CNN Transfer Learning with CNNs 4

Question 1

When freezing layers during transfer learning in Keras/TensorFlow, which attribute is set to False?

Accepted Answer

layer.trainable

Answer

Setting layer.trainable = False in Keras prevents weight updates for that layer during training.

Question 2

Which pretrained model is known for its 'inception modules' that process features at multiple scales simultaneously?

Accepted Answer

GoogLeNet (Inception)

Answer

GoogLeNet introduced inception modules that apply convolutions of different kernel sizes in parallel, capturing multi-scale features.

Question 3

What problem does data augmentation specifically help address during transfer learning fine-tuning?

Accepted Answer

Overfitting when the target dataset is small

Answer

Data augmentation artificially expands the small target dataset, reducing overfitting during fine-tuning.

Question 4

In PyTorch, how do you freeze all parameters of a pretrained model before adding a new classifier?

Accepted Answer

for param in model.parameters(): param.requires_grad = False

Answer

Setting requires_grad = False on all parameters prevents gradient computation and weight updates for the pretrained backbone.

Question 5

EfficientNet scales CNN depth, width, and resolution using a principle called:

Accepted Answer

Compound scaling

Answer

EfficientNet uses compound scaling to uniformly scale all three dimensions (depth, width, resolution) for balanced performance.

CNN - Convolutional Neural Networks Practice Test