+3
T 420
☑ 420
---
Q 627+617
T 1244
☑ 1244
---
--------------------------------------------------
Iteration 62
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0022 - acc: 0.9999 - val_loss: 0.0041 - val_acc: 0.9992
Q 579+72
T 651
☑ 651
---
Q 960+44
T 1004
☑ 1004
---
Q 529+59
T 588
☑ 588
---
Q 590+8
T 598
☑ 598
---
Q 622+4
T 626
☑ 626
---
Q 352+809
T 1161
☑ 1161
---
Q 75+74
T 149
☑ 149
---
Q 489+90
T 579
☑ 579
---
Q 46+313
T 359
☑ 359
---
Q 138+11
T 149
☑ 149
---
--------------------------------------------------
Iteration 63
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0015 - acc: 0.9999 - val_loss: 0.0030 - val_acc: 0.9994
Q 482+5
T 487
☑ 487
---
Q 47+510
T 557
☑ 557
---
Q 325+804
T 1129
☑ 1129
---
Q 253+873
T 1126
☑ 1126
---
Q 616+33
T 649
☑ 649
---
Q 926+310
T 1236
☑ 1236
---
Q 5+890
T 895
☑ 895
---
Q 630+20
T 650
☑ 650
---
Q 535+37
T 572
☑ 572
---
Q 52+402
T 454
☑ 454
---
--------------------------------------------------
Iteration 64
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0011 - acc: 1.0000 - val_loss: 0.0028 - val_acc: 0.9994
Q 523+376
T 899
☑ 899
---
Q 64+310
T 374
☑ 374
---
Q 15+219
T 234
☑ 234
---
Q 400+37
T 437
☑ 437
---
Q 597+364
T 961
☑ 961
---
Q 90+506
T 596
☑ 596
---
Q 890+600
T 1490
☑ 1490
---
Q 155+62
T 217
☑ 217
---
Q 764+17
T 781
☑ 781
---
Q 64+933
T 997
☑ 997
---
--------------------------------------------------
Iteration 65
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 9.1291e-04 - acc: 1.0000 - val_loss: 0.0025 - val_acc: 0.9994
Q 331+304
T 635
☑ 635
---
Q 1+125
T 126
☑ 126
---
Q 5+128
T 133
☑ 133
---
Q 728+675
T 1403
☑ 1403
---
Q 217+370
T 587
☑ 587
---
Q 327+9
T 336
☑ 336
---
Q 46+472
T 518
☑ 518
---
Q 558+18
T 576
☑ 576
---
Q 590+115
T 705
☑ 705
---
Q 72+140
T 212
☑ 212
---
--------------------------------------------------
Iteration 66
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0054 - acc: 0.9986 - val_loss: 0.1097 - val_acc: 0.9686
Q 8+763
T 771
☒ 772
---
Q 81+973
T 1054
☑ 1054
---
Q 53+786
T 839
☑ 839
---
Q 159+44
T 203
☑ 203
---
Q 147+797
T 944
☒ 933
---
Q 179+0
T 179
☒ 189
---
Q 113+439
T 552
☑ 552
---
Q 31+794
T 825
☑ 825
---
Q 538+736
T 1274
☑ 1274
---
Q 494+108
T 602
☑ 602
---
--------------------------------------------------
Iteration 67
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0326 - acc: 0.9903 - val_loss: 0.0047 - val_acc: 0.9991
Q 12+860
T 872
☑ 872
---
Q 41+494
T 535
☑ 535
---
Q 508+364
T 872
☑ 872
---
Q 511+92
T 603
☑ 603
---
Q 85+582
T 667
☑ 667
---
Q 146+45
T 191
☑ 191
---
Q 892+942
T 1834
☑ 1834
---
Q 919+99
T 1018
☑ 1018
---
Q 738+85
T 823
☑ 823
---
Q 54+579
T 633
☑ 633
---
--------------------------------------------------
Iteration 68
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0015 - acc: 0.9999 - val_loss: 0.0032 - val_acc: 0.9994
Q 985+26
T 1011
☑ 1011
---
Q 974+43
T 1017
☑ 1017
---
Q 117+2
T 119
☑ 119
---
Q 196+43
T 239
☑ 239
---
Q 738+748
T 1486
☑ 1486
---
Q 42+253
T 295
☑ 295
---
Q 515+98
T 613
☑ 613
---
Q 149+529
T 678
☑ 678
---
Q 5+956
T 961
☑ 961
---
Q 43+586
T 629
☑ 629
---
--------------------------------------------------
Iteration 69
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 9.6461e-04 - acc: 1.0000 - val_loss: 0.0027 - val_acc: 0.9995
Q 24+14
T 38
☑ 38
---
Q 46+348
T 394
☑ 394
---
Q 23+978
T 1001
☑ 1001
---
Q 1+208
T 209
☑ 209
---
Q 613+538
T 1151
☑ 1151
---
Q 56+296
T 352
☑ 352
---
Q 51+810
T 861
☑ 861
---
Q 929+896
T 1825
☑ 1825
---
Q 128+2
T 130
☑ 130
---
Q 40+14
T 54
☑ 54
---
--------------------------------------------------
Iteration 70
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 8.1041e-04 - acc: 1.0000 - val_loss: 0.0025 - val_acc: 0.9995
Q 373+3
T 376
☑ 376
---
Q 43+586
T 629
☑ 629
---
Q 174+297
T 471
☑ 471
---
Q 615+688
T 1303
☑ 1303
---
Q 759+82
T 841
☑ 841
---
Q 0+842
T 842
☑ 842
---
Q 41+589
T 630
☑ 630
---
Q 58+865
T 923
☑ 923
---
Q 634+903
T 1537
☑ 1537
---
Q 32+477
T 509
☑ 509
---
--------------------------------------------------
Iteration 71
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 8.0131e-04 - acc: 1.0000 - val_loss: 0.0026 - val_acc: 0.9993
Q 693+956
T 1649
☑ 1649
---
Q 13+104
T 117
☑ 117
---
Q 181+144
T 325
☑ 325
---
Q 403+57
T 460
☑ 460
---
Q 151+941
T 1092
☑ 1092
---
Q 721+88
T 809
☑ 809
---
Q 89+62
T 151
☑ 151
---
Q 513+34
T 547
☑ 547
---
Q 133+112
T 245
☑ 245
---
Q 277+4
T 281
☑ 281
---
--------------------------------------------------
Iteration 72
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 7.6304e-04 - acc: 1.0000 - val_loss: 0.0024 - val_acc: 0.9997
Q 761+979
T 1740
☑ 1740
---
Q 68+840
T 908
☑ 908
---
Q 357+57
T 414
☑ 414
---
Q 925+969
T 1894
☑ 1894
---
Q 5+405
T 410
☑ 410
---
Q 774+34
T 808
☑ 808
---
Q 589+10
T 599
☑ 599
---
Q 538+344
T 882
☑ 882
---
Q 880+63
T 943
☑ 943
---
Q 586+7
T 593
☑ 593
---
--------------------------------------------------
Iteration 73
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0354 - acc: 0.9901 - val_loss: 0.0561 - val_acc: 0.9803
Q 0+700
T 700
☑ 700
---
Q 634+542
T 1176
☑ 1176
---
Q 53+487
T 540
☑ 540
---
Q 68+841
T 909
☒ 919
---
Q 740+49
T 789
☑ 789
---
Q 99+861
T 960
☑ 960
---
Q 725+51
T 776
☑ 776
---
Q 71+497
T 568
☑ 568
---
Q 653+34
T 687
☑ 687
---
Q 0+353
T 353
☑ 353
---
--------------------------------------------------
Iteration 74
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0119 - acc: 0.9966 - val_loss: 0.0041 - val_acc: 0.9992
Q 525+39
T 564
☑ 564
---
Q 6+214
T 220
☑ 220
---
Q 796+98
T 894
☑ 894
---
Q 257+37
T 294
☑ 294
---
Q 596+206
T 802
☑ 802
---
Q 748+456
T 1204
☑ 1204
---
Q 22+248
T 270
☑ 270
---
Q 810+318
T 1128
☑ 1128
---
Q 780+903
T 1683
☑ 1683
---
Q 9+193
T 202
☑ 202
---
--------------------------------------------------
Iteration 75
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0012 - acc: 1.0000 - val_loss: 0.0028 - val_acc: 0.9994
Q 584+83
T 667
☑ 667
---
Q 64+353
T 417
☑ 417
---
Q 10+69
T 79
☑ 79
---
Q 52+942
T 994
☑ 994
---
Q 37+13
T 50
☑ 50
---
Q 197+4
T 201
☑ 201
---
Q 990+74
T 1064
☑ 1064
---
Q 253+434
T 687
☑ 687
---
Q 98+431
T 529
☑ 529
---
Q 808+93
T 901
☑ 901
---
--------------------------------------------------
Iteration 76
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 8.3983e-04 - acc: 1.0000 - val_loss: 0.0025 - val_acc: 0.9993
Q 401+85
T 486
☑ 486
---
Q 526+2
T 528
☑ 528
---
Q 961+11
T 972
☑ 972
---
Q 384+18
T 402
☑ 402
---
Q 55+296
T 351
☑ 351
---
Q 349+974
T 1323
☑ 1323
---
Q 45+143
T 188
☑ 188
---
Q 18+219
T 237
☑ 237
---
Q 91+129
T 220
☑ 220
---
Q 92+878
T 970
☑ 970
---
--------------------------------------------------
Iteration 77
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 7.1116e-04 - acc: 1.0000 - val_loss: 0.0023 - val_acc: 0.9994
Q 23+91
T 114
☑ 114
---
Q 616+2
T 618
☑ 618
---
Q 761+979
T 1740
☑ 1740
---
Q 98+88
T 186
☑ 186
---
Q 91+529
T 620
☑ 620
---
Q 379+731
T 1110
☑ 1110
---
Q 664+55
T 719
☑ 719
---
Q 129+999
T 1128
☑ 1128
---
Q 10+381
T 391
☑ 391
---
Q 2+897
T 899
☑ 899
---
--------------------------------------------------
Iteration 78
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 6.1981e-04 - acc: 1.0000 - val_loss: 0.0022 - val_acc: 0.9994
Q 933+84
T 1017
☑ 1017
---
Q 3+530
T 533
☑ 533
---
Q 19+293
T 312
☑ 312
---
Q 374+730
T 1104
☑ 1104
---
Q 92+55
T 147
☑ 147
---
Q 9+343
T 352
☑ 352
---
Q 19+70
T 89
☑ 89
---
Q 34+217
T 251
☑ 251
---
Q 236+948
T 1184
☑ 1184
---
Q 452+81
T 533
☑ 533
---
--------------------------------------------------
Iteration 79
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 5.6210e-04 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 0.9994
