变化匿名

keras实现卷积神经网络mnist手写数据集识别

以下程序在python 3.5的环境下可以直接运行成功。

from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils

batch_size = 128
nb_classes = 10
nb_epoch = 12

# 输入数据的维度
img_rows, img_cols = 28, 28

(X_train, y_train), (X_test, y_test) = mnist.load_data()

print(X_train.shape)  # 60000个
print(X_test.shape)  # 10000个
X_train = X_train.reshape(X_train.shape[0], img_rows, img_cols, 1)
X_test = X_test.reshape(X_test.shape[0], img_rows, img_cols, 1)
input_shape = (img_rows, img_cols, 1)  # 1代表1通道

x_train = X_train/255.
x_test = X_test/255.
y_train = np_utils.to_categorical(y_train)  # 变成one-hot编码
y_test = np_utils.to_categorical(y_test)

print(y_train.shape)

model = Sequential()
model.add(Convolution2D(16, kernel_size=(5, 5), activation='relu', padding='same', strides=1, input_shape=(img_rows, img_cols, 1)))
model.add(MaxPooling2D(2, 2))
model.add(Convolution2D(8, kernel_size=(5, 5), activation='relu', padding='same', strides=1))
model.add(MaxPooling2D(2, 2))
model.add(Convolution2D(8, kernel_size=(5, 5), activation='relu', padding='same', strides=1))
model.add(MaxPooling2D(2, 2))
model.add(Flatten())
model.add(Dense(1000, activation='relu'))
model.add(Dense(10, activation='softmax'))

model.summary()

model.compile(loss='categorical_crossentropy', optimizer='Adam', metrics=['accuracy'])  # 交叉熵损失函数，Adam下降法
history = model.fit(X_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch, verbose=1, validation_data=(X_test, y_test))  # 开始训练

运行结果如下：

_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_1 (Conv2D)            (None, 28, 28, 16)        416       
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 14, 14, 16)        0         
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 14, 14, 8)         3208      
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 7, 7, 8)           0         
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 7, 7, 8)           1608      
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 3, 3, 8)           0         
_________________________________________________________________
flatten_1 (Flatten)          (None, 72)                0         
_________________________________________________________________
dense_1 (Dense)              (None, 1000)              73000     
_________________________________________________________________
dense_2 (Dense)              (None, 10)                10010     
=================================================================
Total params: 88,242
Trainable params: 88,242
Non-trainable params: 0
_________________________________________________________________
Train on 60000 samples, validate on 10000 samples
Epoch 1/12

