1

So, I have to work with Vgg16 in my semester group project, and was following this to do transfer learning.

I don't understand CNN much, but am learning currently.

The very first problem was that Vgg16 has 16 layers, whereas the base_model.summary() had 26 when initialised with VGGFace(include_top=True and 19 when VGGFace(include_top=False. Looks like the 16 layers are those with weight.

Now, tutorial uses include_top=False and did

x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dense(1024, activation='relu')(x)
x = Dense(1024, activation='relu')(x)
x = Dense(512, activation='relu')(x)

preds = Dense(NO_CLASSES, activation='softmax')(x)

model = Model(base_model.input, preds)

As much as I understood, we first took output layer of base_model and it added 5 layers to that 1 GlobalAveragePooling2d, 4 Dense layers.

My question is why did it modify the Vgg16 layer structure. Why do we need to repace last 7 layers with 5 different layers. Couldn't we set the same 7 layers as trainable or just add identical layers. What is the actual advantage of this replacement.

Before replacement enter image description here

After replacement

'global_average_pooling2d_11', 'dense_42', 'dense_43', 'dense_44', 'dense_45'
royal_awake
  • 36
  • 5
  • 1
    Hi @royal_awake, When the data similarity is very high, we do not need to retrain the model. All we need to do is to customize and modify the output layers according to our problem statement .Kindly refer to this [article](https://www.analyticsvidhya.com/blog/2017/06/transfer-learning-the-art-of-fine-tuning-a-pre-trained-model/) for more information. Thank you! –  Dec 16 '22 at 10:23

0 Answers0