Q 382+90
T 472
☑ 472
---
Q 884+80
T 964
☑ 964
---
Q 62+705
T 767
☑ 767
---
Q 71+2
T 73
☑ 73
---
Q 36+70
T 106
☑ 106
---
Q 25+44
T 69
☑ 69
---
Q 867+944
T 1811
☑ 1811
---
Q 802+591
T 1393
☑ 1393
---
Q 720+23
T 743
☑ 743
---
Q 907+445
T 1352
☑ 1352
---
--------------------------------------------------
Iteration 80
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 5.1905e-04 - acc: 1.0000 - val_loss: 0.0027 - val_acc: 0.9991
Q 99+953
T 1052
☑ 1052
---
Q 356+88
T 444
☑ 444
---
Q 40+14
T 54
☑ 54
---
Q 816+22
T 838
☑ 838
---
Q 615+34
T 649
☑ 649
---
Q 50+30
T 80
☑ 80
---
Q 509+563
T 1072
☑ 1072
---
Q 530+1
T 531
☑ 531
---
Q 83+767
T 850
☑ 850
---
Q 348+568
T 916
☑ 916
---
--------------------------------------------------
Iteration 81
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 4.9667e-04 - acc: 1.0000 - val_loss: 0.0025 - val_acc: 0.9994
Q 947+227
T 1174
☑ 1174
---
Q 250+25
T 275
☑ 275
---
Q 238+475
T 713
☑ 713
---
Q 597+21
T 618
☑ 618
---
Q 773+8
T 781
☑ 781
---
Q 36+396
T 432
☑ 432
---
Q 88+79
T 167
☑ 167
---
Q 513+34
T 547
☑ 547
---
Q 60+943
T 1003
☑ 1003
---
Q 42+108
T 150
☑ 150
---
--------------------------------------------------
Iteration 82
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0386 - acc: 0.9884 - val_loss: 0.0189 - val_acc: 0.9937
Q 48+908
T 956
☑ 956
---
Q 808+98
T 906
☑ 906
---
Q 508+2
T 510
☑ 510
---
Q 99+48
T 147
☑ 147
---
Q 590+36
T 626
☑ 626
---
Q 359+3
T 362
☑ 362
---
Q 664+39
T 703
☑ 703
---
Q 313+972
T 1285
☑ 1285
---
Q 381+53
T 434
☑ 434
---
Q 293+176
T 469
☑ 469
---
--------------------------------------------------
Iteration 83
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 0.0035 - acc: 0.9994 - val_loss: 0.0031 - val_acc: 0.9993
Q 319+0
T 319
☑ 319
---
Q 65+721
T 786
☑ 786
---
Q 310+17
T 327
☑ 327
---
Q 513+805
T 1318
☑ 1318
---
Q 257+4
T 261
☑ 261
---
Q 608+234
T 842
☑ 842
---
Q 208+10
T 218
☑ 218
---
Q 441+80
T 521
☑ 521
---
Q 18+43
T 61
☑ 61
---
Q 637+7
T 644
☑ 644
---
--------------------------------------------------
Iteration 84
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 8.9579e-04 - acc: 1.0000 - val_loss: 0.0025 - val_acc: 0.9993
Q 908+63
T 971
☑ 971
---
Q 55+587
T 642
☑ 642
---
Q 24+978
T 1002
☑ 1002
---
Q 690+57
T 747
☑ 747
---
Q 94+10
T 104
☑ 104
---
Q 673+224
T 897
☑ 897
---
Q 590+993
T 1583
☑ 1583
---
Q 37+17
T 54
☑ 54
---
Q 6+614
T 620
☑ 620
---
Q 502+155
T 657
☑ 657
---
--------------------------------------------------
Iteration 85
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 6.7702e-04 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 0.9997
Q 30+849
T 879
☑ 879
---
Q 8+650
T 658
☑ 658
---
Q 24+576
T 600
☑ 600
---
Q 547+85
T 632
☑ 632
---
Q 7+986
T 993
☑ 993
---
Q 547+85
T 632
☑ 632
---
Q 968+2
T 970
☑ 970
---
Q 132+50
T 182
☑ 182
---
Q 813+684
T 1497
☑ 1497
---
Q 658+706
T 1364
☑ 1364
---
--------------------------------------------------
Iteration 86
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 5.8183e-04 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 0.9996
Q 881+0
T 881
☑ 881
---
Q 928+758
T 1686
☑ 1686
---
Q 17+767
T 784
☑ 784
---
Q 372+185
T 557
☑ 557
---
Q 217+338
T 555
☑ 555
---
Q 129+22
T 151
☑ 151
---
Q 557+7
T 564
☑ 564
---
Q 997+885
T 1882
☑ 1882
---
Q 880+63
T 943
☑ 943
---
Q 592+97
T 689
☑ 689
---
--------------------------------------------------
Iteration 87
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 8.8703e-04 - acc: 0.9999 - val_loss: 0.0020 - val_acc: 0.9996
Q 672+990
T 1662
☑ 1662
---
Q 54+402
T 456
☑ 456
---
Q 70+201
T 271
☑ 271
---
Q 24+825
T 849
☑ 849
---
Q 93+50
T 143
☑ 143
---
Q 256+678
T 934
☑ 934
---
Q 851+661
T 1512
☑ 1512
---
Q 538+736
T 1274
☑ 1274
---
Q 33+109
T 142
☑ 142
---
Q 329+795
T 1124
☑ 1124
---
--------------------------------------------------
Iteration 88
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 4.7175e-04 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 0.9996
Q 519+38
T 557
☑ 557
---
Q 545+95
T 640
☑ 640
---
Q 331+3
T 334
☑ 334
---
Q 753+44
T 797
☑ 797
---
Q 258+9
T 267
☑ 267
---
Q 31+385
T 416
☑ 416
---
Q 5+939
T 944
☑ 944
---
Q 793+688
T 1481
☑ 1481
---
Q 15+267
T 282
☑ 282
---
Q 977+5
T 982
☑ 982
---
--------------------------------------------------
Iteration 89
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 3.9875e-04 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 0.9997
Q 179+0
T 179
☑ 179
---
Q 320+56
T 376
☑ 376
---
Q 805+29
T 834
☑ 834
---
Q 129+22
T 151
☑ 151
---
Q 27+376
T 403
☑ 403
---
Q 814+43
T 857
☑ 857
---
Q 18+885
T 903
☑ 903
---
Q 50+30
T 80
☑ 80
---
Q 61+34
T 95
☑ 95
---
Q 12+26
T 38
☑ 38
---
--------------------------------------------------
Iteration 90
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0367 - acc: 0.9900 - val_loss: 0.1267 - val_acc: 0.9598
Q 510+11
T 521
☒ 531
---
Q 98+981
T 1079
☑ 1079
---
Q 181+834
T 1015
☑ 1015
---
Q 51+279
T 330
☑ 330
---
Q 84+623
T 707
☒ 717
---
Q 51+420
T 471
☑ 471
---
Q 263+38
T 301
☑ 301
---
Q 131+572
T 703
☑ 703
---
Q 9+605
T 614
☑ 614
---
Q 9+457
T 466
☑ 466
---
--------------------------------------------------
Iteration 91
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 0.0114 - acc: 0.9968 - val_loss: 0.0046 - val_acc: 0.9987
Q 800+852
T 1652
☑ 1652
---
Q 90+721
T 811
☑ 811
---
Q 671+862
T 1533
☑ 1533
---
Q 8+306
T 314
☑ 314
---
Q 334+694
T 1028
☑ 1028
---
Q 42+179
T 221
☑ 221
---
Q 74+35
T 109
☑ 109
---
Q 97+999
T 1096
☑ 1096
---
Q 528+5
T 533
☑ 533
---
Q 735+86
T 821
☑ 821
---
--------------------------------------------------
Iteration 92
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 0.0010 - acc: 1.0000 - val_loss: 0.0025 - val_acc: 0.9997
Q 95+657
T 752
☑ 752
---
Q 598+220
T 818
☑ 818
---
Q 750+862
T 1612
☑ 1612
---
Q 25+0
T 25
☑ 25
---
Q 402+93
T 495
☑ 495
---
Q 36+675
T 711
☑ 711
---
Q 634+13
T 647
☑ 647
---
Q 97+558
T 655
☑ 655
---
Q 607+1
T 608
☑ 608
---
Q 646+205
T 851
☑ 851
---
--------------------------------------------------
Iteration 93
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 6.6099e-04 - acc: 1.0000 - val_loss: 0.0022 - val_acc: 0.9997
Q 51+630
T 681
☑ 681
---
Q 3+461
T 464
☑ 464
---
Q 760+460
T 1220
☑ 1220
---
Q 688+55
T 743
☑ 743
---
Q 665+59
T 724
☑ 724
---
Q 5+259
T 264
☑ 264
---
Q 115+5
T 120
☑ 120
---
Q 256+678
T 934
☑ 934
---
Q 3+965
T 968
☑ 968
---
Q 325+78
T 403
☑ 403
---
--------------------------------------------------
Iteration 94
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 5.4595e-04 - acc: 1.0000 - val_loss: 0.0020 - val_acc: 0.9997
Q 190+65
T 255
☑ 255
---
Q 817+986
T 1803
☑ 1803
---
Q 346+51
T 397
☑ 397
---
Q 59+339
T 398
☑ 398
---
Q 242+31
T 273
☑ 273
---
Q 671+843
T 1514
☑ 1514
---
Q 41+494
T 535
☑ 535
---
Q 726+332
T 1058
☑ 1058
---
Q 355+751
T 1106
☑ 1106
---
Q 939+937
T 1876
☑ 1876
---
--------------------------------------------------
Iteration 95
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 4.7194e-04 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 0.9996
Q 935+12
T 947
☑ 947
---
Q 60+496
T 556
☑ 556
---
Q 211+0
T 211
☑ 211
---
Q 117+550
T 667
☑ 667
---
Q 510+11
T 521
☑ 521
---
Q 44+954
T 998
☑ 998
---
Q 2+971
T 973
☑ 973
---
Q 0+122
T 122
☑ 122
---
Q 773+8
T 781
☑ 781
---
Q 4+397
T 401
☑ 401
---
--------------------------------------------------
Iteration 96
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 4.1235e-04 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 0.9997
Q 8+54
T 62
☑ 62
---
Q 750+47
T 797
☑ 797
---
Q 379+731
T 1110
☑ 1110
---
Q 449+80
T 529
☑ 529
---
Q 966+7
T 973