  128/60000 [..............................] - ETA: 3:02 - loss: 11.4638 - acc: 0.0703
  256/60000 [..............................] - ETA: 2:01 - loss: 9.9714 - acc: 0.0938 
  384/60000 [..............................] - ETA: 1:39 - loss: 9.0545 - acc: 0.1224
  512/60000 [..............................] - ETA: 1:27 - loss: 8.7409 - acc: 0.1309
  640/60000 [..............................] - ETA: 1:17 - loss: 8.3626 - acc: 0.1500
  768/60000 [..............................] - ETA: 1:11 - loss: 8.0643 - acc: 0.1615
  896/60000 [..............................] - ETA: 1:07 - loss: 7.7652 - acc: 0.1763
 1024/60000 [..............................] - ETA: 1:03 - loss: 7.5162 - acc: 0.1963
 1152/60000 [..............................] - ETA: 1:00 - loss: 7.2951 - acc: 0.2153
 1280/60000 [..............................] - ETA: 59s - loss: 7.0206 - acc: 0.2320 
 1408/60000 [..............................] - ETA: 56s - loss: 6.8069 - acc: 0.2479
 1536/60000 [..............................] - ETA: 56s - loss: 6.4920 - acc: 0.2650
 1664/60000 [..............................] - ETA: 54s - loss: 6.2206 - acc: 0.2746
 1792/60000 [..............................] - ETA: 53s - loss: 5.9817 - acc: 0.2840
 1920/60000 [..............................] - ETA: 52s - loss: 5.7366 - acc: 0.2979
 2048/60000 [>.............................] - ETA: 51s - loss: 5.5341 - acc: 0.3071
 2176/60000 [>.............................] - ETA: 50s - loss: 5.3221 - acc: 0.3153
 2304/60000 [>.............................] - ETA: 49s - loss: 5.1387 - acc: 0.3207
 2432/60000 [>.............................] - ETA: 49s - loss: 4.9679 - acc: 0.3248
 2560/60000 [>.............................] - ETA: 48s - loss: 4.8076 - acc: 0.3281
 2688/60000 [>.............................] - ETA: 47s - loss: 4.6587 - acc: 0.3348
 2816/60000 [>.............................] - ETA: 47s - loss: 4.5180 - acc: 0.3416
 2944/60000 [>.............................] - ETA: 46s - loss: 4.3913 - acc: 0.3505
 3072/60000 [>.............................] - ETA: 46s - loss: 4.2687 - acc: 0.3577
 3200/60000 [>.............................] - ETA: 45s - loss: 4.1486 - acc: 0.3694
 3328/60000 [>.............................] - ETA: 45s - loss: 4.0348 - acc: 0.3789
 3456/60000 [>.............................] - ETA: 45s - loss: 3.9353 - acc: 0.3854
 3584/60000 [>.............................] - ETA: 44s - loss: 3.8398 - acc: 0.3931
 3712/60000 [>.............................] - ETA: 44s - loss: 3.7546 - acc: 0.3968
 3840/60000 [>.............................] - ETA: 43s - loss: 3.6737 - acc: 0.4026
 3968/60000 [>.............................] - ETA: 43s - loss: 3.5959 - acc: 0.4093
 4096/60000 [=>............................] - ETA: 43s - loss: 3.5261 - acc: 0.4143
 4224/60000 [=>............................] - ETA: 43s - loss: 3.4505 - acc: 0.4214
 4352/60000 [=>............................] - ETA: 43s - loss: 3.3799 - acc: 0.4281
 4480/60000 [=>............................] - ETA: 42s - loss: 3.3123 - acc: 0.4350
 4608/60000 [=>............................] - ETA: 42s - loss: 3.2440 - acc: 0.4429
 4736/60000 [=>............................] - ETA: 42s - loss: 3.1815 - acc: 0.4495
 4864/60000 [=>............................] - ETA: 41s - loss: 3.1250 - acc: 0.4554
 4992/60000 [=>............................] - ETA: 41s - loss: 3.0633 - acc: 0.4623
 5120/60000 [=>............................] - ETA: 41s - loss: 3.0115 - acc: 0.4668
 5248/60000 [=>............................] - ETA: 41s - loss: 2.9598 - acc: 0.4720
 5376/60000 [=>............................] - ETA: 41s - loss: 2.9129 - acc: 0.4773
 5504/60000 [=>............................] - ETA: 40s - loss: 2.8581 - acc: 0.4849
 5632/60000 [=>............................] - ETA: 40s - loss: 2.8110 - acc: 0.4906
 5760/60000 [=>............................] - ETA: 40s - loss: 2.7670 - acc: 0.4960
 5888/60000 [=>............................] - ETA: 40s - loss: 2.7250 - acc: 0.5015
 6016/60000 [==>...........................] - ETA: 40s - loss: 2.6872 - acc: 0.5066
 6144/60000 [==>...........................] - ETA: 40s - loss: 2.6538 - acc: 0.5109
 6272/60000 [==>...........................] - ETA: 39s - loss: 2.6123 - acc: 0.5166
 6400/60000 [==>...........................] - ETA: 39s - loss: 2.5745 - acc: 0.5211
 6528/60000 [==>...........................] - ETA: 39s - loss: 2.5413 - acc: 0.5251
 6656/60000 [==>...........................] - ETA: 39s - loss: 2.5077 - acc: 0.5299
 6784/60000 [==>...........................] - ETA: 39s - loss: 2.4747 - acc: 0.5345
 6912/60000 [==>...........................] - ETA: 39s - loss: 2.4423 - acc: 0.5380
 7040/60000 [==>...........................] - ETA: 38s - loss: 2.4094 - acc: 0.5432
 7168/60000 [==>...........................] - ETA: 38s - loss: 2.3792 - acc: 0.5474
 7296/60000 [==>...........................] - ETA: 38s - loss: 2.3481 - acc: 0.5525
 7424/60000 [==>...........................] - ETA: 38s - loss: 2.3164 - acc: 0.5574
 7552/60000 [==>...........................] - ETA: 38s - loss: 2.2875 - acc: 0.5616
 7680/60000 [==>...........................] - ETA: 38s - loss: 2.2598 - acc: 0.5647
 7808/60000 [==>...........................] - ETA: 37s - loss: 2.2303 - acc: 0.5693
 7936/60000 [==>...........................] - ETA: 37s - loss: 2.2027 - acc: 0.5735
 8064/60000 [===>..........................] - ETA: 37s - loss: 2.1758 - acc: 0.5776
 8192/60000 [===>..........................] - ETA: 37s - loss: 2.1515 - acc: 0.5814
 8320/60000 [===>..........................] - ETA: 37s - loss: 2.1264 - acc: 0.5857
 8448/60000 [===>..........................] - ETA: 37s - loss: 2.1038 - acc: 0.5897
 8576/60000 [===>..........................] - ETA: 37s - loss: 2.0823 - acc: 0.5928
 8704/60000 [===>..........................] - ETA: 36s - loss: 2.0625 - acc: 0.5957
 8832/60000 [===>..........................] - ETA: 36s - loss: 2.0403 - acc: 0.5992
 8960/60000 [===>..........................] - ETA: 36s - loss: 2.0184 - acc: 0.6029
 9088/60000 [===>..........................] - ETA: 36s - loss: 1.9966 - acc: 0.6061
 9216/60000 [===>..........................] - ETA: 36s - loss: 1.9763 - acc: 0.6087
 9344/60000 [===>..........................] - ETA: 36s - loss: 1.9554 - acc: 0.6123
 9472/60000 [===>..........................] - ETA: 36s - loss: 1.9350 - acc: 0.6159
 9600/60000 [===>..........................] - ETA: 35s - loss: 1.9167 - acc: 0.6188
 9728/60000 [===>..........................] - ETA: 35s - loss: 1.8997 - acc: 0.6209
 9856/60000 [===>..........................] - ETA: 35s - loss: 1.8818 - acc: 0.6230
 9984/60000 [===>..........................] - ETA: 35s - loss: 1.8627 - acc: 0.6263
10112/60000 [====>.........................] - ETA: 35s - loss: 1.8479 - acc: 0.6279
10240/60000 [====>.........................] - ETA: 35s - loss: 1.8301 - acc: 0.6308
10368/60000 [====>.........................] - ETA: 35s - loss: 1.8143 - acc: 0.6328
10496/60000 [====>.........................] - ETA: 35s - loss: 1.7979 - acc: 0.6354
10624/60000 [====>.........................] - ETA: 35s - loss: 1.7828 - acc: 0.6376
10752/60000 [====>.........................] - ETA: 34s - loss: 1.7687 - acc: 0.6396
10880/60000 [====>.........................] - ETA: 34s - loss: 1.7544 - acc: 0.6417
11008/60000 [====>.........................] - ETA: 34s - loss: 1.7394 - acc: 0.6443
11136/60000 [====>.........................] - ETA: 34s - loss: 1.7227 - acc: 0.6474
11264/60000 [====>.........................] - ETA: 34s - loss: 1.7094 - acc: 0.6499
11392/60000 [====>.........................] - ETA: 34s - loss: 1.6951 - acc: 0.6524
11520/60000 [====>.........................] - ETA: 34s - loss: 1.6817 - acc: 0.6543
11648/60000 [====>.........................] - ETA: 34s - loss: 1.6686 - acc: 0.6565
11776/60000 [====>.........................] - ETA: 33s - loss: 1.6595 - acc: 0.6578
11904/60000 [====>.........................] - ETA: 33s - loss: 1.6487 - acc: 0.6594
12032/60000 [=====>........................] - ETA: 33s - loss: 1.6370 - acc: 0.6612
12160/60000 [=====>........................] - ETA: 33s - loss: 1.6239 - acc: 0.6635
12288/60000 [=====>........................] - ETA: 33s - loss: 1.6119 - acc: 0.6654
12416/60000 [=====>........................] - ETA: 33s - loss: 1.5994 - acc: 0.6674
12544/60000 [=====>........................] - ETA: 33s - loss: 1.5876 - acc: 0.6693
12672/60000 [=====>........................] - ETA: 33s - loss: 1.5766 - acc: 0.6710
12800/60000 [=====>........................] - ETA: 33s - loss: 1.5642 - acc: 0.6734
12928/60000 [=====>........................] - ETA: 32s - loss: 1.5516 - acc: 0.6758
13056/60000 [=====>........................] - ETA: 32s - loss: 1.5396 - acc: 0.6779
13184/60000 [=====>........................] - ETA: 32s - loss: 1.5291 - acc: 0.6801
13312/60000 [=====>........................] - ETA: 32s - loss: 1.5180 - acc: 0.6822
13440/60000 [=====>........................] - ETA: 32s - loss: 1.5079 - acc: 0.6834
13568/60000 [=====>........................] - ETA: 32s - loss: 1.4976 - acc: 0.6851
13696/60000 [=====>........................] - ETA: 32s - loss: 1.4867 - acc: 0.6869
13824/60000 [=====>........................] - ETA: 32s - loss: 1.4777 - acc: 0.6880
13952/60000 [=====>........................] - ETA: 32s - loss: 1.4666 - acc: 0.6900
14080/60000 [======>.......................] - ETA: 32s - loss: 1.4564 - acc: 0.6919
14208/60000 [======>.......................] - ETA: 31s - loss: 1.4452 - acc: 0.6943
14336/60000 [======>.......................] - ETA: 31s - loss: 1.4351 - acc: 0.6961
14464/60000 [======>.......................] - ETA: 31s - loss: 1.4247 - acc: 0.6981
14592/60000 [======>.......................] - ETA: 31s - loss: 1.4175 - acc: 0.6991
14720/60000 [======>.......................] - ETA: 31s - loss: 1.4071 - acc: 0.7012
14848/60000 [======>.......................] - ETA: 31s - loss: 1.3977 - acc: 0.7030
14976/60000 [======>.......................] - ETA: 31s - loss: 1.3879 - acc: 0.7047
