接很久之前的一篇，今天主要考虑的问题是FC dense层后面如果有dropout层该怎么办？
模型如下：
Layer (type) Output Shape Param #
=================================================================
input_1 (InputLayer) [(None, 128, 129, 1)] 0
_________________________________________________________________
conv2d (Conv2D) (None, 128, 129, 16) 160
_________________________________________________________________
activation (Activation) (None, 128, 129, 16) 0
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 64, 64, 16) 0
_________________________________________________________________
dropout (Dropout) (None, 64, 64, 16) 0
_________________________________________________________________
conv2d_1 (Conv2D) (None, 64, 64, 32) 4640
_________________________________________________________________
activation_1 (Activation) (None, 64, 64, 32) 0
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 32, 32, 32) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 32, 32, 32) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 32, 32, 64) 18496
_________________________________________________________________
activation_2 (Activation) (None, 32, 32, 64) 0
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 16, 16, 64) 0
_________________________________________________________________
dropout_2 (Dropout) (None, 16, 16, 64) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 16, 16, 128) 73856
_________________________________________________________________
activation_3 (Activation) (None, 16, 16, 128) 0
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 8, 8, 128) 0
_________________________________________________________________
dropout_3 (Dropout) (None, 8, 8, 128) 0
_________________________________________________________________
conv2d_4 (Conv2D) (None, 8, 8, 256) 295168
_________________________________________________________________
activation_4 (Activation) (None, 8, 8, 256) 0
_________________________________________________________________
max_pooling2d_4 (MaxPooling2 (None, 4, 4, 256) 0
_________________________________________________________________
dropout_4 (Dropout) (None, 4, 4, 256) 0
_________________________________________________________________
flatten (Flatten) (None, 4096) 0
_________________________________________________________________
dropout_5 (Dropout) (None, 4096) 0
_________________________________________________________________
dense (Dense) (None, 512) 2097664
_________________________________________________________________
dropout_6 (Dropout) (None, 512) 0
_________________________________________________________________
dense_1 (Dense) (None, 10) 5130
=================================================================
Total params: 2,495,114
Trainable params: 2,495,114
Non-trainable params: 0dense层后面有一个dropout_6，是要这个层的输出作为高级特征呢还是dense层的呢？不妨用随机数试试有没有差别。
【小明哥事无巨细，事必躬亲，身体力行】
我哭了，卧槽，后来发现音频的长度不一样，batch是不一样的，卧槽，最后一个维度虽然是512，但它有batch，卧槽，特征融合也是个问题啊，不然这个根本没法做embedding啊，卧槽，这么大的维度不实用。
尽管经过验证结果是一样的，但我特征咋办啊？还是不能解决现实问题啊，这个博文的问题咋解决啊，人生好不艰难啊。
另外有相关问题可以加入QQ群讨论，不设微信群
QQ群：868373192
语音图像视频深度-学习群