☑ 973
---
Q 719+8
T 727
☑ 727
---
Q 123+45
T 168
☑ 168
---
Q 73+459
T 532
☑ 532
---
Q 740+542
T 1282
☑ 1282
---
Q 84+843
T 927
☑ 927
---
--------------------------------------------------
Iteration 97
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 3.6908e-04 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 0.9997
Q 2+126
T 128
☑ 128
---
Q 79+842
T 921
☑ 921
---
Q 768+6
T 774
☑ 774
---
Q 937+360
T 1297
☑ 1297
---
Q 22+1
T 23
☑ 23
---
Q 449+80
T 529
☑ 529
---
Q 590+237
T 827
☑ 827
---
Q 1+258
T 259
☑ 259
---
Q 98+657
T 755
☑ 755
---
Q 426+67
T 493
☑ 493
---
--------------------------------------------------
Iteration 98
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 29s - loss: 3.5174e-04 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 0.9997
Q 696+25
T 721
☑ 721
---
Q 90+606
T 696
☑ 696
---
Q 49+95
T 144
☑ 144
---
Q 438+345
T 783
☑ 783
---
Q 282+4
T 286
☑ 286
---
Q 737+303
T 1040
☑ 1040
---
Q 511+4
T 515
☑ 515
---
Q 29+400
T 429
☑ 429
---
Q 2+372
T 374
☑ 374
---
Q 38+85
T 123
☑ 123
---
--------------------------------------------------
Iteration 99
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 3.2164e-04 - acc: 1.0000 - val_loss: 0.0029 - val_acc: 0.9994
Q 5+529
T 534
☑ 534
---
Q 444+640
T 1084
☑ 1084
---
Q 96+74
T 170
☑ 170
---
Q 93+50
T 143
☑ 143
---
Q 40+59
T 99
☑ 99
---
Q 325+257
T 582
☑ 582
---
Q 8+901
T 909
☑ 909
---
Q 47+20
T 67
☑ 67
---
Q 543+21
T 564
☑ 564
---
Q 837+20
T 857
☑ 857
---
--------------------------------------------------
Iteration 100
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0428 - acc: 0.9881 - val_loss: 0.0072 - val_acc: 0.9980
Q 962+624
T 1586
☑ 1586
---
Q 132+47
T 179
☑ 179
---
Q 828+602
T 1430
☑ 1430
---
Q 15+933
T 948
☑ 948
---
Q 319+58
T 377
☑ 377
---
Q 11+365
T 376
☑ 376
---
Q 623+19
T 642
☑ 642
---
Q 270+61
T 331
☑ 331
---
Q 60+294
T 354
☑ 354
---
Q 312+211
T 523
☑ 523
---
--------------------------------------------------
Iteration 101
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 0.0019 - acc: 0.9998 - val_loss: 0.0026 - val_acc: 0.9994
Q 685+394
T 1079
☑ 1079
---
Q 1+196
T 197
☑ 197
---
Q 65+259
T 324
☑ 324
---
Q 77+139
T 216
☑ 216
---
Q 456+816
T 1272
☑ 1272
---
Q 816+633
T 1449
☑ 1449
---
Q 87+294
T 381
☑ 381
---
Q 9+858
T 867
☑ 867
---
Q 787+894
T 1681
☑ 1681
---
Q 124+25
T 149
☑ 149
---
--------------------------------------------------
Iteration 102
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 6.6114e-04 - acc: 1.0000 - val_loss: 0.0023 - val_acc: 0.9996
Q 949+404
T 1353
☑ 1353
---
Q 9+593
T 602
☑ 602
---
Q 18+76
T 94
☑ 94
---
Q 913+501
T 1414
☑ 1414
---
Q 414+256
T 670
☑ 670
---
Q 6+448
T 454
☑ 454
---
Q 641+62
T 703
☑ 703
---
Q 59+761
T 820
☑ 820
---
Q 15+862
T 877
☑ 877
---
Q 210+497
T 707
☑ 707
---
--------------------------------------------------
Iteration 103
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 30s - loss: 4.9612e-04 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 0.9996
Q 670+13
T 683
☑ 683
---
Q 1+35
T 36
☑ 36
---
Q 6+438
T 444
☑ 444
---
Q 196+208
T 404
☑ 404
---
Q 344+7
T 351
☑ 351
---
Q 893+506
T 1399
☑ 1399
---
Q 729+466
T 1195
☑ 1195
---
Q 529+59
T 588
☑ 588
---
Q 7+169
T 176
☑ 176
---
Q 135+12
T 147
☑ 147
---
--------------------------------------------------
Iteration 104
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 32s - loss: 4.2308e-04 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 0.9996
Q 736+17
T 753
☑ 753
---
Q 830+271
T 1101
☑ 1101
---
Q 732+92
T 824
☑ 824
---
Q 0+31
T 31
☑ 31
---
Q 4+981
T 985
☑ 985
---
Q 1+442
T 443
☑ 443
---
Q 383+43
T 426
☑ 426
---
Q 122+7
T 129
☑ 129
---
Q 917+490
T 1407
☑ 1407
---
Q 3+311
T 314
☑ 314
---
--------------------------------------------------
Iteration 105
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 31s - loss: 3.6788e-04 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 0.9996
Q 51+553
T 604
☑ 604
---
Q 23+800
T 823
☑ 823
---
Q 711+365
T 1076
☑ 1076
---
Q 12+709
T 721
☑ 721
---
Q 844+289
T 1133
☑ 1133
---
Q 867+478
T 1345
☑ 1345
---
Q 538+408
T 946
☑ 946
---
Q 26+963
T 989
☑ 989
---
Q 834+713
T 1547
☑ 1547
---
Q 50+75
T 125
☑ 125
---
--------------------------------------------------
Iteration 106
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 20s - loss: 3.3169e-04 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 0.9994
Q 33+109
T 142
☑ 142
---
Q 12+63
T 75
☑ 75
---
Q 51+630
T 681
☑ 681
---
Q 325+78
T 403
☑ 403
---
Q 39+96
T 135
☑ 135
---
Q 9+783
T 792
☑ 792
---
Q 278+59
T 337
☑ 337
---
Q 603+926
T 1529
☑ 1529
---
Q 749+64
T 813
☑ 813
---
Q 28+970
T 998
☑ 998
---
--------------------------------------------------
Iteration 107
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 3.1954e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9996
Q 945+842
T 1787
☑ 1787
---
Q 873+0
T 873
☑ 873
---
Q 819+182
T 1001
☑ 1001
---
Q 906+38
T 944
☑ 944
---
Q 151+86
T 237
☑ 237
---
Q 59+226
T 285
☑ 285
---
Q 96+595
T 691
☑ 691
---
Q 353+47
T 400
☑ 400
---
Q 234+240
T 474
☑ 474
---
Q 941+227
T 1168
☑ 1168
---
--------------------------------------------------
Iteration 108
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.6826e-04 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 0.9994
Q 2+373
T 375
☑ 375
---
Q 531+79
T 610
☑ 610
---
Q 508+2
T 510
☑ 510
---
Q 84+738
T 822
☑ 822
---
Q 490+137
T 627
☑ 627
---
Q 592+257
T 849
☑ 849
---
Q 371+981
T 1352
☑ 1352
---
Q 41+35
T 76
☑ 76
---
Q 437+90
T 527
☑ 527
---
Q 75+26
T 101
☑ 101
---
--------------------------------------------------
Iteration 109
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 0.0355 - acc: 0.9900 - val_loss: 0.0243 - val_acc: 0.9917.99
Q 40+926
T 966
☑ 966
---
Q 772+545
T 1317
☑ 1317
---
Q 880+5
T 885
☑ 885
---
Q 688+93
T 781
☑ 781
---
Q 937+579
T 1516
☑ 1516
---
Q 78+202
T 280
☑ 280
---
Q 98+981
T 1079
☑ 1079
---
Q 170+481
T 651
☑ 651
---
Q 652+366
T 1018
☑ 1018
---
Q 782+10
T 792
☑ 792
---
--------------------------------------------------
Iteration 110
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 0.0044 - acc: 0.9990 - val_loss: 0.0049 - val_acc: 0.9986
Q 37+433
T 470
☑ 470
---
Q 32+21
T 53
☑ 53
---
Q 950+85
T 1035
☑ 1035
---
Q 895+8
T 903
☑ 903
---
Q 300+44
T 344
☑ 344
---
Q 49+449
T 498
☑ 498
---
Q 3+549
T 552
☑ 552
---
Q 969+3
T 972
☑ 972
---
Q 555+27
T 582
☑ 582
---
Q 636+435
T 1071
☑ 1071
---
--------------------------------------------------
Iteration 111
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 8.9508e-04 - acc: 1.0000 - val_loss: 0.0021 - val_acc: 0.9995
Q 969+262
T 1231
☑ 1231
---
Q 194+64
T 258
☑ 258
---
Q 521+525
T 1046
☑ 1046
---
Q 56+274
T 330
☑ 330
---
Q 53+69
T 122
☑ 122
---
Q 637+7
T 644
☑ 644
---
Q 964+569
T 1533
☑ 1533
---
Q 45+759
T 804
☑ 804
---
Q 586+7
T 593
☑ 593
---
Q 95+311
T 406
☑ 406
---
--------------------------------------------------
Iteration 112
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 4.9268e-04 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 0.9996
Q 703+31
T 734
☑ 734
---
Q 732+570
T 1302
☑ 1302
---
Q 243+875
T 1118
☑ 1118
---
Q 562+623
T 1185
☑ 1185
---
Q 136+5
T 141
☑ 141
---
Q 7+563
T 570
☑ 570
---
Q 59+761
T 820
☑ 820
---
Q 411+17
T 428
☑ 428
---
Q 513+48
T 561
☑ 561
---
Q 93+21
T 114
☑ 114
---
--------------------------------------------------
Iteration 113
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 4.0623e-04 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 0.9996
Q 756+20
T 776
☑ 776
---
Q 44+29
T 73
☑ 73
---
Q 691+671
T 1362
☑ 1362
---
Q 8+175
T 183
☑ 183
---
Q 314+25
T 339
☑ 339
---
Q 10+75