15104/60000 [======>.......................] - ETA: 31s - loss: 1.3786 - acc: 0.7064
15232/60000 [======>.......................] - ETA: 31s - loss: 1.3691 - acc: 0.7080
15360/60000 [======>.......................] - ETA: 31s - loss: 1.3602 - acc: 0.7098
15488/60000 [======>.......................] - ETA: 30s - loss: 1.3512 - acc: 0.7115
15616/60000 [======>.......................] - ETA: 30s - loss: 1.3444 - acc: 0.7125
15744/60000 [======>.......................] - ETA: 30s - loss: 1.3363 - acc: 0.7139
15872/60000 [======>.......................] - ETA: 30s - loss: 1.3278 - acc: 0.7154
16000/60000 [=======>......................] - ETA: 30s - loss: 1.3194 - acc: 0.7169
16128/60000 [=======>......................] - ETA: 30s - loss: 1.3110 - acc: 0.7183
16256/60000 [=======>......................] - ETA: 30s - loss: 1.3044 - acc: 0.7196
16384/60000 [=======>......................] - ETA: 30s - loss: 1.2965 - acc: 0.7211
16512/60000 [=======>......................] - ETA: 30s - loss: 1.2899 - acc: 0.7221
16640/60000 [=======>......................] - ETA: 30s - loss: 1.2837 - acc: 0.7237
16768/60000 [=======>......................] - ETA: 29s - loss: 1.2762 - acc: 0.7251
16896/60000 [=======>......................] - ETA: 29s - loss: 1.2691 - acc: 0.7264
17024/60000 [=======>......................] - ETA: 29s - loss: 1.2614 - acc: 0.7280
17152/60000 [=======>......................] - ETA: 29s - loss: 1.2540 - acc: 0.7294
17280/60000 [=======>......................] - ETA: 29s - loss: 1.2465 - acc: 0.7307
17408/60000 [=======>......................] - ETA: 29s - loss: 1.2386 - acc: 0.7324
17536/60000 [=======>......................] - ETA: 29s - loss: 1.2323 - acc: 0.7336
17664/60000 [=======>......................] - ETA: 29s - loss: 1.2271 - acc: 0.7344
17792/60000 [=======>......................] - ETA: 29s - loss: 1.2210 - acc: 0.7356
17920/60000 [=======>......................] - ETA: 29s - loss: 1.2146 - acc: 0.7368
18048/60000 [========>.....................] - ETA: 28s - loss: 1.2091 - acc: 0.7376
18176/60000 [========>.....................] - ETA: 28s - loss: 1.2034 - acc: 0.7387
18304/60000 [========>.....................] - ETA: 28s - loss: 1.1981 - acc: 0.7397
18432/60000 [========>.....................] - ETA: 28s - loss: 1.1912 - acc: 0.7410
18560/60000 [========>.....................] - ETA: 28s - loss: 1.1851 - acc: 0.7420
18688/60000 [========>.....................] - ETA: 28s - loss: 1.1800 - acc: 0.7427
18816/60000 [========>.....................] - ETA: 28s - loss: 1.1741 - acc: 0.7436
18944/60000 [========>.....................] - ETA: 28s - loss: 1.1686 - acc: 0.7446
19072/60000 [========>.....................] - ETA: 28s - loss: 1.1630 - acc: 0.7456
19200/60000 [========>.....................] - ETA: 28s - loss: 1.1584 - acc: 0.7467
19328/60000 [========>.....................] - ETA: 28s - loss: 1.1532 - acc: 0.7475
19456/60000 [========>.....................] - ETA: 27s - loss: 1.1479 - acc: 0.7484
19584/60000 [========>.....................] - ETA: 27s - loss: 1.1432 - acc: 0.7492
19712/60000 [========>.....................] - ETA: 27s - loss: 1.1373 - acc: 0.7503
19840/60000 [========>.....................] - ETA: 27s - loss: 1.1320 - acc: 0.7512
19968/60000 [========>.....................] - ETA: 27s - loss: 1.1261 - acc: 0.7524
20096/60000 [=========>....................] - ETA: 27s - loss: 1.1215 - acc: 0.7531
20224/60000 [=========>....................] - ETA: 27s - loss: 1.1177 - acc: 0.7537
20352/60000 [=========>....................] - ETA: 27s - loss: 1.1122 - acc: 0.7549
20480/60000 [=========>....................] - ETA: 27s - loss: 1.1069 - acc: 0.7559
20608/60000 [=========>....................] - ETA: 27s - loss: 1.1028 - acc: 0.7565
20736/60000 [=========>....................] - ETA: 27s - loss: 1.0976 - acc: 0.7574
20864/60000 [=========>....................] - ETA: 26s - loss: 1.0923 - acc: 0.7584
20992/60000 [=========>....................] - ETA: 26s - loss: 1.0874 - acc: 0.7595
21120/60000 [=========>....................] - ETA: 26s - loss: 1.0821 - acc: 0.7606
21248/60000 [=========>....................] - ETA: 26s - loss: 1.0767 - acc: 0.7617
21376/60000 [=========>....................] - ETA: 26s - loss: 1.0735 - acc: 0.7623
21504/60000 [=========>....................] - ETA: 26s - loss: 1.0689 - acc: 0.7631
21632/60000 [=========>....................] - ETA: 26s - loss: 1.0642 - acc: 0.7640
21760/60000 [=========>....................] - ETA: 26s - loss: 1.0589 - acc: 0.7651
21888/60000 [=========>....................] - ETA: 26s - loss: 1.0545 - acc: 0.7658
22016/60000 [==========>...................] - ETA: 26s - loss: 1.0498 - acc: 0.7667
22144/60000 [==========>...................] - ETA: 26s - loss: 1.0444 - acc: 0.7679
22272/60000 [==========>...................] - ETA: 26s - loss: 1.0401 - acc: 0.7688
22400/60000 [==========>...................] - ETA: 25s - loss: 1.0356 - acc: 0.7697
22528/60000 [==========>...................] - ETA: 25s - loss: 1.0311 - acc: 0.7706
22656/60000 [==========>...................] - ETA: 25s - loss: 1.0266 - acc: 0.7714
22784/60000 [==========>...................] - ETA: 25s - loss: 1.0220 - acc: 0.7724
22912/60000 [==========>...................] - ETA: 25s - loss: 1.0179 - acc: 0.7731
23040/60000 [==========>...................] - ETA: 25s - loss: 1.0137 - acc: 0.7740
23168/60000 [==========>...................] - ETA: 25s - loss: 1.0091 - acc: 0.7749
23296/60000 [==========>...................] - ETA: 25s - loss: 1.0047 - acc: 0.7757
23424/60000 [==========>...................] - ETA: 25s - loss: 1.0011 - acc: 0.7764
23552/60000 [==========>...................] - ETA: 25s - loss: 0.9966 - acc: 0.7771
23680/60000 [==========>...................] - ETA: 25s - loss: 0.9922 - acc: 0.7781
23808/60000 [==========>...................] - ETA: 25s - loss: 0.9884 - acc: 0.7789
23936/60000 [==========>...................] - ETA: 24s - loss: 0.9846 - acc: 0.7797
24064/60000 [===========>..................] - ETA: 24s - loss: 0.9801 - acc: 0.7806
24192/60000 [===========>..................] - ETA: 24s - loss: 0.9757 - acc: 0.7815
24320/60000 [===========>..................] - ETA: 24s - loss: 0.9719 - acc: 0.7823
24448/60000 [===========>..................] - ETA: 24s - loss: 0.9674 - acc: 0.7833
24576/60000 [===========>..................] - ETA: 24s - loss: 0.9638 - acc: 0.7841
24704/60000 [===========>..................] - ETA: 24s - loss: 0.9598 - acc: 0.7848
24832/60000 [===========>..................] - ETA: 24s - loss: 0.9562 - acc: 0.7854
24960/60000 [===========>..................] - ETA: 24s - loss: 0.9529 - acc: 0.7861
25088/60000 [===========>..................] - ETA: 24s - loss: 0.9491 - acc: 0.7866
25216/60000 [===========>..................] - ETA: 24s - loss: 0.9460 - acc: 0.7873
25344/60000 [===========>..................] - ETA: 24s - loss: 0.9419 - acc: 0.7881
25472/60000 [===========>..................] - ETA: 24s - loss: 0.9386 - acc: 0.7887
25600/60000 [===========>..................] - ETA: 23s - loss: 0.9350 - acc: 0.7894
25728/60000 [===========>..................] - ETA: 23s - loss: 0.9312 - acc: 0.7902
25856/60000 [===========>..................] - ETA: 23s - loss: 0.9283 - acc: 0.7908
25984/60000 [===========>..................] - ETA: 23s - loss: 0.9247 - acc: 0.7914
26112/60000 [============>.................] - ETA: 23s - loss: 0.9215 - acc: 0.7919
26240/60000 [============>.................] - ETA: 23s - loss: 0.9186 - acc: 0.7926
26368/60000 [============>.................] - ETA: 23s - loss: 0.9150 - acc: 0.7933
26496/60000 [============>.................] - ETA: 23s - loss: 0.9122 - acc: 0.7938
26624/60000 [============>.................] - ETA: 23s - loss: 0.9089 - acc: 0.7945
26752/60000 [============>.................] - ETA: 23s - loss: 0.9054 - acc: 0.7953
26880/60000 [============>.................] - ETA: 23s - loss: 0.9026 - acc: 0.7958
27008/60000 [============>.................] - ETA: 23s - loss: 0.8994 - acc: 0.7965
27136/60000 [============>.................] - ETA: 23s - loss: 0.8968 - acc: 0.7969
27264/60000 [============>.................] - ETA: 23s - loss: 0.8932 - acc: 0.7976
27392/60000 [============>.................] - ETA: 22s - loss: 0.8900 - acc: 0.7982
27520/60000 [============>.................] - ETA: 22s - loss: 0.8881 - acc: 0.7985
27648/60000 [============>.................] - ETA: 22s - loss: 0.8852 - acc: 0.7991
27776/60000 [============>.................] - ETA: 22s - loss: 0.8825 - acc: 0.7995
27904/60000 [============>.................] - ETA: 22s - loss: 0.8794 - acc: 0.8001
28032/60000 [=============>................] - ETA: 22s - loss: 0.8763 - acc: 0.8007
28160/60000 [=============>................] - ETA: 22s - loss: 0.8732 - acc: 0.8014
28288/60000 [=============>................] - ETA: 22s - loss: 0.8702 - acc: 0.8020
28416/60000 [=============>................] - ETA: 22s - loss: 0.8674 - acc: 0.8025
28544/60000 [=============>................] - ETA: 22s - loss: 0.8650 - acc: 0.8029
28672/60000 [=============>................] - ETA: 22s - loss: 0.8619 - acc: 0.8035
28800/60000 [=============>................] - ETA: 21s - loss: 0.8587 - acc: 0.8041
28928/60000 [=============>................] - ETA: 21s - loss: 0.8562 - acc: 0.8047
29056/60000 [=============>................] - ETA: 21s - loss: 0.8531 - acc: 0.8053
29184/60000 [=============>................] - ETA: 21s - loss: 0.8506 - acc: 0.8057
29312/60000 [=============>................] - ETA: 21s - loss: 0.8478 - acc: 0.8063
29440/60000 [=============>................] - ETA: 21s - loss: 0.8454 - acc: 0.8069
29568/60000 [=============>................] - ETA: 21s - loss: 0.8427 - acc: 0.8075
29696/60000 [=============>................] - ETA: 21s - loss: 0.8401 - acc: 0.8080
29824/60000 [=============>................] - ETA: 21s - loss: 0.8378 - acc: 0.8084
29952/60000 [=============>................] - ETA: 21s - loss: 0.8355 - acc: 0.8088
