torchvision detection models in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the main purpose of torchvision detection models?

Torchvision detection models are used to find and locate objects within images. They can tell what objects are present and where they are by drawing boxes around them.

beginner

Name two popular torchvision detection models.

Two popular torchvision detection models are Faster R-CNN and SSD (Single Shot MultiBox Detector). Both are used for detecting objects but differ in speed and accuracy.

beginner

How do you load a pretrained Faster R-CNN model from torchvision?

You can load it using: <br><code>import torchvision.models.detection as detection<br>model = detection.fasterrcnn_resnet50_fpn(pretrained=True)</code><br>This loads a model trained on COCO dataset ready to detect common objects.

intermediate

What kind of output do torchvision detection models produce?

They output a list of dictionaries, each dictionary contains:<br>- boxes: coordinates of detected objects<br>- labels: class IDs of objects<br>- scores: confidence scores for each detection

intermediate

Why is it important to set the model to evaluation mode during inference?

Setting the model to evaluation mode (model.eval()) disables training behaviors like dropout and batch normalization updates, ensuring consistent and correct predictions.

Which torchvision detection model is known for balancing speed and accuracy well?

A VGG16

B ResNet-50

C AlexNet

D Faster R-CNN

Faster R-CNN is a popular detection model that balances speed and accuracy well. ResNet-50, VGG16, and AlexNet are classification models.

What does the 'boxes' output from a detection model represent?

A Coordinates of detected objects

B Class names of objects

C Image pixel values

D Model weights

The 'boxes' output contains the coordinates (usually x_min, y_min, x_max, y_max) of each detected object in the image.

How do you prepare a torchvision detection model for inference?

A Call model.train()

B Reset model weights

C Call model.eval()

D Increase learning rate

Calling model.eval() sets the model to evaluation mode, which is necessary for correct inference.

Which dataset is commonly used to pretrain torchvision detection models?

A COCO

B ImageNet

C MNIST

D CIFAR-10

COCO (Common Objects in Context) is a large dataset used for object detection and is commonly used to pretrain detection models.

What does the 'scores' output from a detection model indicate?

A Training loss

B Confidence level of each detected object

C Size of the image

D Number of objects detected

The 'scores' represent the confidence level that the detected object belongs to the predicted class.

Explain how to use a pretrained torchvision detection model to detect objects in a new image.

Think about the steps from loading the model to getting predictions.

Describe the structure of the output from torchvision detection models and what each part means.

Focus on what the model tells you about each detected object.

Practice

1. Which of the following is a detection model provided by torchvision for finding objects in images?

easy

A. ResNet

B. Faster R-CNN

C. VGG16

D. Transformer

Solution

1. Step 1: Understand torchvision detection models

   torchvision offers models specifically for object detection like Faster R-CNN, Mask R-CNN, and RetinaNet.

2. Step 2: Identify the correct model

   ResNet and VGG16 are classification models, and Transformer is a general architecture, not a torchvision detection model.

3. Final Answer:

   Faster R-CNN -> Option B

4. Quick Check:

   Detection model = Faster R-CNN [OK]

Hint: Detection models include 'R-CNN' names in torchvision [OK]

Common Mistakes:

• Confusing classification models with detection models
• Thinking Transformer is a torchvision detection model
• Mixing up model types

2. Which code snippet correctly loads a pretrained Faster R-CNN model from torchvision?

easy

A. model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT')

B. model = torchvision.models.fasterrcnn_resnet50_fpn(pretrained=True)

C. model = torchvision.detection.fasterrcnn_resnet50_fpn(pretrained=True)

D. model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=False)

Solution

1. Step 1: Check the correct module and argument

   In recent torchvision versions, detection models are under torchvision.models.detection and use weights='DEFAULT' instead of pretrained=True.

2. Step 2: Identify the correct syntax

   model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT') uses the correct module path and argument for loading pretrained weights.

3. Final Answer:

   model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT') -> Option A

4. Quick Check:

   Use weights='DEFAULT' to load pretrained detection models [OK]

Hint: Use weights='DEFAULT' for pretrained detection models [OK]

Common Mistakes:

• Using pretrained=True instead of weights='DEFAULT'
• Wrong module path
• Missing 'models' in import path

3. What will be the output type of the following code snippet?

import torch
import torchvision
model = torchvision.models.detection.fasterrcnn_resnet50_fpn(weights='DEFAULT')
model.eval()
inputs = [torch.rand(3, 300, 400)]
outputs = model(inputs)
print(type(outputs))

medium

A.

B.

C.

D.

Solution

1. Step 1: Understand model output format

   torchvision detection models return a list of dictionaries, one per input image.

2. Step 2: Check the type of outputs variable

   Since inputs is a list with one tensor, outputs will be a list containing one dictionary.

3. Final Answer:

   <class 'list'> -> Option D

4. Quick Check:

   Detection model output = list of dicts [OK]

Hint: Detection models output a list, one dict per input image [OK]

Common Mistakes:

• Expecting a single tensor output
• Confusing output with dict directly
• Not wrapping inputs in a list

4. Identify the error in this code snippet that tries to use a pretrained Mask R-CNN model:

import torchvision
model = torchvision.models.detection.maskrcnn_resnet50_fpn(pretrained=True)
model.eval()

medium

A. The function name should be fasterrcnn_resnet50_fpn

B. Mask R-CNN is not available in torchvision

C. The argument 'pretrained' is deprecated; use 'weights' instead

D. Missing import for torch

Solution

1. Step 1: Check function and argument usage

   Mask R-CNN is available as maskrcnn_resnet50_fpn in torchvision.models.detection.

2. Step 2: Identify deprecated argument

   Using pretrained=True is deprecated; the correct way is weights='DEFAULT'.

3. Final Answer:

   The argument 'pretrained' is deprecated; use 'weights' instead -> Option C

4. Quick Check:

   Use weights='DEFAULT' instead of pretrained=True [OK]

Hint: Replace pretrained=True with weights='DEFAULT' [OK]

Common Mistakes:

• Using deprecated pretrained argument
• Confusing model names
• Assuming Mask R-CNN is missing

5. You want to fine-tune a pretrained RetinaNet model from torchvision on your custom dataset with 5 classes. Which step is necessary before training?

hard

A. Replace the model's box predictor head to output 6 classes (5 + background)

B. Change the input image size to 224x224

C. Set pretrained=False to train from scratch

D. Freeze all layers except the backbone

Solution

1. Step 1: Understand class output adjustment

   Detection models include a background class, so for 5 classes, output head must predict 6 classes.

2. Step 2: Modify the box predictor head

   Replace the box predictor to match the number of classes (5 + 1 background) before training.

3. Final Answer:

   Replace the model's box predictor head to output 6 classes (5 + background) -> Option A

4. Quick Check:

   Adjust output head for custom classes [OK]

Hint: Add 1 for background class when changing output head [OK]

Common Mistakes:

• Not adjusting output head for new classes
• Changing input size unnecessarily
• Freezing all layers without fine-tuning head