T 85
☑ 85
---
Q 81+79
T 160
☑ 160
---
Q 457+40
T 497
☑ 497
---
Q 859+865
T 1724
☑ 1724
---
Q 82+940
T 1022
☑ 1022
---
--------------------------------------------------
Iteration 114
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.4817e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9997
Q 501+910
T 1411
☑ 1411
---
Q 50+502
T 552
☑ 552
---
Q 330+6
T 336
☑ 336
---
Q 966+7
T 973
☑ 973
---
Q 268+53
T 321
☑ 321
---
Q 56+41
T 97
☑ 97
---
Q 393+76
T 469
☑ 469
---
Q 2+527
T 529
☑ 529
---
Q 867+68
T 935
☑ 935
---
Q 237+17
T 254
☑ 254
---
--------------------------------------------------
Iteration 115
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.0627e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9997
Q 85+127
T 212
☑ 212
---
Q 0+58
T 58
☑ 58
---
Q 296+68
T 364
☑ 364
---
Q 99+475
T 574
☑ 574
---
Q 863+9
T 872
☑ 872
---
Q 274+19
T 293
☑ 293
---
Q 569+3
T 572
☑ 572
---
Q 286+42
T 328
☑ 328
---
Q 122+7
T 129
☑ 129
---
Q 108+33
T 141
☑ 141
---
--------------------------------------------------
Iteration 116
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.7302e-04 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 0.9997
Q 70+59
T 129
☑ 129
---
Q 3+163
T 166
☑ 166
---
Q 530+1
T 531
☑ 531
---
Q 907+264
T 1171
☑ 1171
---
Q 669+68
T 737
☑ 737
---
Q 864+50
T 914
☑ 914
---
Q 72+271
T 343
☑ 343
---
Q 252+17
T 269
☑ 269
---
Q 55+550
T 605
☑ 605
---
Q 5+157
T 162
☑ 162
---
--------------------------------------------------
Iteration 117
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.4437e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9998
Q 722+0
T 722
☑ 722
---
Q 3+630
T 633
☑ 633
---
Q 77+35
T 112
☑ 112
---
Q 835+5
T 840
☑ 840
---
Q 62+248
T 310
☑ 310
---
Q 110+0
T 110
☑ 110
---
Q 726+700
T 1426
☑ 1426
---
Q 97+97
T 194
☑ 194
---
Q 785+112
T 897
☑ 897
---
Q 55+431
T 486
☑ 486
---
--------------------------------------------------
Iteration 118
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.5606e-04 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 0.9996
Q 40+729
T 769
☑ 769
---
Q 880+63
T 943
☑ 943
---
Q 68+746
T 814
☑ 814
---
Q 72+505
T 577
☑ 577
---
Q 133+112
T 245
☑ 245
---
Q 387+165
T 552
☑ 552
---
Q 873+27
T 900
☑ 900
---
Q 351+975
T 1326
☑ 1326
---
Q 830+597
T 1427
☑ 1427
---
Q 113+480
T 593
☑ 593
---
--------------------------------------------------
Iteration 119
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0364 - acc: 0.9903 - val_loss: 0.0044 - val_acc: 0.9990
Q 112+74
T 186
☑ 186
---
Q 55+619
T 674
☑ 674
---
Q 873+53
T 926
☑ 926
---
Q 62+674
T 736
☑ 736
---
Q 537+0
T 537
☑ 537
---
Q 40+389
T 429
☑ 429
---
Q 481+69
T 550
☑ 550
---
Q 245+83
T 328
☑ 328
---
Q 6+142
T 148
☑ 148
---
Q 873+371
T 1244
☑ 1244
---
--------------------------------------------------
Iteration 120
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0028 - acc: 0.9994 - val_loss: 0.0053 - val_acc: 0.9984
Q 23+313
T 336
☑ 336
---
Q 28+475
T 503
☑ 503
---
Q 9+502
T 511
☑ 511
---
Q 455+4
T 459
☑ 459
---
Q 598+90
T 688
☑ 688
---
Q 789+9
T 798
☑ 798
---
Q 340+4
T 344
☑ 344
---
Q 533+53
T 586
☑ 586
---
Q 639+84
T 723
☑ 723
---
Q 75+648
T 723
☑ 723
---
--------------------------------------------------
Iteration 121
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0014 - acc: 0.9997 - val_loss: 0.0024 - val_acc: 0.9995
Q 982+547
T 1529
☑ 1529
---
Q 873+836
T 1709
☑ 1709
---
Q 66+68
T 134
☑ 134
---
Q 123+45
T 168
☑ 168
---
Q 46+472
T 518
☑ 518
---
Q 614+18
T 632
☑ 632
---
Q 897+78
T 975
☑ 975
---
Q 973+554
T 1527
☑ 1527
---
Q 381+1
T 382
☑ 382
---
Q 833+902
T 1735
☑ 1735
---
--------------------------------------------------
Iteration 122
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 4.0803e-04 - acc: 1.0000 - val_loss: 0.0019 - val_acc: 0.9996
Q 215+213
T 428
☑ 428
---
Q 688+93
T 781
☑ 781
---
Q 32+561
T 593
☑ 593
---
Q 1+864
T 865
☑ 865
---
Q 38+85
T 123
☑ 123
---
Q 327+42
T 369
☑ 369
---
Q 119+356
T 475
☑ 475
---
Q 0+776
T 776
☑ 776
---
Q 737+80
T 817
☑ 817
---
Q 457+129
T 586
☑ 586
---
--------------------------------------------------
Iteration 123
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.3046e-04 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 0.9997
Q 99+53
T 152
☑ 152
---
Q 829+42
T 871
☑ 871
---
Q 46+579
T 625
☑ 625
---
Q 939+937
T 1876
☑ 1876
---
Q 87+531
T 618
☑ 618
---
Q 34+694
T 728
☑ 728
---
Q 39+305
T 344
☑ 344
---
Q 40+668
T 708
☑ 708
---
Q 16+997
T 1013
☑ 1013
---
Q 165+945
T 1110
☑ 1110
---
--------------------------------------------------
Iteration 124
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.8636e-04 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 0.9997
Q 685+394
T 1079
☑ 1079
---
Q 462+81
T 543
☑ 543
---
Q 270+61
T 331
☑ 331
---
Q 127+646
T 773
☑ 773
---
Q 990+40
T 1030
☑ 1030
---
Q 227+29
T 256
☑ 256
---
Q 46+769
T 815
☑ 815
---
Q 129+999
T 1128
☑ 1128
---
Q 965+0
T 965
☑ 965
---
Q 6+690
T 696
☑ 696
---
--------------------------------------------------
Iteration 125
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 16s - loss: 2.5346e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9996
Q 2+401
T 403
☑ 403
---
Q 57+396
T 453
☑ 453
---
Q 94+17
T 111
☑ 111
---
Q 116+47
T 163
☑ 163
---
Q 62+256
T 318
☑ 318
---
Q 16+797
T 813
☑ 813
---
Q 75+516
T 591
☑ 591
---
Q 93+919
T 1012
☑ 1012
---
Q 163+11
T 174
☑ 174
---
Q 211+121
T 332
☑ 332
---
--------------------------------------------------
Iteration 126
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.2791e-04 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 0.9996
Q 308+7
T 315
☑ 315
---
Q 18+24
T 42
☑ 42
---
Q 68+153
T 221
☑ 221
---
Q 5+279
T 284
☑ 284
---
Q 694+2
T 696
☑ 696
---
Q 123+45
T 168
☑ 168
---
Q 367+161
T 528
☑ 528
---
Q 703+33
T 736
☑ 736
---
Q 73+318
T 391
☑ 391
---
Q 597+364
T 961
☑ 961
---
--------------------------------------------------
Iteration 127
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.0599e-04 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 0.9997
Q 666+299
T 965
☑ 965
---
Q 709+393
T 1102
☑ 1102
---
Q 89+18
T 107
☑ 107
---
Q 865+206
T 1071
☑ 1071
---
Q 4+516
T 520
☑ 520
---
Q 42+8
T 50
☑ 50
---
Q 317+92
T 409
☑ 409
---
Q 866+41
T 907
☑ 907
---
Q 724+788
T 1512
☑ 1512
---
Q 453+11
T 464
☑ 464
---
--------------------------------------------------
Iteration 128
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.0974e-04 - acc: 1.0000 - val_loss: 0.0036 - val_acc: 0.9989
Q 140+16
T 156
☑ 156
---
Q 7+812
T 819
☑ 819
---
Q 538+521
T 1059
☑ 1059
---
Q 268+27
T 295
☑ 295
---
Q 8+256
T 264
☑ 264
---
Q 617+691
T 1308
☑ 1308
---
Q 565+549
T 1114
☑ 1114
---
Q 431+5
T 436
☑ 436
---
Q 700+8
T 708
☑ 708
---
Q 867+21
T 888
☑ 888
---
--------------------------------------------------
Iteration 129
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0410 - acc: 0.9884 - val_loss: 0.0053 - val_acc: 0.9989
Q 26+568
T 594
☑ 594
---
Q 174+15
T 189
☑ 189
---
Q 25+44
T 69
☑ 69
---
Q 645+95
T 740
☑ 740
---
Q 117+270
T 387
☑ 387
---
Q 42+734
T 776
☑ 776
---
Q 471+33
T 504
☑ 504
---
Q 2+399
T 401
☑ 401
---
Q 497+28
T 525
☑ 525
---
Q 38+902
T 940
☑ 940
---
--------------------------------------------------
Iteration 130
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0107 - acc: 0.9973 - val_loss: 0.0070 - val_acc: 0.9979
Q 990+40
T 1030
☑ 1030
---
Q 253+709
T 962
☑ 962
---
Q 771+867
T 1638
☑ 1638
---
Q 239+379
T 618
☑ 618
---
Q 119+29
T 148
☑ 148
---
Q 201+73
T 274
☑ 274
---
Q 81+646
T 727
☑ 727
---
Q 965+0
T 965
☑ 965
---
Q 356+88
T 444
☑ 444
---
Q 794+70
T 864
☑ 864
---