30080/60000 [==============>...............] - ETA: 21s - loss: 0.8328 - acc: 0.8093
30208/60000 [==============>...............] - ETA: 21s - loss: 0.8300 - acc: 0.8099
30336/60000 [==============>...............] - ETA: 20s - loss: 0.8278 - acc: 0.8102
30464/60000 [==============>...............] - ETA: 20s - loss: 0.8250 - acc: 0.8107
30592/60000 [==============>...............] - ETA: 20s - loss: 0.8227 - acc: 0.8110
30720/60000 [==============>...............] - ETA: 20s - loss: 0.8200 - acc: 0.8115
30848/60000 [==============>...............] - ETA: 20s - loss: 0.8180 - acc: 0.8118
30976/60000 [==============>...............] - ETA: 20s - loss: 0.8154 - acc: 0.8122
31104/60000 [==============>...............] - ETA: 20s - loss: 0.8128 - acc: 0.8127
31232/60000 [==============>...............] - ETA: 20s - loss: 0.8110 - acc: 0.8129
31360/60000 [==============>...............] - ETA: 20s - loss: 0.8087 - acc: 0.8134
31488/60000 [==============>...............] - ETA: 20s - loss: 0.8062 - acc: 0.8139
31616/60000 [==============>...............] - ETA: 20s - loss: 0.8040 - acc: 0.8143
31744/60000 [==============>...............] - ETA: 19s - loss: 0.8011 - acc: 0.8149
31872/60000 [==============>...............] - ETA: 19s - loss: 0.7985 - acc: 0.8154
32000/60000 [===============>..............] - ETA: 19s - loss: 0.7966 - acc: 0.8157
32128/60000 [===============>..............] - ETA: 19s - loss: 0.7941 - acc: 0.8162
32256/60000 [===============>..............] - ETA: 19s - loss: 0.7915 - acc: 0.8167
32384/60000 [===============>..............] - ETA: 19s - loss: 0.7889 - acc: 0.8173
32512/60000 [===============>..............] - ETA: 19s - loss: 0.7869 - acc: 0.8177
32640/60000 [===============>..............] - ETA: 19s - loss: 0.7848 - acc: 0.8182
32768/60000 [===============>..............] - ETA: 19s - loss: 0.7827 - acc: 0.8187
32896/60000 [===============>..............] - ETA: 19s - loss: 0.7812 - acc: 0.8190
33024/60000 [===============>..............] - ETA: 19s - loss: 0.7797 - acc: 0.8193
33152/60000 [===============>..............] - ETA: 18s - loss: 0.7770 - acc: 0.8199
33280/60000 [===============>..............] - ETA: 18s - loss: 0.7748 - acc: 0.8202
33408/60000 [===============>..............] - ETA: 18s - loss: 0.7725 - acc: 0.8207
33536/60000 [===============>..............] - ETA: 18s - loss: 0.7703 - acc: 0.8211
33664/60000 [===============>..............] - ETA: 18s - loss: 0.7689 - acc: 0.8214
33792/60000 [===============>..............] - ETA: 18s - loss: 0.7666 - acc: 0.8218
33920/60000 [===============>..............] - ETA: 18s - loss: 0.7643 - acc: 0.8223
34048/60000 [================>.............] - ETA: 18s - loss: 0.7620 - acc: 0.8228
34176/60000 [================>.............] - ETA: 18s - loss: 0.7600 - acc: 0.8232
34304/60000 [================>.............] - ETA: 18s - loss: 0.7583 - acc: 0.8236
34432/60000 [================>.............] - ETA: 18s - loss: 0.7568 - acc: 0.8239
34560/60000 [================>.............] - ETA: 18s - loss: 0.7546 - acc: 0.8243
34688/60000 [================>.............] - ETA: 17s - loss: 0.7525 - acc: 0.8248
34816/60000 [================>.............] - ETA: 17s - loss: 0.7506 - acc: 0.8252
34944/60000 [================>.............] - ETA: 17s - loss: 0.7484 - acc: 0.8256
35072/60000 [================>.............] - ETA: 17s - loss: 0.7468 - acc: 0.8260
35200/60000 [================>.............] - ETA: 17s - loss: 0.7447 - acc: 0.8264
35328/60000 [================>.............] - ETA: 17s - loss: 0.7428 - acc: 0.8267
35456/60000 [================>.............] - ETA: 17s - loss: 0.7407 - acc: 0.8272
35584/60000 [================>.............] - ETA: 17s - loss: 0.7385 - acc: 0.8276
35712/60000 [================>.............] - ETA: 17s - loss: 0.7363 - acc: 0.8280
35840/60000 [================>.............] - ETA: 17s - loss: 0.7342 - acc: 0.8284
35968/60000 [================>.............] - ETA: 17s - loss: 0.7324 - acc: 0.8287
36096/60000 [=================>............] - ETA: 16s - loss: 0.7307 - acc: 0.8290
36224/60000 [=================>............] - ETA: 16s - loss: 0.7287 - acc: 0.8294
36352/60000 [=================>............] - ETA: 16s - loss: 0.7268 - acc: 0.8299
36480/60000 [=================>............] - ETA: 16s - loss: 0.7251 - acc: 0.8302
36608/60000 [=================>............] - ETA: 16s - loss: 0.7236 - acc: 0.8305
36736/60000 [=================>............] - ETA: 16s - loss: 0.7218 - acc: 0.8309
36864/60000 [=================>............] - ETA: 16s - loss: 0.7199 - acc: 0.8313
36992/60000 [=================>............] - ETA: 16s - loss: 0.7181 - acc: 0.8317
37120/60000 [=================>............] - ETA: 16s - loss: 0.7162 - acc: 0.8322
37248/60000 [=================>............] - ETA: 16s - loss: 0.7150 - acc: 0.8324
37376/60000 [=================>............] - ETA: 16s - loss: 0.7134 - acc: 0.8327
37504/60000 [=================>............] - ETA: 15s - loss: 0.7113 - acc: 0.8332
37632/60000 [=================>............] - ETA: 15s - loss: 0.7097 - acc: 0.8335
37760/60000 [=================>............] - ETA: 15s - loss: 0.7078 - acc: 0.8340
37888/60000 [=================>............] - ETA: 15s - loss: 0.7060 - acc: 0.8343
38016/60000 [==================>...........] - ETA: 15s - loss: 0.7038 - acc: 0.8348
38144/60000 [==================>...........] - ETA: 15s - loss: 0.7020 - acc: 0.8352
38272/60000 [==================>...........] - ETA: 15s - loss: 0.7000 - acc: 0.8355
38400/60000 [==================>...........] - ETA: 15s - loss: 0.6982 - acc: 0.8359
38528/60000 [==================>...........] - ETA: 15s - loss: 0.6964 - acc: 0.8362
38656/60000 [==================>...........] - ETA: 15s - loss: 0.6944 - acc: 0.8367
38784/60000 [==================>...........] - ETA: 15s - loss: 0.6926 - acc: 0.8370
38912/60000 [==================>...........] - ETA: 14s - loss: 0.6911 - acc: 0.8372
39040/60000 [==================>...........] - ETA: 14s - loss: 0.6893 - acc: 0.8377
39168/60000 [==================>...........] - ETA: 14s - loss: 0.6873 - acc: 0.8381
39296/60000 [==================>...........] - ETA: 14s - loss: 0.6859 - acc: 0.8384
39424/60000 [==================>...........] - ETA: 14s - loss: 0.6843 - acc: 0.8387
39552/60000 [==================>...........] - ETA: 14s - loss: 0.6825 - acc: 0.8391
39680/60000 [==================>...........] - ETA: 14s - loss: 0.6807 - acc: 0.8396
39808/60000 [==================>...........] - ETA: 14s - loss: 0.6787 - acc: 0.8400
39936/60000 [==================>...........] - ETA: 14s - loss: 0.6770 - acc: 0.8403
40064/60000 [===================>..........] - ETA: 14s - loss: 0.6755 - acc: 0.8406
40192/60000 [===================>..........] - ETA: 14s - loss: 0.6738 - acc: 0.8410
40320/60000 [===================>..........] - ETA: 13s - loss: 0.6724 - acc: 0.8413
40448/60000 [===================>..........] - ETA: 13s - loss: 0.6709 - acc: 0.8416
40576/60000 [===================>..........] - ETA: 13s - loss: 0.6691 - acc: 0.8420
40704/60000 [===================>..........] - ETA: 13s - loss: 0.6679 - acc: 0.8423
40832/60000 [===================>..........] - ETA: 13s - loss: 0.6661 - acc: 0.8427
40960/60000 [===================>..........] - ETA: 13s - loss: 0.6651 - acc: 0.8429
41088/60000 [===================>..........] - ETA: 13s - loss: 0.6635 - acc: 0.8432
41216/60000 [===================>..........] - ETA: 13s - loss: 0.6619 - acc: 0.8436
41344/60000 [===================>..........] - ETA: 13s - loss: 0.6604 - acc: 0.8439
41472/60000 [===================>..........] - ETA: 13s - loss: 0.6591 - acc: 0.8441
41600/60000 [===================>..........] - ETA: 13s - loss: 0.6576 - acc: 0.8444
41728/60000 [===================>..........] - ETA: 12s - loss: 0.6558 - acc: 0.8448
41856/60000 [===================>..........] - ETA: 12s - loss: 0.6550 - acc: 0.8450
41984/60000 [===================>..........] - ETA: 12s - loss: 0.6534 - acc: 0.8453
42112/60000 [====================>.........] - ETA: 12s - loss: 0.6518 - acc: 0.8457
42240/60000 [====================>.........] - ETA: 12s - loss: 0.6502 - acc: 0.8460
42368/60000 [====================>.........] - ETA: 12s - loss: 0.6487 - acc: 0.8463
42496/60000 [====================>.........] - ETA: 12s - loss: 0.6470 - acc: 0.8467
42624/60000 [====================>.........] - ETA: 12s - loss: 0.6456 - acc: 0.8470
42752/60000 [====================>.........] - ETA: 12s - loss: 0.6439 - acc: 0.8474
42880/60000 [====================>.........] - ETA: 12s - loss: 0.6426 - acc: 0.8477
43008/60000 [====================>.........] - ETA: 12s - loss: 0.6413 - acc: 0.8479
43136/60000 [====================>.........] - ETA: 11s - loss: 0.6403 - acc: 0.8481
43264/60000 [====================>.........] - ETA: 11s - loss: 0.6389 - acc: 0.8484
43392/60000 [====================>.........] - ETA: 11s - loss: 0.6373 - acc: 0.8487
43520/60000 [====================>.........] - ETA: 11s - loss: 0.6358 - acc: 0.8490
43648/60000 [====================>.........] - ETA: 11s - loss: 0.6344 - acc: 0.8493
43776/60000 [====================>.........] - ETA: 11s - loss: 0.6330 - acc: 0.8496
43904/60000 [====================>.........] - ETA: 11s - loss: 0.6317 - acc: 0.8498
44032/60000 [=====================>........] - ETA: 11s - loss: 0.6306 - acc: 0.8500
44160/60000 [=====================>........] - ETA: 11s - loss: 0.6291 - acc: 0.8504
44288/60000 [=====================>........] - ETA: 11s - loss: 0.6276 - acc: 0.8507
44416/60000 [=====================>........] - ETA: 11s - loss: 0.6260 - acc: 0.8510
44544/60000 [=====================>........] - ETA: 10s - loss: 0.6246 - acc: 0.8513
44672/60000 [=====================>........] - ETA: 10s - loss: 0.6232 - acc: 0.8516
44800/60000 [=====================>........] - ETA: 10s - loss: 0.6219 - acc: 0.8519
44928/60000 [=====================>........] - ETA: 10s - loss: 0.6209 - acc: 0.8522
