Fine-tuning approach in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained model for fine-tuning.

Computer Vision

from torchvision import models
model = models.resnet18(pretrained=[1])

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

A0

BFalse

CTrue

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using pretrained=False will initialize random weights, not useful for fine-tuning.

Passing None or 0 will cause errors or ignore pre-trained weights.

Setting pretrained=True loads the model with weights trained on ImageNet, which is needed for fine-tuning.

2fill in blank

medium

Complete the code to freeze all layers except the last fully connected layer.

Computer Vision

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

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

Adetach

Bgrad

Ctrain

Drequires_grad

Attempts:

3 left

💡 Hint

Common Mistakes

Using grad or train attributes will cause errors or have no effect.

detach is a method, not an attribute to freeze parameters.

Setting requires_grad=False freezes the parameters so they won't update during training.

3fill in blank

hard

Fix the error in replacing the last layer to match 10 output classes.

Computer Vision

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

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

A10

B0

C1

D100

Attempts:

3 left

💡 Hint

Common Mistakes

Using 100 or 1 will cause shape mismatch errors during training.

Using 0 will cause runtime errors.

The last layer must output the number of classes, here 10 for fine-tuning on a 10-class dataset.

4fill in blank

hard

Fill both blanks to set the optimizer to update only trainable parameters with learning rate 0.001.

Computer Vision

import torch.optim as optim
optimizer = optim.SGD([1], lr=[2])

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

Afilter(lambda p: p.requires_grad, model.parameters())

Bmodel.parameters()

C0.01

D0.001

Attempts:

3 left

💡 Hint

Common Mistakes

Passing all parameters causes frozen layers to update unnecessarily.

Using a too high learning rate like 0.01 may harm fine-tuning.

We use filter to pass only parameters that require gradients to the optimizer, and set learning rate to 0.001 for fine-tuning.

5fill in blank

hard

Fill all three blanks to complete the training loop for one epoch with loss calculation and optimizer step.

Computer Vision

model.train()
for inputs, labels in dataloader:
    optimizer.zero_grad()
    outputs = model([1])
    loss = criterion(outputs, [2])
    loss.[3]()
    optimizer.step()

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

Ainputs

Blabels

Cbackward

Dforward

Attempts:

3 left

💡 Hint

Common Mistakes

Passing labels to model instead of inputs causes errors.

Calling forward() on loss is invalid; use backward().

We pass inputs to the model, compare outputs with labels to compute loss, then call loss.backward() to compute gradients before optimizer.step().