Jetson Nano deployment in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained model on Jetson Nano using PyTorch.

Computer Vision

import torch
model = torch.load('[1]')

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

A'model.pth'

B'model.txt'

C'data.csv'

D'image.jpg'

Attempts:

3 left

💡 Hint

Common Mistakes

Trying to load a non-model file like a CSV or image.

Using incorrect file extensions.

The model file saved by PyTorch usually has a .pth extension. Loading 'model.pth' correctly loads the model.

2fill in blank

medium

Complete the code to move the model to the Jetson Nano GPU device.

Computer Vision

device = torch.device('[1]' if torch.cuda.is_available() else 'cpu')
model.to(device)

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

A'cpu'

B'cuda'

C'gpu'

D'tpu'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'gpu' or 'tpu' which are not valid device strings in PyTorch.

Not checking if CUDA is available before moving the model.

Jetson Nano uses CUDA-enabled GPU, so the device string is 'cuda' to move the model to GPU.

3fill in blank

hard

Fix the error in the code to preprocess an image for Jetson Nano model inference.

Computer Vision

from torchvision import transforms
preprocess = transforms.Compose([
    transforms.Resize(256),
    transforms.CenterCrop(224),
    transforms.ToTensor(),
    transforms.Normalize(mean=[1], std=[0.229, 0.224, 0.225])
])

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

A[0.5, 0.5, 0.5]

B[0.229, 0.224, 0.225]

C[0.485, 0.456, 0.406]

D[1.0, 1.0, 1.0]

Attempts:

3 left

💡 Hint

Common Mistakes

Using the std values as mean.

Using incorrect normalization values causing poor model performance.

The mean values for normalization in ImageNet pretrained models are [0.485, 0.456, 0.406].

4fill in blank

hard

Fill both blanks to run inference on Jetson Nano and get the predicted class index.

Computer Vision

with torch.no_grad():
    input_tensor = preprocess(image).unsqueeze(0).to(device)
    output = model([1])
    _, predicted = torch.max(output, [2])

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

Ainput_tensor

Bdim=1

Cdim=0

Dimage

Attempts:

3 left

💡 Hint

Common Mistakes

Passing raw image instead of tensor to model.

Using wrong dimension in torch.max causing wrong prediction.

The model input is the preprocessed tensor 'input_tensor'. The max is taken along dimension 1 for batch predictions.

5fill in blank

hard

Fill all three blanks to convert model output to probabilities and get top 3 predictions.

Computer Vision

probabilities = torch.nn.functional.[1](output[0])
top_probs, top_idxs = torch.topk(probabilities, [2])
top_probs = top_probs.[3]()

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

Asoftmax

B3

Ctolist

Dsigmoid

Attempts:

3 left

💡 Hint

Common Mistakes

Using sigmoid instead of softmax for multi-class probabilities.

Forgetting to convert tensor to list for easier use.

Softmax converts logits to probabilities. topk with 3 gets top 3 predictions. tolist converts tensor to Python list.