45056/60000 [=====================>........] - ETA: 10s - loss: 0.6196 - acc: 0.8525
45184/60000 [=====================>........] - ETA: 10s - loss: 0.6185 - acc: 0.8527
45312/60000 [=====================>........] - ETA: 10s - loss: 0.6171 - acc: 0.8530
45440/60000 [=====================>........] - ETA: 10s - loss: 0.6157 - acc: 0.8533
45568/60000 [=====================>........] - ETA: 10s - loss: 0.6144 - acc: 0.8535
45696/60000 [=====================>........] - ETA: 10s - loss: 0.6132 - acc: 0.8538
45824/60000 [=====================>........] - ETA: 10s - loss: 0.6121 - acc: 0.8541
45952/60000 [=====================>........] - ETA: 9s - loss: 0.6112 - acc: 0.8543 
46080/60000 [======================>.......] - ETA: 9s - loss: 0.6100 - acc: 0.8546
46208/60000 [======================>.......] - ETA: 9s - loss: 0.6084 - acc: 0.8550
46336/60000 [======================>.......] - ETA: 9s - loss: 0.6071 - acc: 0.8552
46464/60000 [======================>.......] - ETA: 9s - loss: 0.6058 - acc: 0.8555
46592/60000 [======================>.......] - ETA: 9s - loss: 0.6047 - acc: 0.8557
46720/60000 [======================>.......] - ETA: 9s - loss: 0.6036 - acc: 0.8560
46848/60000 [======================>.......] - ETA: 9s - loss: 0.6024 - acc: 0.8563
46976/60000 [======================>.......] - ETA: 9s - loss: 0.6013 - acc: 0.8564
47104/60000 [======================>.......] - ETA: 9s - loss: 0.6001 - acc: 0.8567
47232/60000 [======================>.......] - ETA: 9s - loss: 0.5989 - acc: 0.8570
47360/60000 [======================>.......] - ETA: 8s - loss: 0.5976 - acc: 0.8573
47488/60000 [======================>.......] - ETA: 8s - loss: 0.5964 - acc: 0.8575
47616/60000 [======================>.......] - ETA: 8s - loss: 0.5953 - acc: 0.8578
47744/60000 [======================>.......] - ETA: 8s - loss: 0.5942 - acc: 0.8580
47872/60000 [======================>.......] - ETA: 8s - loss: 0.5931 - acc: 0.8582
48000/60000 [=======================>......] - ETA: 8s - loss: 0.5918 - acc: 0.8585
48128/60000 [=======================>......] - ETA: 8s - loss: 0.5908 - acc: 0.8587
48256/60000 [=======================>......] - ETA: 8s - loss: 0.5894 - acc: 0.8590
48384/60000 [=======================>......] - ETA: 8s - loss: 0.5883 - acc: 0.8593
48512/60000 [=======================>......] - ETA: 8s - loss: 0.5870 - acc: 0.8595
48640/60000 [=======================>......] - ETA: 8s - loss: 0.5856 - acc: 0.8598
48768/60000 [=======================>......] - ETA: 7s - loss: 0.5843 - acc: 0.8601
48896/60000 [=======================>......] - ETA: 7s - loss: 0.5832 - acc: 0.8603
49024/60000 [=======================>......] - ETA: 7s - loss: 0.5822 - acc: 0.8606
49152/60000 [=======================>......] - ETA: 7s - loss: 0.5809 - acc: 0.8609
49280/60000 [=======================>......] - ETA: 7s - loss: 0.5798 - acc: 0.8611
49408/60000 [=======================>......] - ETA: 7s - loss: 0.5787 - acc: 0.8614
49536/60000 [=======================>......] - ETA: 7s - loss: 0.5776 - acc: 0.8616
49664/60000 [=======================>......] - ETA: 7s - loss: 0.5766 - acc: 0.8618
49792/60000 [=======================>......] - ETA: 7s - loss: 0.5755 - acc: 0.8621
49920/60000 [=======================>......] - ETA: 7s - loss: 0.5744 - acc: 0.8623
50048/60000 [========================>.....] - ETA: 7s - loss: 0.5733 - acc: 0.8626
50176/60000 [========================>.....] - ETA: 6s - loss: 0.5720 - acc: 0.8629
50304/60000 [========================>.....] - ETA: 6s - loss: 0.5709 - acc: 0.8631
50432/60000 [========================>.....] - ETA: 6s - loss: 0.5700 - acc: 0.8633
50560/60000 [========================>.....] - ETA: 6s - loss: 0.5690 - acc: 0.8635
50688/60000 [========================>.....] - ETA: 6s - loss: 0.5677 - acc: 0.8638
50816/60000 [========================>.....] - ETA: 6s - loss: 0.5664 - acc: 0.8641
50944/60000 [========================>.....] - ETA: 6s - loss: 0.5654 - acc: 0.8644
51072/60000 [========================>.....] - ETA: 6s - loss: 0.5644 - acc: 0.8646
51200/60000 [========================>.....] - ETA: 6s - loss: 0.5635 - acc: 0.8648
51328/60000 [========================>.....] - ETA: 6s - loss: 0.5630 - acc: 0.8649
51456/60000 [========================>.....] - ETA: 6s - loss: 0.5618 - acc: 0.8651
51584/60000 [========================>.....] - ETA: 5s - loss: 0.5606 - acc: 0.8654
51712/60000 [========================>.....] - ETA: 5s - loss: 0.5596 - acc: 0.8656
51840/60000 [========================>.....] - ETA: 5s - loss: 0.5585 - acc: 0.8659
51968/60000 [========================>.....] - ETA: 5s - loss: 0.5576 - acc: 0.8660
52096/60000 [=========================>....] - ETA: 5s - loss: 0.5564 - acc: 0.8663
52224/60000 [=========================>....] - ETA: 5s - loss: 0.5554 - acc: 0.8665
52352/60000 [=========================>....] - ETA: 5s - loss: 0.5544 - acc: 0.8667
52480/60000 [=========================>....] - ETA: 5s - loss: 0.5534 - acc: 0.8669
52608/60000 [=========================>....] - ETA: 5s - loss: 0.5524 - acc: 0.8671
52736/60000 [=========================>....] - ETA: 5s - loss: 0.5515 - acc: 0.8673
52864/60000 [=========================>....] - ETA: 5s - loss: 0.5503 - acc: 0.8675
52992/60000 [=========================>....] - ETA: 4s - loss: 0.5492 - acc: 0.8678
53120/60000 [=========================>....] - ETA: 4s - loss: 0.5481 - acc: 0.8680
53248/60000 [=========================>....] - ETA: 4s - loss: 0.5471 - acc: 0.8683
53376/60000 [=========================>....] - ETA: 4s - loss: 0.5461 - acc: 0.8685
53504/60000 [=========================>....] - ETA: 4s - loss: 0.5449 - acc: 0.8688
53632/60000 [=========================>....] - ETA: 4s - loss: 0.5441 - acc: 0.8689
53760/60000 [=========================>....] - ETA: 4s - loss: 0.5431 - acc: 0.8691
53888/60000 [=========================>....] - ETA: 4s - loss: 0.5419 - acc: 0.8694
54016/60000 [==========================>...] - ETA: 4s - loss: 0.5411 - acc: 0.8696
54144/60000 [==========================>...] - ETA: 4s - loss: 0.5404 - acc: 0.8697
54272/60000 [==========================>...] - ETA: 4s - loss: 0.5396 - acc: 0.8699
54400/60000 [==========================>...] - ETA: 3s - loss: 0.5389 - acc: 0.8700
54528/60000 [==========================>...] - ETA: 3s - loss: 0.5381 - acc: 0.8702
54656/60000 [==========================>...] - ETA: 3s - loss: 0.5372 - acc: 0.8704
54784/60000 [==========================>...] - ETA: 3s - loss: 0.5362 - acc: 0.8706
54912/60000 [==========================>...] - ETA: 3s - loss: 0.5351 - acc: 0.8708
55040/60000 [==========================>...] - ETA: 3s - loss: 0.5343 - acc: 0.8711
55168/60000 [==========================>...] - ETA: 3s - loss: 0.5337 - acc: 0.8712
55296/60000 [==========================>...] - ETA: 3s - loss: 0.5328 - acc: 0.8714
55424/60000 [==========================>...] - ETA: 3s - loss: 0.5318 - acc: 0.8716
55552/60000 [==========================>...] - ETA: 3s - loss: 0.5307 - acc: 0.8718
55680/60000 [==========================>...] - ETA: 3s - loss: 0.5298 - acc: 0.8720
55808/60000 [==========================>...] - ETA: 2s - loss: 0.5289 - acc: 0.8722
55936/60000 [==========================>...] - ETA: 2s - loss: 0.5279 - acc: 0.8724
56064/60000 [===========================>..] - ETA: 2s - loss: 0.5271 - acc: 0.8726
56192/60000 [===========================>..] - ETA: 2s - loss: 0.5260 - acc: 0.8729
56320/60000 [===========================>..] - ETA: 2s - loss: 0.5251 - acc: 0.8731
56448/60000 [===========================>..] - ETA: 2s - loss: 0.5244 - acc: 0.8732
56576/60000 [===========================>..] - ETA: 2s - loss: 0.5235 - acc: 0.8734
56704/60000 [===========================>..] - ETA: 2s - loss: 0.5225 - acc: 0.8737
56832/60000 [===========================>..] - ETA: 2s - loss: 0.5214 - acc: 0.8739
56960/60000 [===========================>..] - ETA: 2s - loss: 0.5204 - acc: 0.8742
57088/60000 [===========================>..] - ETA: 2s - loss: 0.5193 - acc: 0.8744
57216/60000 [===========================>..] - ETA: 1s - loss: 0.5186 - acc: 0.8746
57344/60000 [===========================>..] - ETA: 1s - loss: 0.5178 - acc: 0.8747
57472/60000 [===========================>..] - ETA: 1s - loss: 0.5172 - acc: 0.8748
57600/60000 [===========================>..] - ETA: 1s - loss: 0.5162 - acc: 0.8750
57728/60000 [===========================>..] - ETA: 1s - loss: 0.5151 - acc: 0.8752
57856/60000 [===========================>..] - ETA: 1s - loss: 0.5144 - acc: 0.8754
57984/60000 [===========================>..] - ETA: 1s - loss: 0.5134 - acc: 0.8756
58112/60000 [============================>.] - ETA: 1s - loss: 0.5125 - acc: 0.8758
58240/60000 [============================>.] - ETA: 1s - loss: 0.5116 - acc: 0.8760
58368/60000 [============================>.] - ETA: 1s - loss: 0.5108 - acc: 0.8761
58496/60000 [============================>.] - ETA: 1s - loss: 0.5102 - acc: 0.8763
58624/60000 [============================>.] - ETA: 0s - loss: 0.5092 - acc: 0.8765
58752/60000 [============================>.] - ETA: 0s - loss: 0.5086 - acc: 0.8766
58880/60000 [============================>.] - ETA: 0s - loss: 0.5079 - acc: 0.8768
59008/60000 [============================>.] - ETA: 0s - loss: 0.5071 - acc: 0.8769
59136/60000 [============================>.] - ETA: 0s - loss: 0.5063 - acc: 0.8771
59264/60000 [============================>.] - ETA: 0s - loss: 0.5054 - acc: 0.8773
59392/60000 [============================>.] - ETA: 0s - loss: 0.5044 - acc: 0.8775
59520/60000 [============================>.] - ETA: 0s - loss: 0.5035 - acc: 0.8778
59648/60000 [============================>.] - ETA: 0s - loss: 0.5025 - acc: 0.8780
59776/60000 [============================>.] - ETA: 0s - loss: 0.5017 - acc: 0.8782
59904/60000 [============================>.] - ETA: 0s - loss: 0.5010 - acc: 0.8783
60000/60000 [==============================] - 46s 767us/step - loss: 0.5005 - acc: 0.8784 - val_loss: 0.1180 - val_acc: 0.9608
Epoch 2/12

