torchvision detection models in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained Faster R-CNN model from torchvision.

PyTorch

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

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

Afasterrcnn_resnet50_fpn

Bresnet50

Cmobilenet_v2

Dvgg16

Attempts:

3 left

💡 Hint

Common Mistakes

Using classification model names like 'resnet50' instead of detection models.

Forgetting to set pretrained=True to load weights.

The function fasterrcnn_resnet50_fpn loads a Faster R-CNN model with a ResNet-50 backbone and Feature Pyramid Network, commonly used for object detection.

2fill in blank

medium

Complete the code to put the model in evaluation mode before inference.

PyTorch

model = detection.fasterrcnn_resnet50_fpn(pretrained=True)
model.[1]()

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

Aeval

Bfit

Ctrain

Dpredict

Attempts:

3 left

💡 Hint

Common Mistakes

Using train() mode during inference, which can cause inconsistent results.

Trying to call predict() which is not a PyTorch model method.

Calling eval() on the model sets it to evaluation mode, disabling dropout and batch normalization updates, which is important for inference.

3fill in blank

hard

Fix the error in the code to move the model to the GPU device if available.

PyTorch

import torch
model = detection.fasterrcnn_resnet50_fpn(pretrained=True)
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = model.[1](device)

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

Amove

Bto

Ccuda

Ddevice

Attempts:

3 left

💡 Hint

Common Mistakes

Using cuda() directly, which fails if CUDA is not available.

Using non-existent methods like device() or move().

The to() method moves the model to the specified device, which can be CPU or GPU.

4fill in blank

hard

Fill in the blank to perform inference with the model.

PyTorch

import torch
from PIL import Image
from torchvision import transforms

image = Image.open('image.jpg').convert('RGB')
transform = transforms.Compose([
    transforms.ToTensor(),
])
input_tensor = transform(image)
model.eval()
with torch.no_grad():
    outputs = model([1])

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

Aunsqueeze

Bsqueeze

Cinput_tensor

D[input_tensor]

Attempts:

3 left

💡 Hint

Common Mistakes

Passing input_tensor directly instead of a list.

Trying to add a batch dimension with unsqueeze(), which is unnecessary and incorrect for these models.

The model expects a list of tensors as input (even for a single image), so we pass [input_tensor] to it. Each tensor should be of shape (C, H, W).

5fill in blank

hard

Fill all three blanks to filter detection results by confidence score and print detected labels.

PyTorch

labels = outputs[0]['labels']
scores = outputs[0]['scores']
threshold = 0.8
filtered_indices = [i for i, score in enumerate(scores) if score [1] threshold]
filtered_labels = [labels[i].item() for i in filtered_indices]
print('Detected labels:', [2])

# Convert label IDs to class names
COCO_INSTANCE_CATEGORY_NAMES = [
    '__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
    'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign',
    'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
    'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag',
    'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball', 'kite',
    'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
    'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana',
    'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
    'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'dining table',
    'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
    'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock',
    'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
]

filtered_names = [COCO_INSTANCE_CATEGORY_NAMES[label] for label in filtered_labels]
print('Detected class names:', [3])

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

A>

B>=

Cfiltered_labels

Dfiltered_names

Attempts:

3 left

💡 Hint

Common Mistakes

Using '>' which excludes scores exactly equal to threshold.

Printing class names before converting label IDs.

Confusing filtered_labels and filtered_names in print statements.

We filter scores with >= threshold to include confident detections. We print the filtered label IDs first, then convert them to class names and print those.

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