Alpaca Model - Test exercise 2

Course Q&A Deep Learning Specialization Convolutional Neural Networks
1

Buenas, me pasa con el test de ALPACA_MODEL (Cell 16)

En el Summary del modelo obtengo la lista de Layers que no se corresponden con el test.

Model: “functional_1”

Layer (type) Output Shape Param

input_23 (InputLayer) [(None, 160, 160, 3)] 0

mobilenetv2_1.00_160 (Functi (None, 5, 5, 1280) 2257984

global_average_pooling2d_3 ( (None, 1280) 0

dropout_2 (Dropout) (None, 1280) 0

dense_2 (Dense) (None, 1) 1281

Total params: 2,259,265
Trainable params: 1,281
Non-trainable params: 2,257,984

Y el TEST busca

( [‘Sequential’, (None, 160, 160, 3), 0],
[‘TensorFlowOpLayer’, [(None, 160, 160, 3)], 0],
[‘TensorFlowOpLayer’, [(None, 160, 160, 3)], 0],)

alpaca_summary = [[‘InputLayer’, [(None, 160, 160, 3)], 0],
[‘Sequential’, (None, 160, 160, 3), 0],
[‘TensorFlowOpLayer’, [(None, 160, 160, 3)], 0],
[‘TensorFlowOpLayer’, [(None, 160, 160, 3)], 0],
[‘Functional’, (None, 5, 5, 1280), 2257984],
[‘GlobalAveragePooling2D’, (None, 1280), 0],
[‘Dropout’, (None, 1280), 0, 0.2],
[‘Dense’, (None, 1), 1281, ‘linear’]] #linear is the default activation

Las dimensiones me parecen correctas, pero no entiendo porque tendriamso esas capas si lo que agregamos es GlobalAveragePooling2D, Droopout y Dense

Me peuden ayuda a entender ?

Saludos.

2

Hello Juan,

The official language of this forum is English so I recommend that you write your questions/problems in this language so that more people can try to help you :slight_smile:

The layers that you do not understand are those that you need before the base_model line in the code of the alpaca_model and after the input. Remember that you need to add a data augmentation layer and the data preprocessing layers, otherwise the model is not complete.

Happy learning,

Rosa