  128/60000 [..............................] - ETA: 43s - loss: 0.1245 - acc: 0.9609
  256/60000 [..............................] - ETA: 43s - loss: 0.1551 - acc: 0.9492
  384/60000 [..............................] - ETA: 46s - loss: 0.1367 - acc: 0.9531
  512/60000 [..............................] - ETA: 45s - loss: 0.1619 - acc: 0.9492
  640/60000 [..............................] - ETA: 45s - loss: 0.1387 - acc: 0.9578
  768/60000 [..............................] - ETA: 45s - loss: 0.1420 - acc: 0.9583
  896/60000 [..............................] - ETA: 44s - loss: 0.1396 - acc: 0.9587
 ……
 59264/60000 [============================>.] - ETA: 0s - loss: 0.0341 - acc: 0.9894
59392/60000 [============================>.] - ETA: 0s - loss: 0.0341 - acc: 0.9894
59520/60000 [============================>.] - ETA: 0s - loss: 0.0341 - acc: 0.9894
59648/60000 [============================>.] - ETA: 0s - loss: 0.0340 - acc: 0.9894
59776/60000 [============================>.] - ETA: 0s - loss: 0.0341 - acc: 0.9894
59904/60000 [============================>.] - ETA: 0s - loss: 0.0341 - acc: 0.9894
60000/60000 [==============================] - 50s 837us/step - loss: 0.0340 - acc: 0.9894 - val_loss: 0.0605 - val_acc: 0.9837

