设计思路

输出结果

Using TensorFlow backend.

F:\Program Files\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:526: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.

 _np_quint16 = np.dtype([("quint16", np.uint16, 1)])

F:\Program Files\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:527: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.

 _np_qint32 = np.dtype([("qint32", np.int32, 1)])

F:\Program Files\Python\Python36\lib\site-packages\tensorflow\python\framework\dtypes.py:532: FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecated; in a future version of numpy, it will be understood as (type, (1,)) / '(1,)type'.

 np_resource = np.dtype([("resource", np.ubyte, 1)])

None

2020-11-22 13:40:03.693339: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2

Found 17500 images belonging to 2 classes.

Found 7500 images belonging to 2 classes.

-------------显示网络结构--------------------

_________________________________________________________________

Layer (type)                 Output Shape              Param #  

=================================================================

input_2 (InputLayer)         (None, 4, 4, 512)         0        

_________________________________________________________________

flatten_1 (Flatten)          (None, 8192)              0        

_________________________________________________________________

dense_1 (Dense)              (None, 256)               2097408  

_________________________________________________________________

activation_1 (Activation)    (None, 256)               0        

_________________________________________________________________

dropout_1 (Dropout)          (None, 256)               0        

_________________________________________________________________

dense_2 (Dense)              (None, 1)                 257      

_________________________________________________________________

activation_2 (Activation)    (None, 1)                 0        

=================================================================

Total params: 2,097,665

Trainable params: 2,097,665

Non-trainable params: 0

_________________________________________________________________

None

 

1488/1488 4s 2ms/step - loss: 0.0139 - acc: 0.9966 - val_loss: 1.0130 - val_acc: 0.8762

2000/2000 6s 3ms/step - loss: 0.0122 - acc: 0.9950 - val_loss: 0.7943 - val_acc: 0.9125

4000/4000 10s 2ms/step - loss: 0.0216 - acc: 0.9945 - val_loss: 0.9137 - val_acc: 0.8812

6000/6000 15s 2ms/step - loss: 0.0262 - acc: 0.9933 - val_loss: 0.6805 - val_acc: 0.8988

6992/6992 20s 3ms/step - loss: 0.0395 - acc: 0.9894 - val_loss: 0.6387 - val_acc: 0.8975

99980/99980 237s 2ms/step - loss: 0.0598 - acc: 0.9922 - val_loss: 1.2305 - val_acc: 0.9100