--------------------------------------------------
Iteration 131
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0013 - acc: 0.9998 - val_loss: 0.0022 - val_acc: 0.9996
Q 70+45
T 115
☑ 115
---
Q 99+861
T 960
☑ 960
---
Q 661+63
T 724
☑ 724
---
Q 609+418
T 1027
☑ 1027
---
Q 43+586
T 629
☑ 629
---
Q 765+67
T 832
☑ 832
---
Q 78+968
T 1046
☑ 1046
---
Q 101+37
T 138
☑ 138
---
Q 751+217
T 968
☑ 968
---
Q 92+750
T 842
☑ 842
---
--------------------------------------------------
Iteration 132
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 4.9136e-04 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 0.9997
Q 907+445
T 1352
☑ 1352
---
Q 719+7
T 726
☑ 726
---
Q 93+104
T 197
☑ 197
---
Q 9+11
T 20
☒ 10
---
Q 728+6
T 734
☑ 734
---
Q 28+135
T 163
☑ 163
---
Q 54+83
T 137
☑ 137
---
Q 6+761
T 767
☑ 767
---
Q 90+277
T 367
☑ 367
---
Q 46+769
T 815
☑ 815
---
--------------------------------------------------
Iteration 133
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.5864e-04 - acc: 1.0000 - val_loss: 0.0018 - val_acc: 0.9997
Q 7+459
T 466
☑ 466
---
Q 5+939
T 944
☑ 944
---
Q 264+94
T 358
☑ 358
---
Q 83+178
T 261
☑ 261
---
Q 208+178
T 386
☑ 386
---
Q 3+483
T 486
☑ 486
---
Q 996+38
T 1034
☑ 1034
---
Q 588+9
T 597
☑ 597
---
Q 142+36
T 178
☑ 178
---
Q 755+71
T 826
☑ 826
---
--------------------------------------------------
Iteration 134
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.0334e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9997
Q 47+602
T 649
☑ 649
---
Q 613+47
T 660
☑ 660
---
Q 754+662
T 1416
☑ 1416
---
Q 511+877
T 1388
☑ 1388
---
Q 68+258
T 326
☑ 326
---
Q 3+216
T 219
☑ 219
---
Q 36+396
T 432
☑ 432
---
Q 51+8
T 59
☑ 59
---
Q 667+603
T 1270
☑ 1270
---
Q 5+252
T 257
☑ 257
---
--------------------------------------------------
Iteration 135
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 19s - loss: 2.6355e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9997
Q 40+134
T 174
☑ 174
---
Q 538+860
T 1398
☑ 1398
---
Q 8+763
T 771
☑ 771
---
Q 995+335
T 1330
☑ 1330
---
Q 773+8
T 781
☑ 781
---
Q 962+51
T 1013
☑ 1013
---
Q 2+897
T 899
☑ 899
---
Q 51+810
T 861
☑ 861
---
Q 3+123
T 126
☑ 126
---
Q 91+495
T 586
☑ 586
---
--------------------------------------------------
Iteration 136
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.3368e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9997
Q 318+541
T 859
☑ 859
---
Q 363+75
T 438
☑ 438
---
Q 53+567
T 620
☑ 620
---
Q 7+126
T 133
☑ 133
---
Q 326+162
T 488
☑ 488
---
Q 121+41
T 162
☑ 162
---
Q 996+810
T 1806
☑ 1806
---
Q 45+762
T 807
☑ 807
---
Q 69+730
T 799
☑ 799
---
Q 46+736
T 782
☑ 782
---
--------------------------------------------------
Iteration 137
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.0864e-04 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 0.9997
Q 2+289
T 291
☑ 291
---
Q 954+289
T 1243
☑ 1243
---
Q 724+64
T 788
☑ 788
---
Q 98+24
T 122
☑ 122
---
Q 74+382
T 456
☑ 456
---
Q 608+60
T 668
☑ 668
---
Q 61+960
T 1021
☑ 1021
---
Q 59+194
T 253
☑ 253
---
Q 49+218
T 267
☑ 267
---
Q 415+540
T 955
☑ 955
---
--------------------------------------------------
Iteration 138
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.8762e-04 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 0.9997
Q 95+498
T 593
☑ 593
---
Q 708+47
T 755
☑ 755
---
Q 35+18
T 53
☑ 53
---
Q 855+48
T 903
☑ 903
---
Q 767+203
T 970
☑ 970
---
Q 176+5
T 181
☑ 181
---
Q 57+82
T 139
☑ 139
---
Q 90+435
T 525
☑ 525
---
Q 83+273
T 356
☑ 356
---
Q 133+637
T 770
☑ 770
---
--------------------------------------------------
Iteration 139
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.6911e-04 - acc: 1.0000 - val_loss: 0.0014 - val_acc: 0.9997
Q 70+320
T 390
☑ 390
---
Q 33+835
T 868
☑ 868
---
Q 203+458
T 661
☑ 661
---
Q 793+1
T 794
☑ 794
---
Q 611+37
T 648
☑ 648
---
Q 167+4
T 171
☑ 171
---
Q 83+625
T 708
☑ 708
---
Q 511+877
T 1388
☑ 1388
---
Q 24+226
T 250
☑ 250
---
Q 41+721
T 762
☑ 762
---
--------------------------------------------------
Iteration 140
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.5227e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9996
Q 94+17
T 111
☑ 111
---
Q 469+29
T 498
☑ 498
---
Q 33+490
T 523
☑ 523
---
Q 9+925
T 934
☑ 934
---
Q 650+502
T 1152
☑ 1152
---
Q 231+412
T 643
☑ 643
---
Q 124+25
T 149
☑ 149
---
Q 589+83
T 672
☑ 672
---
Q 228+933
T 1161
☑ 1161
---
Q 611+92
T 703
☑ 703
---
--------------------------------------------------
Iteration 141
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.5119e-04 - acc: 1.0000 - val_loss: 0.0017 - val_acc: 0.9996
Q 465+3
T 468
☑ 468
---
Q 59+332
T 391
☑ 391
---
Q 552+9
T 561
☑ 561
---
Q 962+131
T 1093
☑ 1093
---
Q 257+37
T 294
☑ 294
---
Q 4+105
T 109
☑ 109
---
Q 757+485
T 1242
☑ 1242
---
Q 58+304
T 362
☑ 362
---
Q 9+11
T 20
☒ 10
---
Q 71+561
T 632
☑ 632
---
--------------------------------------------------
Iteration 142
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 0.0346 - acc: 0.9900 - val_loss: 0.0052 - val_acc: 0.9986
Q 30+849
T 879
☑ 879
---
Q 725+789
T 1514
☑ 1514
---
Q 26+0
T 26
☑ 26
---
Q 277+596
T 873
☑ 873
---
Q 31+251
T 282
☑ 282
---
Q 317+493
T 810
☑ 810
---
Q 607+42
T 649
☑ 649
---
Q 742+42
T 784
☑ 784
---
Q 446+357
T 803
☑ 803
---
Q 42+745
T 787
☑ 787
---
--------------------------------------------------
Iteration 143
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0012 - acc: 0.9999 - val_loss: 0.0019 - val_acc: 0.9996
Q 678+907
T 1585
☑ 1585
---
Q 653+366
T 1019
☑ 1019
---
Q 230+1
T 231
☑ 231
---
Q 24+226
T 250
☑ 250
---
Q 253+709
T 962
☑ 962
---
Q 88+67
T 155
☑ 155
---
Q 57+656
T 713
☑ 713
---
Q 489+197
T 686
☑ 686
---
Q 41+589
T 630
☑ 630
---
Q 133+2
T 135
☑ 135
---
--------------------------------------------------
Iteration 144
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 4.2291e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9997
Q 703+205
T 908
☑ 908
---
Q 38+36
T 74
☑ 74
---
Q 564+265
T 829
☑ 829
---
Q 30+481
T 511
☑ 511
---
Q 937+579
T 1516
☑ 1516
---
Q 804+91
T 895
☑ 895
---
Q 6+10
T 16
☑ 16
---
Q 2+574
T 576
☑ 576
---
Q 0+52
T 52
☑ 52
---
Q 753+44
T 797
☑ 797
---
--------------------------------------------------
Iteration 145
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.2329e-04 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 0.9997
Q 181+22
T 203
☑ 203
---
Q 214+1
T 215
☑ 215
---
Q 231+244
T 475
☑ 475
---
Q 87+251
T 338
☑ 338
---
Q 14+549
T 563
☑ 563
---
Q 80+439
T 519
☑ 519
---
Q 85+95
T 180
☑ 180
---
Q 90+610
T 700
☑ 700
---
Q 396+85
T 481
☑ 481
---
Q 117+1
T 118
☑ 118
---
--------------------------------------------------
Iteration 146
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.7293e-04 - acc: 1.0000 - val_loss: 0.0014 - val_acc: 0.9998
Q 8+52
T 60
☑ 60
---
Q 51+770
T 821
☑ 821
---
Q 77+410
T 487
☑ 487
---
Q 93+866
T 959
☑ 959
---
Q 611+37
T 648
☑ 648
---
Q 7+435
T 442
☑ 442
---
Q 303+31
T 334
☑ 334
---
Q 872+665
T 1537
☑ 1537
---
Q 425+31
T 456
☑ 456
---
Q 95+36
T 131
☑ 131
---
--------------------------------------------------
Iteration 147
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.3483e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9997
Q 36+858
T 894
☑ 894
---
Q 478+550
T 1028
☑ 1028
---
Q 190+65
T 255
☑ 255
---
Q 5+157
T 162
☑ 162
---
Q 26+136
T 162
☑ 162
---
Q 452+223
T 675
☑ 675
---
Q 755+71
T 826
☑ 826
---
Q 384+608
T 992
☑ 992
---
Q 62+59
T 121
☑ 121
---
Q 464+5
T 469
☑ 469
---
--------------------------------------------------
Iteration 148
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.0585e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9997
