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.