我正在研究一种转移学习模型（基于Vgg19），具有以下架构。
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) (None, 224, 224, 3) 0
_________________________________________________________________
block1_conv1 (Conv2D) (None, 224, 224, 64) 1792
_________________________________________________________________
block1_conv2 (Conv2D) (None, 224, 224, 64) 36928
_________________________________________________________________
block1_pool (MaxPooling2D) (None, 112, 112, 64) 0
_________________________________________________________________
block2_conv1 (Conv2D) (None, 112, 112, 128) 73856
_________________________________________________________________
block2_conv2 (Conv2D) (None, 112, 112, 128) 147584
_________________________________________________________________
block2_pool (MaxPooling2D) (None, 56, 56, 128) 0
_________________________________________________________________
block3_conv1 (Conv2D) (None, 56, 56, 256) 295168
_________________________________________________________________
block3_conv2 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv3 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_conv4 (Conv2D) (None, 56, 56, 256) 590080
_________________________________________________________________
block3_pool (MaxPooling2D) (None, 28, 28, 256) 0
_________________________________________________________________
block4_conv1 (Conv2D) (None, 28, 28, 512) 1180160
_________________________________________________________________
block4_conv2 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv3 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_conv4 (Conv2D) (None, 28, 28, 512) 2359808
_________________________________________________________________
block4_pool (MaxPooling2D) (None, 14, 14, 512) 0
_________________________________________________________________
block5_conv1 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv2 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv3 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_conv4 (Conv2D) (None, 14, 14, 512) 2359808
_________________________________________________________________
block5_pool (MaxPooling2D) (None, 7, 7, 512) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 25088) 0
_________________________________________________________________
dense_1 (Dense) (None, 4096) 102764544
_________________________________________________________________
dropout_1 (Dropout) (None, 4096) 0
_________________________________________________________________
dense_2 (Dense) (None, 1024) 4195328
_________________________________________________________________
dropout_2 (Dropout) (None, 1024) 0
_________________________________________________________________
dense_3 (Dense) (None, 512) 524800
_________________________________________________________________
dense_4 (Dense) (None, 2) 1026
=================================================================
问题：训练错误结果（如下所示）反映了第一个时期的有意义值。一旦模型达到第二个时期，精度达到1.0 - 这是不可能的。当我将VGG切换到Inception时，当我添加正则化时，当我在不同的优化器（sgd，addagrad，rmsprop）之间切换时，或者当我在丢失之间切换时，这种行为不会改变（categorical_crossentropy，mean_squared_error）。
，所有测试/ val图像的分类结果为[[1。 0. 0 0. 0。]]意味着分类器总是倾向于支持class0。
Epoch 1/2
10/10 [==============================] - 109s 11s/step - loss: 1.7893 - acc: 0.9000
Epoch 00001: val_acc improved from -inf to 0.60000, saving model to vgg19_12.h5
Epoch 2/2
10/10 [==============================] - 122s 12s/step - loss: 0.9368 - acc: 1.0000
问：有什么想法可能是这个问题的根源？