Process finished with exit code 0

可以看到，该模型在训练集上的准确率为98.94%，在测试集上的准确率为98.37%。

你可能感兴趣的:(keras实现卷积神经网络mnist手写数据集识别)

python 读excel每行替换_Python脚本操作Excel实现批量替换功能 weixin_39646695 python 读excel每行替换
Python脚本操作Excel实现批量替换功能大家好，给大家分享下如何使用Python脚本操作Excel实现批量替换。使用的工具Openpyxl，一个处理excel的python库，处理excel，其实针对的就是WorkBook，Sheet，Cell这三个最根本的元素~明确需求原始excel如下我们的目标是把下面excel工作表的sheet1表页A列的内容“替换我吧”批量替换为B列的“我用来替换的
移动端城市区县二级联动选择功能实现包 good2know
本文还有配套的精品资源，点击获取简介：本项目是一套为移动端设计的jQuery实现方案，用于简化用户在选择城市和区县时的流程。它包括所有必需文件：HTML、JavaScript、CSS及图片资源。通过动态更新下拉菜单选项，实现城市到区县的联动效果，支持数据异步加载。开发者可以轻松集成此功能到移动网站或应用，并可基于需求进行扩展和优化。1.jQuery移动端解决方案概述jQuery技术简介jQuery
9、汇编语言编程入门：从环境搭建到简单程序实现神经网络酱汇编语言 MEPIS GNU工具链
汇编语言编程入门：从环境搭建到简单程序实现1.数据存储介质问题解决在处理数据存储时，若要使用MEPIS系统，需确保有其可访问的存储介质。目前，MEPIS无法向采用NTFS格式（常用于Windows2000和XP工作站）的硬盘写入数据。不过，若硬盘采用FAT32格式，MEPIS就能进行写入操作。此外，MEPIS还能将文件写入软盘和大多数USB闪存驱动器。若工作站连接到局域网，还可通过FTP协议或挂载
IK分词初心myp
实现简单的分词功能，智能化分词添加依赖配置：4.10.4org.apache.lucenelucene-core${lucene.version}org.apache.lucenelucene-analyzers-common${lucene.version}org.apache.lucenelucene-queryparser${lucene.version}org.apache.lucenel
深入解析JVM工作原理：从字节码到机器指令的全过程
一、JVM概述Java虚拟机(JVM)是Java平台的核心组件，它实现了Java"一次编写，到处运行"的理念。JVM是一个抽象的计算机器，它有自己的指令集和运行时内存管理机制。JVM的主要职责：加载：读取.class文件并验证其正确性存储：管理内存分配和垃圾回收执行：解释或编译字节码为机器指令安全：提供沙箱环境限制恶意代码二、JVM架构详解JVM由三个主要子系统组成：1.类加载子系统类加载过程分为
Spring进阶 - SpringMVC实现原理之DispatcherServlet处理请求的过程倾听铃的声后端 spring java mvc 开发语言分布式
前文我们有了IOC的源码基础以及SpringMVC的基础，我们便可以进一步深入理解SpringMVC主要实现原理，包含DispatcherServlet的初始化过程和DispatcherServlet处理请求的过程的源码解析。本文是第二篇：DispatcherServlet处理请求的过程的源码解析。@pdaiSpring进阶-SpringMVC实现原理之DispatcherServlet处理请求的
JVM 内存模型深度解析：原子性、可见性与有序性的实现练习时长两年半的程序员小胡 JVM 深度剖析：从面试考点到生产实践 jvm java 内存模型
在了解了JVM的基础架构和类加载机制后，我们需要进一步探索Java程序在多线程环境下的内存交互规则。JVM内存模型（JavaMemoryModel，JMM）定义了线程和主内存之间的抽象关系，它通过规范共享变量的访问方式，解决了多线程并发时的数据一致性问题。本文将从内存模型的核心目标出发，详解原子性、可见性、有序性的实现机制，以及volatile、synchronized等关键字在其中的作用。一、J
Flowable 高级扩展：自定义元素与性能优化实战练习时长两年半的程序员小胡 Flowable 流程引擎实战指南流程图 flowable BPMN 流程引擎 java
在前五篇文章中，我们从基础概念、流程设计、API实战、SpringBoot集成，到外部系统协同，逐步构建了Flowable的应用体系。但企业级复杂场景中，原生功能往往难以满足定制化需求——比如需要特殊的审批规则网关、与决策引擎联动实现动态路由，或是在高并发场景下优化流程引擎性能。本文将聚焦Flowable的高级扩展能力，详解如何自定义流程元素、集成规则引擎，并掌握大型系统中的性能调优策略。一、自定
Java | 多线程经典问题 - 售票 Ada54
一、售票需求1）同一个票池2）多个窗口卖票，不能出售同一张票二、售票问题代码实现（线程与进程小总结，请戳：Java|线程和进程，创建线程）step1：定义SaleWindow类实现Runnable接口，覆盖run方法step2：实例化SaleWindow对象，创建Thread对象，将SaleWindow作为参数传给Thread类的构造函数，然后通过Thread.start()方法启动线程step3
企业级区块链平台Hyperchain核心原理剖析 boyedu 区块链区块链企业级区块链平台 Hyperchain
Hyperchain作为国产自主可控的企业级联盟区块链平台，其核心原理围绕高性能共识、隐私保护、智能合约引擎及可扩展架构展开，通过多模块协同实现企业级区块链网络的高效部署与安全运行。以下从核心架构、关键技术、性能优化、安全机制、应用场景五个维度展开剖析：一、核心架构：分层解耦与模块化设计Hyperchain采用分层架构，将区块链功能解耦为独立模块，支持灵活组合与扩展：P2P网络层由验证节点（VP）
在线人数统计业务设计（场景八股文）
业务问题在当经的网站中，在线人数的实时统计已经是一个必不可少的模块了，并且该统计功能最好能够按不同的时间间隔做的统计，现在需要你设计一个在线人数统计的模块，你应该怎么进行设计的呢？背景一个网校下会有多个学员。目前平台大概有十个，平台对应的网校大概五十几个，平均一个网校会有5w个用户，预计总人数为200w，最该学员的在线人数在10w左右。设计思路最开始的时候，想到的就是使用mysql直接实现，但是明
JAVA接口机结构解析秃狼 SpringBoot 八股文 Java java 学习
什么是接口机在Java项目中，接口机通常指用于与外部系统进行数据交互的中间层，负责处理请求和响应的转换、协议适配、数据格式转换等任务。接口机的结构我们的接口机的结构分为两个大部分，外部接口机和内部接口机，在业务的调度上也是通过mq来实现的，只要的目的就是为了解耦合和做差异化。在接口机中主要的方法就是定时任务，消息的发送和消费，其他平台调用接口机只能提供外部接口机的方法进行调用，外部接口机可以提供消
Aop +反射实现方法版本动态切换
需求分析在做技术选型的时候一直存在着两个声音，mongo作为数据库比较mysql好，mysql做为该数据比mongo好。当然不同数据库都有有着自己的优势，我们在做技术选型的时候无非就是做到对数据库的扬长避短。mysql最大的优势就是支持事务，事务的五大特性保证的业务可靠性，随之而来的就是事务会产生的问题：脏读、幻读、不可重复度，当然我们也会使用不同的隔离级别来解决。（最典型的业务问题：银行存取钱）
通义万相2.2：开启高清视频生成新纪元 Liudef06小白特殊专栏 AIGC 人工智能人工智能通义万相2.2 图生视频
通义万相2.2：开启高清视频生成新纪元2025年7月28日，中国AI领域迎来里程碑时刻——通义万相团队正式开源其革命性视频生成模型Wan2.2的核心权重，这标志着开源社区首次获得支持720P高清视频生成的先进模型架构。一、架构革新：混合专家系统1.1MoE视频扩散架构通义万相2.2首次将混合专家（MoE）架构引入视频扩散模型，通过双专家系统实现计算效率与模型容量的平衡：classMoEVideoD
氧惠官方邀请码333777，氧惠邀请码怎么获得？氧惠邀请码有什么套路？知行导师
问：氧惠邀请码怎么获得？答：氧惠官方邀请码333777返点高佣金高真的高。问：氧惠邀请码有什么套路？答：氧惠官方邀请码333777返点高佣金高真的高。氧惠APP汇聚各大主流电商和生活服务平台优惠，展示全网全品类商品，满足网购爱好者对品质好货与极致性价比的追求，并同时享受大平台购物权益保障。满足用户日常吃喝玩乐衣食住行的聚合APP，独特的商业模式，响应国家号召，为实现全民共富而努力奋斗。氧惠邀请码3
最新阿里四面面试真题46道：面试技巧+核心问题+面试心得风平浪静如码
前言做技术的有一种资历，叫做通过了阿里的面试。这些阿里Java相关问题，都是之前通过不断优秀人才的铺垫总结的，先自己弄懂了再去阿里面试，不然就是去丢脸，被虐。希望对大家帮助，祝面试成功，有个更好的职业规划。一，阿里常见技术面1、微信红包怎么实现。2、海量数据分析。3、测试职位问的线程安全和非线程安全。4、HTTP2.0、thrift。5、面试电话沟通可能先让自我介绍。6、分布式事务一致性。7、ni
2025年SDK游戏盾终极解析：重新定义手游安全的“隐形护甲” 上海云盾商务经理杨杨游戏安全
副标题：从客户端加密到AI反外挂，拆解全链路防护如何重塑游戏攻防天平引言：当传统高防在手游战场“失效”2025年全球手游市场规模突破$2000亿，黑客单次攻击成本却降至$30——某SLG游戏因协议层CC攻击单日流失37%玩家，某开放世界游戏遭低频DDoS瘫痪6小时损失千万。传统高防IP的致命短板暴露无遗：无法识别伪造客户端流量、难防协议篡改、误杀率超15%。而集成于游戏终端的SDK游戏盾，正以“源
LVS+Keepalived实现高可用和负载均衡 2401_84412895 程序员 lvs 负载均衡运维
2、开启网卡子接口配置VIP[root@a~]#cd/etc/sysconfig/network-scripts/[root@anetwork-scripts]#cp-aifcfg-ens32ifcfg-ens32:0[root@anetwork-scripts]#catifcfg-ens32:0BOOTPROTO=staticDEVICE=ens32:0ONBOOT=yesIPADDR=10.1
深入理解汇编语言子程序设计与系统调用网安spinage 汇编语言开发语言汇编算法
本文将全面解析汇编语言中子程序设计的核心技术以及系统调用的实现方法，涵盖参数传递的多种方式、堆栈管理、API调用等关键知识点，并提供实际案例演示。一、子程序设计：参数传递的艺术1.寄存器传参：高效简洁.386.modelflat,stdcalloptioncasemap:none.dataxdd5;定义变量ydd6sumdd?.code;函数定义：addxy1addxy1procpushebpmo
大胆的宣传自己工匠良辰
#大胆的宣传自己原创：辉哥奇谭辉哥奇谭今天有朋友问：辉哥，发现你最近很多次宣传「知识星球」…我回答：对我自己用心做的东西有信心。我的观点是：我们每个人要把自己当成一件产品，精心的打磨，大胆的推销。如果我们一辈子都不敢面对自己这件产品，也不好意思去推销，怎样才能实现自己内心的梦想？怎样才能获得自由？怎样才能过上自己想过的生活？人生在世也许就是七八十年光景，我们最终都会败在「时光」脚下。每个人来到这世
京东家电年销售额是去年的1300%，主要来自于他.... Shanshan小课堂
经过大半个月角逐纠缠，时间终于来到6月18日，618全球年中购物节迎来最高潮。作为国内最大的家电零售平台，京东家电从18日0点开始，便开启了飞速狂奔的模式，仅8分钟销售额就突破20亿元!展现出强劲的增长势头与家电主场的王者霸气的同时，也让各家电品牌实现了爆发式增长，美的、海尔、格力、奥克斯均在3分钟内突破1亿元大关。在今年的618中，除了消费者已经熟悉的网购形式外，线上线下联动的融合模式、社交电商
编程算法：技术创新的引擎与业务增长的核心驱动力
在数字经济时代，算法已成为推动技术创新与业务增长的隐形引擎。从存内计算突破冯·诺依曼瓶颈，到动态规划优化万亿级金融交易，编程算法正在重塑产业竞争格局。一、存内计算：突破冯·诺依曼瓶颈的算法革命1.1存内计算的基本原理传统计算架构中90%的能耗消耗在数据搬运上。存内计算（Processing-in-Memory）通过直接在存储单元执行计算，实现能效10-100倍提升：#传统计算vs存内计算能耗模型i
图论算法经典题目解析：DFS、BFS与拓扑排序实战周童學数据结构与算法深度优先算法图论
图论算法经典题目解析：DFS、BFS与拓扑排序实战图论问题是算法面试中的高频考点，本博客将通过四道LeetCode经典题目（均来自"Top100Liked"题库），深入讲解图论的核心算法思想和实现技巧。涵盖DFS、BFS、拓扑排序和前缀树等知识点，每道题配有Java实现和易错点分析。1.岛屿数量(DFS遍历)问题描述给定一个由'1'(陆地)和'0'(水)组成的二维网格，计算岛屿的数量。岛屿由水平或
基于redis的Zset实现作者的轻量级排名周童學 Java redis 数据库缓存
基于redis的Zset实现轻量级作者排名系统在今天的技术架构中，Redis是一种广泛使用的内存数据存储系统，尤其在需要高效检索和排序的场景中表现优异。在本篇博客中，我们将深入探讨如何使用Redis的有序集合（ZSet）构建一个高效的笔记排行榜系统，并提供相关代码示例和详细的解析。1.功能背景与需求假设我们有一个笔记分享平台，用户可以发布各种笔记，系统需要根据用户发布的笔记数量来生成一个实时更新的
【项目实战】容错机制与故障恢复：保障系统连续性的核心体系本本本添哥 004 -研效与DevOps运维工具链 002 -进阶开发能力分布式
在分布式系统中，硬件故障、网络波动、软件异常等问题难以避免。容错机制与故障恢复的核心目标是：通过主动检测故障、自动隔离风险、快速转移负载、重建数据一致性，最大限度减少故障对业务的影响，保障系统“持续可用”与“数据不丢失”。以下从核心机制、实现方式、典型案例等维度展开说明。一、故障检测：及时发现异常节点故障检测是容错的第一步，需通过多维度手段实时感知系统组件状态，确保故障被快速识别。1.健康检查与心
Java并发核心：线程池使用技巧与最佳实践！ | 多线程篇(五) bug菌¹ Java实战(进阶版)java Java零基础入门 Java并发线程池多线程篇
本文收录于「Java进阶实战」专栏，专业攻坚指数级提升，希望能够助你一臂之力，帮你早日登顶实现财富自由；同时，欢迎大家关注&&收藏&&订阅！持续更新中，up！up！up！！环境说明：Windows10+IntelliJIDEA2021.3.2+Jdk1.8本文目录前言摘要正文何为线程池？为什么需要线程池？线程池的好处线程池使用场景如何创建线程池？线程池的常见配置源码解析案例分享案例代码演示案例运行
Java 队列 tryxr java 开发语言队列
队列一般用什么哪种结构实现队列的特性数据入队列时一定是从尾部插入吗数据出队列时一定是从头部删除吗队列的基本运算有什么队列支持随机访问吗队列的英文表示什么是队列队列从哪进、从哪出队列的进出顺序队列是用哪种结构实现的Queue和Deque有什么区别Queue接口的方法Queue中的add与offer的区别offer、poll、peek的模拟实现如何利用链表实现队列如何利用顺序表实现队列什么叫做双端队列
Effective C++ 条款10：令operator=返回一个reference to *this 君鼎 C++c++