Q 603+926
T 1529
☑ 1529
---
Q 974+812
T 1786
☑ 1786
---
Q 85+318
T 403
☑ 403
---
Q 18+102
T 120
☑ 120
---
Q 929+424
T 1353
☑ 1353
---
Q 50+11
T 61
☑ 61
---
Q 12+334
T 346
☑ 346
---
Q 647+495
T 1142
☑ 1142
---
Q 162+647
T 809
☑ 809
---
Q 776+927
T 1703
☑ 1703
---
--------------------------------------------------
Iteration 149
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.8323e-04 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 0.9997
Q 71+242
T 313
☑ 313
---
Q 4+284
T 288
☑ 288
---
Q 400+86
T 486
☑ 486
---
Q 535+600
T 1135
☑ 1135
---
Q 209+3
T 212
☑ 212
---
Q 94+313
T 407
☑ 407
---
Q 127+646
T 773
☑ 773
---
Q 510+142
T 652
☑ 652
---
Q 707+78
T 785
☑ 785
---
Q 785+5
T 790
☑ 790
---
--------------------------------------------------
Iteration 150
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.6286e-04 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 0.9996
Q 9+623
T 632
☑ 632
---
Q 91+407
T 498
☑ 498
---
Q 29+386
T 415
☑ 415
---
Q 7+563
T 570
☑ 570
---
Q 753+44
T 797
☑ 797
---
Q 121+249
T 370
☑ 370
---
Q 5+69
T 74
☑ 74
---
Q 1+938
T 939
☑ 939
---
Q 560+53
T 613
☑ 613
---
Q 786+67
T 853
☑ 853
---
--------------------------------------------------
Iteration 151
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.4827e-04 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 0.9997
Q 898+60
T 958
☑ 958
---
Q 5+718
T 723
☑ 723
---
Q 6+305
T 311
☑ 311
---
Q 61+979
T 1040
☑ 1040
---
Q 4+516
T 520
☑ 520
---
Q 23+359
T 382
☑ 382
---
Q 67+35
T 102
☑ 102
---
Q 331+3
T 334
☑ 334
---
Q 117+5
T 122
☑ 122
---
Q 844+53
T 897
☑ 897
---
--------------------------------------------------
Iteration 152
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.3295e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9997
Q 62+907
T 969
☑ 969
---
Q 533+20
T 553
☑ 553
---
Q 919+78
T 997
☑ 997
---
Q 849+669
T 1518
☑ 1518
---
Q 97+618
T 715
☑ 715
---
Q 82+569
T 651
☑ 651
---
Q 872+40
T 912
☑ 912
---
Q 28+64
T 92
☑ 92
---
Q 900+60
T 960
☑ 960
---
Q 594+530
T 1124
☑ 1124
---
--------------------------------------------------
Iteration 153
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.1862e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9997
Q 617+695
T 1312
☑ 1312
---
Q 82+667
T 749
☑ 749
---
Q 794+41
T 835
☑ 835
---
Q 335+334
T 669
☑ 669
---
Q 55+21
T 76
☑ 76
---
Q 0+871
T 871
☑ 871
---
Q 888+40
T 928
☑ 928
---
Q 772+545
T 1317
☑ 1317
---
Q 113+795
T 908
☑ 908
---
Q 31+473
T 504
☑ 504
---
--------------------------------------------------
Iteration 154
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.1075e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9997
Q 241+813
T 1054
☑ 1054
---
Q 55+829
T 884
☑ 884
---
Q 754+662
T 1416
☑ 1416
---
Q 602+810
T 1412
☑ 1412
---
Q 22+35
T 57
☑ 57
---
Q 37+877
T 914
☑ 914
---
Q 703+31
T 734
☑ 734
---
Q 78+780
T 858
☑ 858
---
Q 940+948
T 1888
☑ 1888
---
Q 782+319
T 1101
☑ 1101
---
--------------------------------------------------
Iteration 155
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0375 - acc: 0.9896 - val_loss: 0.0038 - val_acc: 0.9991
Q 8+922
T 930
☑ 930
---
Q 9+546
T 555
☑ 555
---
Q 152+82
T 234
☑ 234
---
Q 141+9
T 150
☑ 150
---
Q 539+3
T 542
☑ 542
---
Q 61+667
T 728
☑ 728
---
Q 8+52
T 60
☑ 60
---
Q 435+84
T 519
☑ 519
---
Q 28+94
T 122
☑ 122
---
Q 6+646
T 652
☑ 652
---
--------------------------------------------------
Iteration 156
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 9.2601e-04 - acc: 0.9999 - val_loss: 0.0019 - val_acc: 0.9995
Q 344+29
T 373
☑ 373
---
Q 61+52
T 113
☑ 113
---
Q 12+16
T 28
☑ 28
---
Q 209+170
T 379
☑ 379
---
Q 7+23
T 30
☑ 30
---
Q 508+0
T 508
☑ 508
---
Q 491+1
T 492
☑ 492
---
Q 32+196
T 228
☑ 228
---
Q 905+56
T 961
☑ 961
---
Q 69+13
T 82
☑ 82
---
--------------------------------------------------
Iteration 157
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.7565e-04 - acc: 1.0000 - val_loss: 0.0015 - val_acc: 0.9997
Q 34+694
T 728
☑ 728
---
Q 933+85
T 1018
☑ 1018
---
Q 10+98
T 108
☑ 108
---
Q 59+270
T 329
☑ 329
---
Q 545+87
T 632
☑ 632
---
Q 7+70
T 77
☑ 77
---
Q 6+555
T 561
☑ 561
---
Q 65+888
T 953
☑ 953
---
Q 188+147
T 335
☑ 335
---
Q 92+614
T 706
☑ 706
---
--------------------------------------------------
Iteration 158
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.8824e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9997
Q 719+8
T 727
☑ 727
---
Q 81+793
T 874
☑ 874
---
Q 75+756
T 831
☑ 831
---
Q 785+5
T 790
☑ 790
---
Q 158+521
T 679
☑ 679
---
Q 1+619
T 620
☑ 620
---
Q 313+972
T 1285
☑ 1285
---
Q 647+495
T 1142
☑ 1142
---
Q 605+496
T 1101
☑ 1101
---
Q 89+184
T 273
☑ 273
---
--------------------------------------------------
Iteration 159
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.4042e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9997
Q 768+4
T 772
☑ 772
---
Q 596+823
T 1419
☑ 1419
---
Q 21+444
T 465
☑ 465
---
Q 16+554
T 570
☑ 570
---
Q 591+0
T 591
☑ 591
---
Q 762+133
T 895
☑ 895
---
Q 522+2
T 524
☑ 524
---
Q 40+97
T 137
☑ 137
---
Q 298+266
T 564
☑ 564
---
Q 691+236
T 927
☑ 927
---
--------------------------------------------------
Iteration 160
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.0695e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9997
Q 718+86
T 804
☑ 804
---
Q 67+969
T 1036
☑ 1036
---
Q 166+71
T 237
☑ 237
---
Q 6+624
T 630
☑ 630
---
Q 227+86
T 313
☑ 313
---
Q 98+179
T 277
☑ 277
---
Q 112+74
T 186
☑ 186
---
Q 263+38
T 301
☑ 301
---
Q 261+2
T 263
☑ 263
---
Q 6+133
T 139
☑ 139
---
--------------------------------------------------
Iteration 161
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.8032e-04 - acc: 1.0000 - val_loss: 0.0010 - val_acc: 0.9997
Q 923+73
T 996
☑ 996
---
Q 174+15
T 189
☑ 189
---
Q 223+37
T 260
☑ 260
---
Q 606+725
T 1331
☑ 1331
---
Q 521+22
T 543
☑ 543
---
Q 172+15
T 187
☑ 187
---
Q 860+9
T 869
☑ 869
---
Q 552+409
T 961
☑ 961
---
Q 564+14
T 578
☑ 578
---
Q 562+623
T 1185
☑ 1185
---
--------------------------------------------------
Iteration 162
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.6039e-04 - acc: 1.0000 - val_loss: 9.9766e-04 - val_acc: 0.9997
Q 49+207
T 256
☑ 256
---
Q 898+60
T 958
☑ 958
---
Q 382+47
T 429
☑ 429
---
Q 8+622
T 630
☑ 630
---
Q 765+748
T 1513
☑ 1513
---
Q 11+293
T 304
☑ 304
---
Q 48+908
T 956
☑ 956
---
Q 58+497
T 555
☑ 555
---
Q 667+603
T 1270
☑ 1270
---
Q 744+747
T 1491
☑ 1491
---
--------------------------------------------------
Iteration 163
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.4241e-04 - acc: 1.0000 - val_loss: 9.9952e-04 - val_acc: 0.9997
Q 106+72
T 178
☑ 178
---
Q 690+57
T 747
☑ 747
---
Q 382+47
T 429
☑ 429
---
Q 806+157
T 963
☑ 963
---
Q 535+993
T 1528
☑ 1528
---
Q 581+75
T 656
☑ 656
---
Q 975+42
T 1017
☑ 1017
---
Q 78+780
T 858
☑ 858
---
Q 50+95
T 145
☑ 145
---
Q 801+97
T 898
☑ 898
---
--------------------------------------------------
Iteration 164
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.2725e-04 - acc: 1.0000 - val_loss: 0.0010 - val_acc: 0.9997
Q 774+164
T 938
☑ 938
---
Q 867+944
T 1811
☑ 1811
---
Q 13+48
T 61
☑ 61
---
Q 16+62
T 78
☑ 78
---
Q 674+33
T 707
☑ 707
---
Q 363+75
T 438
☑ 438
---
Q 7+307
T 314
☑ 314
---
Q 6+996
T 1002
☑ 1002
---
Q 32+363
T 395
☑ 395
---
Q 93+866
T 959
☑ 959
---
--------------------------------------------------
Iteration 165
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.1405e-04 - acc: 1.0000 - val_loss: 9.5987e-04 - val_acc: 0.9997
Q 40+49
T 89
☑ 89
---
Q 907+98
T 1005
☑ 1005
---
Q 56+758
T 814
☑ 814
---
Q 804+98
T 902
☑ 902
---
Q 36+858
T 894
☑ 894
---
Q 237+5
T 242
