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.

Practice

1. What is the main purpose of using a pre-trained model for feature extraction in PyTorch?

easy

A. To replace the optimizer with a new one

B. To use learned features from a large dataset and avoid training from scratch

C. To train all layers from random weights

D. To increase the size of the dataset automatically

Solution

1. Step 1: Understand feature extraction concept

   Feature extraction uses a model already trained on a large dataset to get useful features without training all layers again.

2. Step 2: Identify the main benefit

   This saves time and resources by reusing learned knowledge instead of starting from scratch.

3. Final Answer:

   To use learned features from a large dataset and avoid training from scratch -> Option B

4. Quick Check:

   Feature extraction = reuse learned features [OK]

Hint: Pre-trained means reuse, not retrain all layers [OK]

Common Mistakes:

• Thinking feature extraction means training all layers
• Confusing feature extraction with data augmentation
• Believing optimizer changes are part of feature extraction

2. Which PyTorch code snippet correctly freezes all layers of a pre-trained model except the final layer?

easy

A. for param in model.parameters(): param.requires_grad = True
model.fc = nn.Linear(512, 10)

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

C. for param in model.parameters(): param.requires_grad = False
model.fc = nn.Linear(512, 10)

D. model.fc = nn.Linear(512, 10)
for param in model.parameters(): param.requires_grad = False

Solution

1. Step 1: Freeze all layers by setting requires_grad to false

   The loop disables gradient updates for all parameters to keep pre-trained weights fixed.

2. Step 2: Replace the final layer with a new one to train

   Assigning a new linear layer to model.fc allows training only this layer for the new task.

3. Final Answer:

   for param in model.parameters(): param.requires_grad = False model.fc = nn.Linear(512, 10) -> Option C

4. Quick Check:

   Freeze all except final layer = for param in model.parameters(): param.requires_grad = False model.fc = nn.Linear(512, 10) [OK]

Hint: Freeze first, then replace final layer [OK]

Common Mistakes:

• Not freezing layers before replacing final layer
• Freezing final layer instead of others
• Setting requires_grad true for all parameters

3. Given this PyTorch code for feature extraction, what will be the output shape of features?

import torch
import torchvision.models as models
model = models.resnet18(pretrained=True)
model.fc = torch.nn.Identity()
input_tensor = torch.randn(4, 3, 224, 224)
features = model(input_tensor)
print(features.shape)

medium

A. torch.Size([4, 512])

B. torch.Size([4, 1000])

C. torch.Size([4, 3, 224, 224])

D. torch.Size([4, 2048])

Solution

1. Step 1: Understand model modification

   Replacing model.fc with Identity removes the final classification layer, so output is the feature vector before classification.

2. Step 2: Know ResNet18 feature size

   ResNet18 outputs a 512-dimensional vector before the final fc layer for each input image.

3. Final Answer:

   torch.Size([4, 512]) -> Option A

4. Quick Check:

   ResNet18 features = 512 dims [OK]

Hint: Identity layer outputs feature vector size [OK]

Common Mistakes:

• Assuming output is 1000 classes without removing fc
• Confusing batch size with feature dimension
• Expecting 2048 features from ResNet18 (it's 512)

4. Identify the error in this feature extraction code snippet and select the fix:

model = models.resnet50(pretrained=True)
for param in model.parameters():
    param.requires_grad = False
model.fc = nn.Linear(2048, 5)
optimizer = torch.optim.SGD(model.parameters(), lr=0.01)

# Training loop here

medium

A. No error; code is correct

B. Set requires_grad=True for model.fc parameters after replacement

C. Use Adam optimizer instead of SGD

D. Remove freezing of parameters to train all layers

Solution

1. Step 1: Check freezing timing

   The loop freezes existing parameters before replacing model.fc, so the new fc layer's parameters are created with requires_grad=True by default.

2. Step 2: Verify optimizer behavior

   Optimizer only updates parameters where requires_grad=True, which are the new fc parameters; backbone remains frozen.

3. Final Answer:

   No error; code is correct -> Option A

4. Quick Check:

   New layer params unfrozen by default [OK]

Hint: New layers have requires_grad=True by default [OK]

Common Mistakes:

• Assuming freezing all parameters includes new layers
• Changing optimizer without fixing requires_grad
• Removing freezing unnecessarily

5. You want to use a pre-trained ResNet34 to classify 3 classes in your dataset. You freeze all layers except the last one. However, your training accuracy stays very low. What is the best next step to improve feature extraction performance?

hard

A. Reduce batch size to 1 to improve gradient estimates

B. Increase learning rate to 1.0 for faster training

C. Replace the optimizer with SGD without momentum

D. Unfreeze some deeper layers to fine-tune features for your task

Solution

1. Step 1: Understand freezing impact

   Freezing all but last layer may limit model's ability to adapt features to new classes, causing low accuracy.

2. Step 2: Fine-tune some deeper layers

   Unfreezing some layers closer to output allows the model to adjust features better for your specific dataset.

3. Final Answer:

   Unfreeze some deeper layers to fine-tune features for your task -> Option D

4. Quick Check:

   Fine-tune layers = better adaptation [OK]

Hint: Fine-tune layers if frozen model underperforms [OK]

Common Mistakes:

• Increasing learning rate too much causes instability
• Changing optimizer without addressing feature adaptation
• Reducing batch size unnecessarily