Model: "sequential_30"
_________________________________________________________________
Layer (type)                 Output Shape              Param #
=================================================================
conv2d_39 (Conv2D)           (None, 32, 32, 16)        1216
_________________________________________________________________
inverted_residual_144 (Inver (None, 32, 32, 16)        4768
_________________________________________________________________
inverted_residual_145 (Inver (None, 32, 32, 16)        4768
_________________________________________________________________
average_pooling2d_2 (Average (None, 16, 16, 16)        0
_________________________________________________________________
inverted_residual_146 (Inver (None, 16, 16, 32)        6368
_________________________________________________________________
inverted_residual_147 (Inver (None, 16, 16, 32)        15680
_________________________________________________________________
average_pooling2d_3 (Average (None, 8, 8, 32)          0
_________________________________________________________________
inverted_residual_148 (Inver (None, 8, 8, 64)          21952
_________________________________________________________________
inverted_residual_149 (Inver (None, 8, 8, 64)          55936
_________________________________________________________________
global_average_pooling2d_10  (None, 64)                0
_________________________________________________________________
dense_24 (Dense)             (None, 100)               6500
=================================================================
Total params: 117,188
Trainable params: 112,516
Non-trainable params: 4,672
_________________________________________________________________