☑ 242
---
Q 91+64
T 155
☑ 155
---
Q 1+938
T 939
☑ 939
---
Q 6+343
T 349
☑ 349
---
Q 97+85
T 182
☑ 182
---
--------------------------------------------------
Iteration 166
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.0392e-04 - acc: 1.0000 - val_loss: 8.6710e-04 - val_acc: 0.9998
Q 34+694
T 728
☑ 728
---
Q 822+500
T 1322
☑ 1322
---
Q 991+7
T 998
☑ 998
---
Q 9+557
T 566
☑ 566
---
Q 169+44
T 213
☑ 213
---
Q 735+19
T 754
☑ 754
---
Q 197+131
T 328
☑ 328
---
Q 381+68
T 449
☑ 449
---
Q 42+595
T 637
☑ 637
---
Q 65+73
T 138
☑ 138
---
--------------------------------------------------
Iteration 167
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0105 - acc: 0.9974 - val_loss: 0.2101 - val_acc: 0.9476
Q 90+277
T 367
☑ 367
---
Q 340+0
T 340
☑ 340
---
Q 366+4
T 370
☑ 370
---
Q 535+993
T 1528
☑ 1528
---
Q 60+982
T 1042
☑ 1042
---
Q 771+867
T 1638
☒ 1538
---
Q 9+375
T 384
☑ 384
---
Q 769+26
T 795
☑ 795
---
Q 894+22
T 916
☑ 916
---
Q 80+6
T 86
☑ 86
---
--------------------------------------------------
Iteration 168
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0299 - acc: 0.9915 - val_loss: 0.0025 - val_acc: 0.9993
Q 897+913
T 1810
☑ 1810
---
Q 434+717
T 1151
☑ 1151
---
Q 16+62
T 78
☑ 78
---
Q 526+2
T 528
☑ 528
---
Q 29+429
T 458
☑ 458
---
Q 2+823
T 825
☑ 825
---
Q 533+53
T 586
☑ 586
---
Q 32+10
T 42
☑ 42
---
Q 287+9
T 296
☑ 296
---
Q 21+125
T 146
☑ 146
---
--------------------------------------------------
Iteration 169
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 6.4347e-04 - acc: 1.0000 - val_loss: 0.0016 - val_acc: 0.9997
Q 99+109
T 208
☑ 208
---
Q 44+51
T 95
☑ 95
---
Q 496+78
T 574
☑ 574
---
Q 499+534
T 1033
☑ 1033
---
Q 312+919
T 1231
☑ 1231
---
Q 961+580
T 1541
☑ 1541
---
Q 346+51
T 397
☑ 397
---
Q 113+795
T 908
☑ 908
---
Q 357+40
T 397
☑ 397
---
Q 43+5
T 48
☑ 48
---
--------------------------------------------------
Iteration 170
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.5476e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9998
Q 19+862
T 881
☑ 881
---
Q 44+465
T 509
☑ 509
---
Q 533+20
T 553
☑ 553
---
Q 87+30
T 117
☑ 117
---
Q 122+292
T 414
☑ 414
---
Q 4+188
T 192
☑ 192
---
Q 531+232
T 763
☑ 763
---
Q 888+40
T 928
☑ 928
---
Q 62+329
T 391
☑ 391
---
Q 67+4
T 71
☑ 71
---
--------------------------------------------------
Iteration 171
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.7804e-04 - acc: 1.0000 - val_loss: 0.0013 - val_acc: 0.9997
Q 66+529
T 595
☑ 595
---
Q 670+13
T 683
☑ 683
---
Q 132+50
T 182
☑ 182
---
Q 967+44
T 1011
☑ 1011
---
Q 7+313
T 320
☑ 320
---
Q 53+680
T 733
☑ 733
---
Q 466+896
T 1362
☑ 1362
---
Q 285+53
T 338
☑ 338
---
Q 66+590
T 656
☑ 656
---
Q 853+567
T 1420
☑ 1420
---
--------------------------------------------------
Iteration 172
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.3245e-04 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 0.9998
Q 343+247
T 590
☑ 590
---
Q 337+66
T 403
☑ 403
---
Q 197+131
T 328
☑ 328
---
Q 718+686
T 1404
☑ 1404
---
Q 565+35
T 600
☑ 600
---
Q 147+43
T 190
☑ 190
---
Q 906+4
T 910
☑ 910
---
Q 28+361
T 389
☑ 389
---
Q 8+466
T 474
☑ 474
---
Q 140+73
T 213
☑ 213
---
--------------------------------------------------
Iteration 173
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.0000e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9997
Q 99+0
T 99
☑ 99
---
Q 7+524
T 531
☑ 531
---
Q 157+244
T 401
☑ 401
---
Q 492+485
T 977
☑ 977
---
Q 206+246
T 452
☑ 452
---
Q 62+248
T 310
☑ 310
---
Q 41+79
T 120
☑ 120
---
Q 32+43
T 75
☑ 75
---
Q 92+614
T 706
☑ 706
---
Q 1+536
T 537
☑ 537
---
--------------------------------------------------
Iteration 174
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.7453e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9998
Q 441+80
T 521
☑ 521
---
Q 7+716
T 723
☑ 723
---
Q 89+744
T 833
☑ 833
---
Q 120+16
T 136
☑ 136
---
Q 992+753
T 1745
☑ 1745
---
Q 755+71
T 826
☑ 826
---
Q 623+47
T 670
☑ 670
---
Q 61+88
T 149
☑ 149
---
Q 718+83
T 801
☑ 801
---
Q 975+574
T 1549
☑ 1549
---
--------------------------------------------------
Iteration 175
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.5390e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9997
Q 139+94
T 233
☑ 233
---
Q 577+657
T 1234
☑ 1234
---
Q 428+8
T 436
☑ 436
---
Q 89+36
T 125
☑ 125
---
Q 188+832
T 1020
☑ 1020
---
Q 795+147
T 942
☑ 942
---
Q 225+797
T 1022
☑ 1022
---
Q 118+6
T 124
☑ 124
---
Q 663+4
T 667
☑ 667
---
Q 375+680
T 1055
☑ 1055
---
--------------------------------------------------
Iteration 176
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.3661e-04 - acc: 1.0000 - val_loss: 0.0010 - val_acc: 0.9998
Q 849+669
T 1518
☑ 1518
---
Q 124+5
T 129
☑ 129
---
Q 30+759
T 789
☑ 789
---
Q 53+855
T 908
☑ 908
---
Q 4+188
T 192
☑ 192
---
Q 87+531
T 618
☑ 618
---
Q 85+862
T 947
☑ 947
---
Q 589+711
T 1300
☑ 1300
---
Q 47+972
T 1019
☑ 1019
---
Q 403+57
T 460
☑ 460
---
--------------------------------------------------
Iteration 177
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.2217e-04 - acc: 1.0000 - val_loss: 9.7273e-04 - val_acc: 0.9998
Q 19+651
T 670
☑ 670
---
Q 521+425
T 946
☑ 946
---
Q 799+9
T 808
☑ 808
---
Q 2+610
T 612
☑ 612
---
Q 906+38
T 944
☑ 944
---
Q 769+26
T 795
☑ 795
---
Q 356+24
T 380
☑ 380
---
Q 183+622
T 805
☑ 805
---
Q 75+756
T 831
☑ 831
---
Q 65+941
T 1006
☑ 1006
---
--------------------------------------------------
Iteration 178
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.0928e-04 - acc: 1.0000 - val_loss: 9.5509e-04 - val_acc: 0.9997
Q 231+39
T 270
☑ 270
---
Q 5+865
T 870
☑ 870
---
Q 52+992
T 1044
☑ 1044
---
Q 413+943
T 1356
☑ 1356
---
Q 9+783
T 792
☑ 792
---
Q 99+289
T 388
☑ 388
---
Q 491+84
T 575
☑ 575
---
Q 41+35
T 76
☑ 76
---
Q 240+666
T 906
☑ 906
---
Q 148+83
T 231
☑ 231
---
--------------------------------------------------
Iteration 179
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 9.8416e-05 - acc: 1.0000 - val_loss: 9.0127e-04 - val_acc: 0.9998
Q 98+32
T 130
☑ 130
---
Q 998+704
T 1702
☑ 1702
---
Q 279+832
T 1111
☑ 1111
---
Q 313+706
T 1019
☑ 1019
---
Q 529+631
T 1160
☑ 1160
---
Q 105+72
T 177
☑ 177
---
Q 694+2
T 696
☑ 696
---
Q 17+38
T 55
☑ 55
---
Q 766+18
T 784
☑ 784
---
Q 835+5
T 840
☑ 840
---
--------------------------------------------------
Iteration 180
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 8.9614e-05 - acc: 1.0000 - val_loss: 9.7640e-04 - val_acc: 0.9998
Q 57+53
T 110
☑ 110
---
Q 22+790
T 812
☑ 812
---
Q 744+267
T 1011
☑ 1011
---
Q 814+43
T 857
☑ 857
---
Q 30+759
T 789
☑ 789
---
Q 957+0
T 957
☑ 957
---
Q 634+13
T 647
☑ 647
---
Q 657+256
T 913
☑ 913
---
Q 69+97
T 166
☑ 166
---
Q 383+43
T 426
☑ 426
---
--------------------------------------------------
Iteration 181
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0324 - acc: 0.9917 - val_loss: 0.0058 - val_acc: 0.9983
Q 190+97
T 287
☑ 287
---
Q 129+999
T 1128
☑ 1128
---
Q 952+351
T 1303
☑ 1303
---
Q 390+461
T 851
☑ 851
---
Q 68+258
T 326
☑ 326
---
Q 278+349
T 627
☑ 627
---
Q 568+7
T 575
☑ 575
---
Q 58+589
T 647
☑ 647
---
Q 425+31
T 456
☑ 456
---
Q 9+508
T 517
☑ 517
---
--------------------------------------------------
Iteration 182
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0013 - acc: 0.9998 - val_loss: 0.0016 - val_acc: 0.9996
Q 713+614
T 1327
☑ 1327
---
Q 113+271
T 384
☑ 384
---
Q 74+658
T 732
☑ 732
---
Q 81+26
T 107
☑ 107
---
Q 270+70
T 340
☑ 340
---
Q 91+759
T 850
☑ 850
---
Q 382+13
T 395
☑ 395
---
Q 1+286
T 287
☑ 287
---
Q 363+75
T 438
☑ 438
---
Q 184+223
T 407
☑ 407
---
--------------------------------------------------
Iteration 183
