torchvision pre-trained models in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained ResNet18 model from torchvision.

PyTorch

import torchvision.models as models
model = models.[1](pretrained=True)

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

Aalexnet

Bvgg16

Cresnet18

Ddensenet121

Attempts:

3 left

💡 Hint

Common Mistakes

Using a different model function like vgg16 instead of resnet18.

Forgetting to set pretrained=True to load pre-trained weights.

The function resnet18 loads the ResNet18 architecture with pre-trained weights.

2fill in blank

medium

Complete the code to set the model to evaluation mode.

PyTorch

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

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

Apredict

Btrain

Cfit

Deval

Attempts:

3 left

💡 Hint

Common Mistakes

Calling train() instead of eval(), which keeps the model in training mode.

Using a non-existent method like predict().

Calling eval() sets the model to evaluation mode, disabling dropout and batch normalization updates.

3fill in blank

hard

Fix the error in the code to correctly load a pre-trained VGG16 model.

PyTorch

import torchvision.models as models
model = models.vgg16([1]=True)

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

Apretrained

Bweights

Cload_pretrained

Duse_pretrained

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'weights' instead of 'pretrained' in older torchvision versions.

Using incorrect argument names like 'load_pretrained' or 'use_pretrained'.

The correct argument to load pre-trained weights in torchvision models is pretrained=True.

4fill in blank

hard

Fill both blanks to create a dictionary of model names and their corresponding pre-trained model functions.

PyTorch

models_dict = {
    'resnet': models.[1],
    'alexnet': models.[2]
}

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

Aresnet18

Bvgg16

Calexnet

Ddensenet121

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing up model function names or using unrelated models.

Using the same option for both blanks.

The dictionary maps 'resnet' to resnet18 and 'alexnet' to alexnet functions from torchvision.models.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps model names to their pre-trained model instances, filtering only models with names longer than 6 characters.

PyTorch

model_names = ['resnet18', 'vgg16', 'alexnet', 'densenet121']
models_dict = {
    [1]: models.[2](pretrained=True)
    for [3] in model_names if len([1]) > 6
}

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

Aname

Cmodel

Attempts:

3 left

💡 Hint

Common Mistakes

Using different variable names inconsistently.

Not matching the variable names in the condition and comprehension.

The comprehension uses name as the key and function name, and model as the loop variable. The condition filters names longer than 6 characters.

Practice

1. What is the main advantage of using torchvision pre-trained models?

easy

A. They automatically improve your dataset quality.

B. They generate new images from text descriptions.

C. They reduce the size of your images.

D. They allow you to use powerful image models without training from scratch.

Solution

1. Step 1: Understand what pre-trained models do

   Pre-trained models are already trained on large datasets, so you don't need to train them from zero.

2. Step 2: Identify the main benefit

   This saves time and resources, letting you use powerful models quickly.

3. Final Answer:

   They allow you to use powerful image models without training from scratch. -> Option D

4. Quick Check:

   Pre-trained models = reuse trained weights [OK]

Hint: Pre-trained means ready to use without full training [OK]

Common Mistakes:

• Thinking pre-trained models improve data quality
• Confusing pre-trained models with image resizing
• Believing they generate images from text

2. Which of the following is the correct way to load a pre-trained ResNet18 model from torchvision?

easy

A. model = torchvision.models.resnet18(weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1)

B. model = torchvision.resnet18(pretrained=True)

C. model = torchvision.models.resnet18(pretrained=False)

D. model = torchvision.models.load_resnet18(pretrained=True)

Solution

1. Step 1: Recall the updated torchvision syntax

   Since torchvision 0.13+, pre-trained weights are loaded using the 'weights' argument with a weights enum, not 'pretrained=True'.

2. Step 2: Identify the correct syntax for ResNet18

   Use torchvision.models.resnet18(weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1).

3. Final Answer:

   model = torchvision.models.resnet18(weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1) -> Option A

4. Quick Check:

   Use weights=enum, not pretrained=True [OK]

Hint: Use weights= argument, not pretrained=True [OK]

Common Mistakes:

• Using pretrained=False which doesn't load pre-trained weights
• Calling torchvision.resnet18 directly
• Using a non-existent load_resnet18 function

3. What will be the output shape of the following code snippet using a pre-trained ResNet18 model on a batch of 8 RGB images of size 224x224?

import torch
import torchvision.models as models
model = models.resnet18(weights=models.ResNet18_Weights.IMAGENET1K_V1)
model.eval()
inputs = torch.randn(8, 3, 224, 224)
outputs = model(inputs)
print(outputs.shape)

medium

A. torch.Size([8, 3, 224, 224])

B. torch.Size([8, 1000])

C. torch.Size([8, 512])

D. torch.Size([1, 1000])

Solution

1. Step 1: Understand ResNet18 output size

   ResNet18 pre-trained on ImageNet outputs logits for 1000 classes, so output shape is (batch_size, 1000).

2. Step 2: Check input batch size and output shape

   Input batch size is 8, so output shape is (8, 1000).

3. Final Answer:

   torch.Size([8, 1000]) -> Option B

4. Quick Check:

   Batch size 8, 1000 classes output [OK]

Hint: Output shape = (batch_size, number_of_classes) [OK]

Common Mistakes:

• Confusing output with input image shape
• Expecting feature vector size instead of class logits
• Assuming batch size 1 output

4. You wrote this code to use a pre-trained model for prediction but get wrong results:

model = torchvision.models.resnet18(weights=torchvision.models.ResNet18_Weights.IMAGENET1K_V1)
inputs = torch.randn(1, 3, 224, 224)
outputs = model(inputs)

What is the likely mistake?

medium

A. Input tensor shape should be (3, 224, 224) without batch dimension.

B. You need to set weights=None to use pre-trained weights.

C. You forgot to call model.eval() before prediction.

D. You must convert inputs to numpy arrays before passing to model.

Solution

1. Step 1: Check model mode for prediction

   Pre-trained models must be set to evaluation mode with model.eval() to disable dropout and batch norm updates.

2. Step 2: Identify the missing step

   The code misses model.eval(), so outputs may be incorrect or inconsistent.

3. Final Answer:

   You forgot to call model.eval() before prediction. -> Option C

4. Quick Check:

   Set model.eval() before inference [OK]

Hint: Always call model.eval() before predicting [OK]

Common Mistakes:

• Not calling model.eval() before inference
• Wrong input tensor shape without batch
• Trying to convert tensors to numpy before model

5. You want to fine-tune a pre-trained ResNet18 model on your own 5-class dataset. Which of the following code snippets correctly replaces the final layer for this task?

hard

A. model.fc = torch.nn.Linear(in_features=512, out_features=5)

B. model.classifier = torch.nn.Linear(in_features=1000, out_features=5)

C. model.fc = torch.nn.Linear(in_features=2048, out_features=5)

D. model.output = torch.nn.Linear(in_features=512, out_features=1000)

Solution

1. Step 1: Identify the final layer of ResNet18

   ResNet18's final fully connected layer is model.fc with input features 512 and output 1000 classes.

2. Step 2: Replace final layer for 5 classes

   To fine-tune, replace model.fc with a new Linear layer with 512 inputs and 5 outputs.

3. Final Answer:

   model.fc = torch.nn.Linear(in_features=512, out_features=5) -> Option A

4. Quick Check:

   Replace model.fc with correct output size [OK]

Hint: Replace model.fc with Linear(512, number_of_classes) [OK]

Common Mistakes:

• Replacing wrong attribute like model.classifier
• Using wrong input feature size (2048 instead of 512)
• Not changing output features to dataset classes