Why pre-trained models accelerate development in PyTorch - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained model in PyTorch.

PyTorch

import torch
import torchvision.models as models

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

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

ATrue

BFalse

CNone

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using False will create a model with random weights.

Setting pretrained=True loads the model with weights trained on a large dataset, speeding up development.

2fill in blank

medium

Complete the code to freeze all layers of the pre-trained model.

PyTorch

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

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

Alayers

Bchildren

Cmodules

Dparameters

Attempts:

3 left

💡 Hint

Common Mistakes

Using children() returns submodules, not parameters.

The parameters() method returns all parameters of the model to freeze them.

3fill in blank

hard

Fix the error in replacing the final layer for transfer learning.

PyTorch

import torch.nn as nn
num_classes = 10
model.fc = nn.[1](num_classes)

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

AConv2d

BLinear

CReLU

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2d or activation layers instead of Linear.

The final fully connected layer should be replaced with nn.Linear to match the number of classes.

4fill in blank

hard

Fill both blanks to set the model to evaluation mode and disable gradient calculation.

PyTorch

model.[1]()
with torch.[2]():
    outputs = model(inputs)

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

Aeval

Bno_grad

Ctrain

Denable_grad

Attempts:

3 left

💡 Hint

Common Mistakes

Using train() instead of eval(), or enable_grad instead of no_grad.

Use eval() to set evaluation mode and no_grad() to disable gradients during inference.

5fill in blank

hard

Fill all three blanks to create a dictionary of layer names and their requires_grad status.

PyTorch

grad_status = {name: param.[1] for name, param in model.[2]() if name.[3]('fc') == False}

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

Arequires_grad

Bnamed_parameters

Cendswith

Dstartswith

Attempts:

3 left

💡 Hint

Common Mistakes

Using parameters() instead of named_parameters(), or endswith instead of startswith.

This code collects the gradient status of all layers except those starting with 'fc' (final layer).