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.6884e-04 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 0.9996
Q 9+52
T 61
☑ 61
---
Q 89+510
T 599
☑ 599
---
Q 237+6
T 243
☑ 243
---
Q 42+734
T 776
☑ 776
---
Q 365+15
T 380
☑ 380
---
Q 914+63
T 977
☑ 977
---
Q 68+129
T 197
☑ 197
---
Q 5+157
T 162
☑ 162
---
Q 51+3
T 54
☑ 54
---
Q 122+99
T 221
☑ 221
---
--------------------------------------------------
Iteration 184
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 2.5577e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9996
Q 203+748
T 951
☑ 951
---
Q 757+485
T 1242
☑ 1242
---
Q 896+9
T 905
☑ 905
---
Q 578+464
T 1042
☑ 1042
---
Q 2+843
T 845
☑ 845
---
Q 849+669
T 1518
☑ 1518
---
Q 58+733
T 791
☑ 791
---
Q 653+366
T 1019
☑ 1019
---
Q 25+229
T 254
☑ 254
---
Q 914+57
T 971
☑ 971
---
--------------------------------------------------
Iteration 185
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.0894e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9997
Q 664+55
T 719
☑ 719
---
Q 747+922
T 1669
☑ 1669
---
Q 10+59
T 69
☑ 69
---
Q 254+19
T 273
☑ 273
---
Q 71+561
T 632
☑ 632
---
Q 53+786
T 839
☑ 839
---
Q 50+276
T 326
☑ 326
---
Q 149+77
T 226
☑ 226
---
Q 150+95
T 245
☑ 245
---
Q 18+8
T 26
☑ 26
---
--------------------------------------------------
Iteration 186
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.7806e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9997
Q 107+198
T 305
☑ 305
---
Q 314+14
T 328
☑ 328
---
Q 344+64
T 408
☑ 408
---
Q 872+135
T 1007
☑ 1007
---
Q 52+942
T 994
☑ 994
---
Q 446+357
T 803
☑ 803
---
Q 790+730
T 1520
☑ 1520
---
Q 100+742
T 842
☑ 842
---
Q 74+26
T 100
☑ 100
---
Q 835+640
T 1475
☑ 1475
---
--------------------------------------------------
Iteration 187
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.5486e-04 - acc: 1.0000 - val_loss: 9.7700e-04 - val_acc: 0.9997
Q 794+508
T 1302
☑ 1302
---
Q 51+189
T 240
☑ 240
---
Q 723+573
T 1296
☑ 1296
---
Q 76+19
T 95
☑ 95
---
Q 398+9
T 407
☑ 407
---
Q 44+90
T 134
☑ 134
---
Q 570+657
T 1227
☑ 1227
---
Q 56+41
T 97
☑ 97
---
Q 4+886
T 890
☒ 880
---
Q 67+187
T 254
☑ 254
---
--------------------------------------------------
Iteration 188
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.3622e-04 - acc: 1.0000 - val_loss: 9.8483e-04 - val_acc: 0.9997
Q 0+198
T 198
☑ 198
---
Q 119+50
T 169
☑ 169
---
Q 51+54
T 105
☑ 105
---
Q 17+226
T 243
☑ 243
---
Q 841+256
T 1097
☑ 1097
---
Q 178+851
T 1029
☑ 1029
---
Q 7+333
T 340
☑ 340
---
Q 148+389
T 537
☑ 537
---
Q 556+95
T 651
☑ 651
---
Q 815+30
T 845
☑ 845
---
--------------------------------------------------
Iteration 189
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.2106e-04 - acc: 1.0000 - val_loss: 9.3022e-04 - val_acc: 0.9997
Q 79+83
T 162
☑ 162
---
Q 341+181
T 522
☑ 522
---
Q 96+595
T 691
☑ 691
---
Q 319+58
T 377
☑ 377
---
Q 91+432
T 523
☑ 523
---
Q 56+289
T 345
☑ 345
---
Q 369+32
T 401
☑ 401
---
Q 431+445
T 876
☑ 876
---
Q 338+21
T 359
☑ 359
---
Q 434+263
T 697
☑ 697
---
--------------------------------------------------
Iteration 190
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 1.0793e-04 - acc: 1.0000 - val_loss: 8.7021e-04 - val_acc: 0.9997
Q 60+314
T 374
☑ 374
---
Q 2+109
T 111
☑ 111
---
Q 372+185
T 557
☑ 557
---
Q 28+452
T 480
☑ 480
---
Q 49+669
T 718
☑ 718
---
Q 312+211
T 523
☑ 523
---
Q 26+385
T 411
☑ 411
---
Q 529+692
T 1221
☑ 1221
---
Q 794+41
T 835
☑ 835
---
Q 135+53
T 188
☑ 188
---
--------------------------------------------------
Iteration 191
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 19s - loss: 9.6888e-05 - acc: 1.0000 - val_loss: 9.1206e-04 - val_acc: 0.9997
Q 656+663
T 1319
☑ 1319
---
Q 55+21
T 76
☑ 76
---
Q 12+26
T 38
☑ 38
---
Q 47+233
T 280
☑ 280
---
Q 390+461
T 851
☑ 851
---
Q 1+210
T 211
☑ 211
---
Q 64+268
T 332
☑ 332
---
Q 455+4
T 459
☑ 459
---
Q 994+205
T 1199
☑ 1199
---
Q 729+466
T 1195
☑ 1195
---
--------------------------------------------------
Iteration 192
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 19s - loss: 8.7078e-05 - acc: 1.0000 - val_loss: 9.0645e-04 - val_acc: 0.9997
Q 80+6
T 86
☑ 86
---
Q 51+480
T 531
☑ 531
---
Q 88+452
T 540
☑ 540
---
Q 975+33
T 1008
☑ 1008
---
Q 770+722
T 1492
☑ 1492
---
Q 623+19
T 642
☑ 642
---
Q 199+82
T 281
☑ 281
---
Q 117+48
T 165
☑ 165
---
Q 809+744
T 1553
☑ 1553
---
Q 953+0
T 953
☑ 953
---
--------------------------------------------------
Iteration 193
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 7.8512e-05 - acc: 1.0000 - val_loss: 8.3686e-04 - val_acc: 0.9997
Q 575+46
T 621
☑ 621
---
Q 722+415
T 1137
☑ 1137
---
Q 86+840
T 926
☑ 926
---
Q 117+550
T 667
☑ 667
---
Q 538+736
T 1274
☑ 1274
---
Q 550+806
T 1356
☑ 1356
---
Q 28+37
T 65
☑ 65
---
Q 672+82
T 754
☑ 754
---
Q 957+310
T 1267
☑ 1267
---
Q 178+851
T 1029
☑ 1029
---
--------------------------------------------------
Iteration 194
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 7.4032e-05 - acc: 1.0000 - val_loss: 7.6828e-04 - val_acc: 0.9997
Q 197+240
T 437
☑ 437
---
Q 79+695
T 774
☑ 774
---
Q 138+939
T 1077
☑ 1077
---
Q 383+43
T 426
☑ 426
---
Q 870+445
T 1315
☑ 1315
---
Q 37+537
T 574
☑ 574
---
Q 65+888
T 953
☑ 953
---
Q 86+806
T 892
☑ 892
---
Q 49+669
T 718
☑ 718
---
Q 28+838
T 866
☑ 866
---
--------------------------------------------------
Iteration 195
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 0.0310 - acc: 0.9916 - val_loss: 0.0048 - val_acc: 0.9986
Q 810+55
T 865
☑ 865
---
Q 717+747
T 1464
☑ 1464
---
Q 37+532
T 569
☑ 569
---
Q 90+238
T 328
☑ 328
---
Q 929+424
T 1353
☑ 1353
---
Q 54+95
T 149
☑ 149
---
Q 884+34
T 918
☑ 918
---
Q 57+72
T 129
☑ 129
---
Q 138+335
T 473
☑ 473
---
Q 207+86
T 293
☑ 293
---
--------------------------------------------------
Iteration 196
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 0.0013 - acc: 0.9998 - val_loss: 0.0015 - val_acc: 0.9997
Q 489+197
T 686
☑ 686
---
Q 81+14
T 95
☑ 95
---
Q 94+17
T 111
☑ 111
---
Q 435+84
T 519
☑ 519
---
Q 88+292
T 380
☑ 380
---
Q 5+961
T 966
☑ 966
---
Q 43+591
T 634
☑ 634
---
Q 39+345
T 384
☑ 384
---
Q 942+112
T 1054
☑ 1054
---
Q 90+277
T 367
☑ 367
---
--------------------------------------------------
Iteration 197
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 3.4687e-04 - acc: 1.0000 - val_loss: 0.0012 - val_acc: 0.9998
Q 23+432
T 455
☑ 455
---
Q 320+649
T 969
☑ 969
---
Q 67+35
T 102
☑ 102
---
Q 726+332
T 1058
☑ 1058
---
Q 109+375
T 484
☑ 484
---
Q 435+181
T 616
☑ 616
---
Q 134+25
T 159
☑ 159
---
Q 673+224
T 897
☑ 897
---
Q 765+213
T 978
☑ 978
---
Q 446+30
T 476
☑ 476
---
--------------------------------------------------
Iteration 198
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 17s - loss: 2.3944e-04 - acc: 1.0000 - val_loss: 0.0011 - val_acc: 0.9998
Q 15+400
T 415
☑ 415
---
Q 40+371
T 411
☑ 411
---
Q 70+600
T 670
☑ 670
---
Q 453+11
T 464
☑ 464
---
Q 718+83
T 801
☑ 801
---
Q 261+969
T 1230
☑ 1230
---
Q 77+39
T 116
☑ 116
---
Q 560+53
T 613
☑ 613
---
Q 30+482
T 512
☑ 512
---
Q 195+74
T 269
☑ 269
---
--------------------------------------------------
Iteration 199
Train on 45000 samples, validate on 5000 samples
Epoch 1/1
45000/45000 [==============================] - 18s - loss: 1.9311e-04 - acc: 1.0000 - val_loss: 0.0010 - val_acc: 0.9998
Q 40+265
T 305
☑ 305
---
Q 151+74
T 225
☑ 225
---
Q 52+617
T 669
☑ 669
---
Q 36+193
T 229
☑ 229
---
Q 198+566
T 764
☑ 764
---
Q 722+754
T 1476
☑ 1476
---
Q 29+597
T 626
☑ 626
---
Q 793+30
T 823
☑ 823
---
Q 720+23
T 743
☑ 743
---
Q 99+298
T 397
☑ 397
---
In [ ]:
Content source: gassantos/ML4Edatics
Similar notebooks: