小编Der*_*aut的帖子

使用Keras和Tensorflow在我自己的数据集上从头开始训练卷积神经网络。

learning rate = 0.0001，排序5个类，不使用Dropout，检查数据集两次，未找到错误的标签

模型：

model = models.Sequential()
model.add(layers.Conv2D(16,(2,2),activation='relu',input_shape=(75,75,3)))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Conv2D(16,(2,2),activation='relu'))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Conv2D(32,(2,2),activation='relu'))
model.add(layers.MaxPooling2D((2,2)))
model.add(layers.Flatten())
model.add(layers.Dense(128,activation='relu'))
model.add(layers.Dense(5,activation='sigmoid'))

model.compile(optimizer=optimizers.adam(lr=0.0001),
             loss='categorical_crossentropy',
             metrics=['acc'])

history = model.fit_generator(train_generator,
                              steps_per_epoch=100,
                              epochs=50,
                              validation_data=val_generator,
                              validation_steps=25)

每当模型达到25-35个纪元（准确度为80-90％）时，就会发生这种情况：

Epoch 31/50
100/100 [==============================] - 3s 34ms/step - loss: 0.3524 - acc: 0.8558 - val_loss: 0.4151 - val_acc: 0.7992
Epoch 32/50
100/100 [==============================] - 3s 34ms/step - loss: 0.3393 - acc: 0.8700 - val_loss: 0.4384 - val_acc: 0.7951
Epoch 33/50
100/100 [==============================] - 3s 34ms/step - loss: 0.3321 - acc: …