小编Gur*_*aur的帖子

我是深度学习和 CNN 的新手。如果已经创建了 CNN，如屏幕截图所示，那么如何解释model.summary(). 我无法理解不同层的输出形状。

型号概要：

Model: "sequential_3"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
conv2d_14 (Conv2D)           (None, 29, 29, 32)        1568      
_________________________________________________________________
max_pooling2d_6 (MaxPooling2 (None, 14, 14, 32)        0         
_________________________________________________________________
conv2d_15 (Conv2D)           (None, 11, 11, 32)        16416     
_________________________________________________________________
max_pooling2d_7 (MaxPooling2 (None, 5, 5, 32)          0         
_________________________________________________________________
flatten_3 (Flatten)          (None, 800)               0         
_________________________________________________________________
dense_6 (Dense)              (None, 32)                25632     
_________________________________________________________________
dense_7 (Dense)              (None, 10)                330       
=================================================================
Total params: 43,946
Trainable params: 43,946
Non-trainable params: 0