torchvision pre-trained models in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output shape of pre-trained ResNet18 model

What is the shape of the output tensor when passing a batch of 8 RGB images of size 224x224 through a pre-trained ResNet18 model from torchvision?

PyTorch

import torch
import torchvision.models as models

model = models.resnet18(pretrained=True)
model.eval()

input_tensor = torch.randn(8, 3, 224, 224)
output = model(input_tensor)
output_shape = output.shape
print(output_shape)

A torch.Size([8, 512])

B torch.Size([8, 100])

C torch.Size([8, 1000])

D torch.Size([8, 2048])

💡 Hint

The pre-trained ResNet18 model outputs class scores for 1000 classes.

The pre-trained ResNet18 model outputs a tensor of shape (batch_size, 1000) representing the scores for 1000 ImageNet classes.

❓ Model Choice

intermediate

Choosing a model for feature extraction

You want to extract 512-dimensional feature vectors from images using a pre-trained torchvision model without the final classification layer. Which model and modification is correct?

A Use squeezenet and replace model.classifier with torch.nn.Linear(512, 1000)

B Use resnet18 and replace model.fc with torch.nn.Identity()

C Use vgg16 and replace model.features with torch.nn.Identity()

D Use alexnet and remove model.classifier entirely

💡 Hint

The final fully connected layer in ResNet18 is model.fc.

In ResNet18, the final classification layer is model.fc. Replacing it with Identity returns the 512-dimensional features before classification.

❓ Hyperparameter

advanced

Correct input normalization for pre-trained models

Which normalization mean and standard deviation values should be used to preprocess images before feeding them into any torchvision pre-trained model?

A mean=[0.406, 0.456, 0.485], std=[0.225, 0.224, 0.229]

B mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5]

C mean=[0.0, 0.0, 0.0], std=[1.0, 1.0, 1.0]

D mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]

💡 Hint

These values are based on ImageNet dataset statistics.

All torchvision pre-trained models expect input images normalized with mean=[0.485, 0.456, 0.406] and std=[0.229, 0.224, 0.225].

❓ Metrics

advanced

Top-1 accuracy of pre-trained models on ImageNet validation

Which of the following is the closest reported Top-1 accuracy on ImageNet validation for the pre-trained torchvision DenseNet121 model?

A 74.9%

B 69.8%

C 77.0%

D 82.3%

💡 Hint

DenseNet121 accuracy is generally around mid-70s percent.

The DenseNet121 pre-trained model achieves about 74.9% Top-1 accuracy on ImageNet validation.

🔧 Debug

expert

Identifying error when loading pre-trained model weights

What error will occur if you try to load a pre-trained model with torchvision.models.resnet50(pretrained=False) and then call model.load_state_dict(torch.load('resnet50_weights.pth')) where the weights file contains pre-trained weights?

A RuntimeError: Error(s) in loading state_dict for ResNet

B FileNotFoundError: No such file or directory: 'resnet50_weights.pth'

C TypeError: load_state_dict() missing 1 required positional argument

D No error, model loads weights successfully

💡 Hint

Mismatch in model architecture or missing keys causes loading errors.

If the weights file does not exactly match the model architecture or keys, load_state_dict raises a RuntimeError with details about missing or unexpected keys.