EffectiveC++条款10：令operator=返回一个referenceto*this核心思想：赋值操作符（operator=）应始终返回当前对象的引用（*this），以实现连锁赋值并保持与内置类型一致的语义。⚠️1.问题场景：违反连锁赋值语义classWidget{public:voidoperator=(constWidget&rhs){//错误：返回voidvalue=rhs.val
打造自己的梦想生态系统轻风style
今天听了第5周5.1的梦想系统和随堂练习：梦想仓库与八大关注表。参照老师给出的例子，列出了八大关注对应的自己的梦想。有些写的时候内心都在怀疑，但因为老师有说到，要没有分别心的去列出，不管是近的，远的，小的，大的，自己觉得可以实现的，或者觉得根本不可能实现的，都统统的列出来。就像音频中提到的，林语堂说过的话，梦想无论怎样模糊，总潜伏在我们心底，使我们的心境永远得不到宁静，直到这些梦想成为事实才止；像
第二十二天（数据结构，无头节点的单项链表）肉夹馍不加青椒 c语言数据结构
线性表：一个线性表里面可以是任意的数据元素，但是同一个线性表里面数据应该是同类型的1存在一个/唯一被称为第一个节点的节点2存在一个/唯一被称为最后一个节点的节点3除了第一个以外，每一个元素都有一个前驱节点4除了最后一个，每一个元素都有一个后继节点满足以上性质，这个表就被称为线性表数组就是一个线性表想实现线性表的保存，我们需要考虑下面的事情1元素要保存2元素与元素之间的序偶关系谁是前面的谁是后面的我
关于旗正规则引擎规则中的上传和下载问题何必如此文件下载压缩 jsp 文件上传
文件的上传下载都是数据流的输入输出，大致流程都是一样的。一、文件打包下载 1.文件写入压缩包 string mainPath="D:\upload\"; 下载路径 string tmpfileName=jar.zip; &n
【Spark九十九】Spark Streaming的batch interval时间内的数据流转源码分析 bit1129 Stream
以如下代码为例（SocketInputDStream）： Spark Streaming从Socket读取数据的代码是在SocketReceiver的receive方法中，撇开异常情况不谈(Receiver有重连机制，restart方法，默认情况下在Receiver挂了之后，间隔两秒钟重新建立Socket连接)，读取到的数据通过调用store(textRead)方法进行存储。数据
spark master web ui 端口8080被占用解决方法 daizj 8080 端口占用 spark master web ui
spark master web ui 默认端口为8080，当系统有其它程序也在使用该接口时，启动master时也不会报错，spark自己会改用其它端口，自动端口号加1，但为了可以控制到指定的端口，我们可以自行设置，修改方法： 1、cd SPARK_HOME/sbin 2、vi start-master.sh 3、定位到下面部分
oracle_执行计划_谓词信息和数据获取周凡杨 oracle 执行计划
oracle_执行计划_谓词信息和数据获取(上) 一：简要说明在查看执行计划的信息中，经常会看到两个谓词filter和access，它们的区别是什么，理解了这两个词对我们解读Oracle的执行计划信息会有所帮助。简单说，执行计划如果显示是access，就表示这个谓词条件的值将会影响数据的访问路径（表还是索引），而filter表示谓词条件的值并不会影响数据访问路径，只起到
spring中datasource配置 g21121 dataSource
datasource配置有很多种，我介绍的一种是采用c3p0的，它的百科地址是： http://baike.baidu.com/view/920062.htm  <bean name="propertiesConfig" class="org.springframework.b
web报表工具FineReport使用中遇到的常见报错及解决办法（三）老A不折腾 finereport FAQ 报表软件
这里写点抛砖引玉，希望大家能把自己整理的问题及解决方法晾出来，Mark一下，利人利己。出现问题先搜一下文档上有没有，再看看度娘有没有，再看看论坛有没有。有报错要看日志。下面简单罗列下常见的问题，大多文档上都有提到的。 1、repeated column width is largerthan paper width：这个看这段话应该是很好理解的。比如做的模板页面宽度只能放
mysql 用户管理墙头上一根草 linux mysql user
1.新建用户 //登录MYSQL@>mysql -u root -p@>密码//创建用户mysql> insert into mysql.user(Host,User,Password) values(‘localhost’,'jeecn’,password(‘jeecn’));//刷新系统权限表mysql>flush privileges;这样就创建了一个名为：
关于使用Spring导致c3p0数据库死锁问题 aijuans spring Spring 入门 Spring 实例 Spring3 Spring 教程
这个问题我实在是为整个 springsource 的员工蒙羞如果大家使用 spring 控制事务，使用 Open Session In View 模式， com.mchange.v2.resourcepool.TimeoutException: A client timed out while waiting to acquire a resource from com.mchange.
百度词库联想 annan211 百度
<!DOCTYPE html> <html> <head> <meta http-equiv="Content-Type" content="text/html; charset=UTF-8"> <title>RunJS</title&g
int数据与byte之间的相互转换实现代码百合不是茶位移 int转byte byte转int 基本数据类型的实现
在BMP文件和文件压缩时需要用到的int与byte转换,现将理解的贴出来; 主要是要理解;位移等概念 http://baihe747.iteye.com/blog/2078029 int转byte; byte转int; /** * 字节转成int,int转成字节 * @author Administrator *
简单模拟实现数据库连接池 bijian1013 java thread java多线程简单模拟实现数据库连接池
简单模拟实现数据库连接池实例1： package com.bijian.thread; public class DB { //private static final int MAX_COUNT = 10; private static final DB instance = new DB(); private int count = 0; private i
一种基于Weblogic容器的鉴权设计 bijian1013 java weblogic
服务器对请求的鉴权可以在请求头中加Authorization之类的key，将用户名、密码保存到此key对应的value中，当然对于用户名、密码这种高机密的信息，应该对其进行加砂加密等，最简单的方法如下： String vuser_id = "weblogic"; String vuse
【RPC框架Hessian二】Hessian 对象序列化和反序列化 bit1129 hessian
任何一个对象从一个JVM传输到另一个JVM，都要经过序列化为二进制数据(或者字符串等其他格式，比如JSON)，然后在反序列化为Java对象，这最后都是通过二进制的数据在不同的JVM之间传输(一般是通过Socket和二进制的数据传输)，本文定义一个比较符合工作中。 1. 定义三个POJO Person类 package com.tom.hes
【Hadoop十四】Hadoop提供的脚本的功能 bit1129 hadoop
1. hadoop-daemon.sh 1.1 启动HDFS ./hadoop-daemon.sh start namenode ./hadoop-daemon.sh start datanode 通过这种逐步启动的方式，比start-all.sh方式少了一个SecondaryNameNode进程，这不影响Hadoop的使用，其实在 Hadoop2.0中，SecondaryNa
中国互联网走在“灰度”上 ronin47 管理灰度
中国互联网走在“灰度”上（转）文/孕峰第一次听说灰度这个词，是任正非说新型管理者所需要的素质。第二次听说是来自马化腾。似乎其他人包括马云也用不同的语言说过类似的意思。灰度这个词所包含的意义和视野是广远的。要理解这个词，可能同样要用“灰度”的心态。灰度的反面，是规规矩矩，清清楚楚，泾渭分明，严谨条理，是决不妥协，不转弯，认死理。黑白分明不是灰度，像彩虹那样
java-51-输入一个矩阵，按照从外向里以顺时针的顺序依次打印出每一个数字。 bylijinnan java
public class PrintMatrixClockwisely { /** * Q51.输入一个矩阵，按照从外向里以顺时针的顺序依次打印出每一个数字。例如：如果输入如下矩阵： 1 2 3 4 5 6 7 8 9
mongoDB 用户管理开窍的石头 mongoDB用户管理
1:添加用户第一次设置用户需要进入admin数据库下设置超级用户（use admin） db.addUsr({user:'useName',pwd:'111111',roles:[readWrite,dbAdmin]}); 第一个参数用户的名字第二个参数
[游戏与生活]玩暗黑破坏神3的一些问题 comsci 生活
暗黑破坏神3是有史以来最让人激动的游戏。。。。但是有几个问题需要我们注意玩这个游戏的时间，每天不要超过一个小时，且每次玩游戏最好在白天结束游戏之后，最好在太阳下面来晒一下身上的暗黑气息，让自己恢复人的生气 &nb
java 二维数组如何存入数据库 cuiyadll java
using System; using System.Linq; using System.Text; using System.Windows.Forms; using System.Xml; using System.Xml.Serialization; using System.IO; namespace WindowsFormsApplication1 {
本地事务和全局事务Local Transaction and Global Transaction(JTA) darrenzhu java spring local global transaction
Configuring Spring and JTA without full Java EE http://spring.io/blog/2011/08/15/configuring-spring-and-jta-without-full-java-ee/ Spring doc -Transaction Management http://docs.spring.io/spri
Linux命令之alias - 设置命令的别名，让 Linux 命令更简练 dcj3sjt126com linux alias
用途说明设置命令的别名。在linux系统中如果命令太长又不符合用户的习惯，那么我们可以为它指定一个别名。虽然可以为命令建立“链接”解决长文件名的问题，但对于带命令行参数的命令，链接就无能为力了。而指定别名则可以解决此类所有问题【1】。常用别名来简化ssh登录【见示例三】，使长命令变短，使常用的长命令行变短，强制执行命令时询问等。常用参数格式：alias 格式：ali
yii2 restful web服务[格式响应] dcj3sjt126com PHP yii2
响应格式当处理一个 RESTful API 请求时，一个应用程序通常需要如下步骤来处理响应格式：确定可能影响响应格式的各种因素，例如媒介类型，语言，版本，等等。这个过程也被称为 content negotiation。资源对象转换为数组，如在 Resources 部分中所描述的。通过 [[yii\rest\Serializer]]
MongoDB索引调优（2）——[十] eksliang mongodb MongoDB索引优化
转载请出自出处：http://eksliang.iteye.com/blog/2178555 一、概述上一篇文档中也说明了，MongoDB的索引几乎与关系型数据库的索引一模一样，优化关系型数据库的技巧通用适合MongoDB，所有这里只讲MongoDB需要注意的地方二、索引内嵌文档可以在嵌套文档的键上建立索引，方式与正常
当滑动到顶部和底部时，实现Item的分离效果的ListView gundumw100 android
拉动ListView，Item之间的间距会变大，释放后恢复原样； package cn.tangdada.tangbang.widget; import android.annotation.TargetApi; import android.content.Context; import android.content.res.TypedArray; import andr
程序员用HTML5制作的爱心树表白动画 ini JavaScript jquery Web html5 css
体验效果：http://keleyi.com/keleyi/phtml/html5/31.htmHTML代码如下： <!DOCTYPE html> <html xmlns="http://www.w3.org/1999/xhtml"><head><meta charset="UTF-8" > <ti
预装windows 8 系统GPT模式的ThinkPad T440改装64位 windows 7旗舰版 kakajw ThinkPad 预装改装 windows 7 windows 8
该教程具有普遍参考性，特别适用于联想的机器，其他品牌机器的处理过程也大同小异。该教程是个人多次尝试和总结的结果，实用性强，推荐给需要的人！缘由小弟最近入手笔记本ThinkPad T440，但是特别不能习惯笔记本出厂预装的Windows 8系统，而且厂商自作聪明地预装了一堆没用的应用软件，消耗不少的系统资源（本本的内存为4G，系统启动完成时，物理内存占用比
Nginx学习笔记 mcj8089 nginx
一、安装nginx 1、在nginx官方网站下载一个包，下载地址是： http://nginx.org/download/nginx-1.4.2.tar.gz 2、WinSCP(ftp上传工
mongodb 聚合查询每天论坛链接点击次数 qiaolevip 每天进步一点点学习永无止境 mongodb 纵观千象
/* 18 */ { "_id" : ObjectId("5596414cbe4d73a327e50274"), "msgType" : "text", "sendTime" : ISODate("2015-07-03T08:01:16.000Z"
java术语（PO/POJO/VO/BO/DAO/DTO） Luob. DAO POJO DTO po VO BO
PO(persistant object) 持久对象在o/r 映射的时候出现的概念,如果没有o/r映射,就没有这个概念存在了.通常对应数据模型(数据库),本身还有部分业务逻辑的处理.可以看成是与数据库中的表相映射的java对象.最简单的PO就是对应数据库中某个表中的一条记录,多个记录可以用PO的集合.PO中应该不包含任何对数据库的操作. VO(value object) 值对象通
算法复杂度 Wuaner Algorithm
Time Complexity & Big-O： http://stackoverflow.com/questions/487258/plain-english-explanation-of-big-o http://bigocheatsheet.com/ http://www.sitepoint.com/time-complexity-algorithms/