Feature extraction strategy in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pretrained ResNet model for feature extraction.

PyTorch

import torch
import torchvision.models as models

model = models.resnet18(pretrained=[1])

Drag options to blanks, or click blank then click option'

AFalse

BTrue

CNone

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Setting pretrained to False loads a model without learned features.

Using None or 0 causes errors or no pretrained weights.

Setting pretrained=True loads the model with weights trained on ImageNet, which is essential for feature extraction.

2fill in blank

medium

Complete the code to freeze all parameters in the model to prevent training updates.

PyTorch

for param in model.parameters():
    param.[1] = False

Drag options to blanks, or click blank then click option'

Arequires_grad

Bgrad

Cdetach

Dtrain

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'grad' or 'train' attributes which do not exist for parameters.

Calling detach() on parameters instead of setting requires_grad.

Setting requires_grad to False disables gradient computation, freezing the parameters during training.

3fill in blank

hard

Fix the error in the code to replace the final fully connected layer with an identity layer for feature extraction.

PyTorch

import torch.nn as nn
model.fc = [1]()

Drag options to blanks, or click blank then click option'

Ann.Identity

Bnn.Linear

Cnn.ReLU

Dnn.Conv2d

Attempts:

3 left

💡 Hint

Common Mistakes

Using nn.Linear requires parameters and changes output size.

Using nn.ReLU or nn.Conv2d changes the output and is not identity.

Replacing the final layer with nn.Identity removes it, so the model outputs features before classification.

4fill in blank

hard

Fill both blanks to create a feature extractor that outputs features without gradients and sets the model to evaluation mode.

PyTorch

with torch.no_grad():
    model.[1]()
    features = model(inputs)

Drag options to blanks, or click blank then click option'

Arequires_grad

Btrain

Ceval

Dzero_grad

Attempts:

3 left

💡 Hint

Common Mistakes

Using model.train() enables training mode, which is incorrect here.

Using requires_grad or zero_grad are not model methods.

Calling model.eval() sets the model to evaluation mode, disabling dropout and batch norm updates during feature extraction.

5fill in blank

hard

Fill all three blanks to extract features from a batch of images using a pretrained model with frozen parameters and identity final layer.

PyTorch

import torch
import torchvision.models as models
import torch.nn as nn

model = models.resnet50(pretrained=[1])
for param in model.parameters():
    param.requires_grad = [2]
model.fc = nn.[3]()
model.eval()

with torch.no_grad():
    features = model(images)

Drag options to blanks, or click blank then click option'

ATrue

BFalse

CIdentity

DLinear

Attempts:

3 left

💡 Hint

Common Mistakes

Not freezing parameters causes training updates.

Not replacing final layer outputs class scores, not features.

Setting pretrained to False loads random weights.

Load pretrained weights (True), freeze parameters (requires_grad=False), and replace final layer with nn.Identity for feature extraction.