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.

Practice

1. What is the main advantage of deploying AI models on a Jetson Nano device?

easy

A. It allows running AI models locally without needing internet connection.

B. It requires a powerful cloud server to function.

C. It only supports training models, not inference.

D. It can only run models written in Java.

Solution

1. Step 1: Understand Jetson Nano's purpose

   Jetson Nano is designed to run AI models locally on a small device, enabling offline use.

2. Step 2: Compare options

   Options A, B, and D are incorrect because Jetson Nano does not require cloud servers, supports inference, and primarily uses Python and C++, not Java.

3. Final Answer:

   It allows running AI models locally without needing internet connection. -> Option A

4. Quick Check:

   Local AI inference = C [OK]

Hint: Jetson Nano runs AI locally, no internet needed [OK]

Common Mistakes:

• Thinking Jetson Nano needs cloud servers
• Confusing training with inference capabilities
• Assuming it only supports Java

2. Which Python library is commonly used to load TensorRT models on Jetson Nano?

easy

A. tensorflow

B. tensorrt

C. scikit-learn

D. matplotlib

Solution

1. Step 1: Identify the library for TensorRT

   The 'tensorrt' Python library is specifically designed to load and run TensorRT models on Jetson Nano.

2. Step 2: Eliminate other options

   'tensorflow' is for TensorFlow models, 'scikit-learn' is for classical ML, and 'matplotlib' is for plotting, not model loading.

3. Final Answer:

   tensorrt -> Option B

4. Quick Check:

   TensorRT model loading = tensorrt [OK]

Hint: TensorRT models load with 'tensorrt' library in Python [OK]

Common Mistakes:

• Choosing tensorflow instead of tensorrt
• Confusing plotting libraries with model libraries
• Using scikit-learn for deep learning models

3. Given the following Python snippet on Jetson Nano, what will be printed?

import tensorrt as trt
TRT_LOGGER = trt.Logger()
with open('model.engine', 'rb') as f:
    engine_data = f.read()
runtime = trt.Runtime(TRT_LOGGER)
engine = runtime.deserialize_cuda_engine(engine_data)
print(type(engine))

medium

A. None

B. <class 'tensorflow.Graph'>

C. SyntaxError

D. <class 'tensorrt.ICudaEngine'>

Solution

1. Step 1: Understand deserialization output

   The 'deserialize_cuda_engine' method returns an ICudaEngine object representing the TensorRT engine.

2. Step 2: Check print statement output

   Printing type(engine) will show <class 'tensorrt.ICudaEngine'> indicating successful engine loading.

3. Final Answer:

   <class 'tensorrt.ICudaEngine'> -> Option D

4. Quick Check:

   deserialize_cuda_engine returns ICudaEngine [OK]

Hint: deserialize_cuda_engine returns ICudaEngine type [OK]

Common Mistakes:

• Expecting TensorFlow graph type
• Assuming None is returned
• Confusing syntax error with runtime output

4. You try to run a TensorRT model on Jetson Nano but get the error: RuntimeError: CUDA out of memory. What is the best way to fix this?

medium

A. Use a larger model for better accuracy.

B. Increase the learning rate.

C. Reduce the batch size during inference.

D. Disable CUDA and run on CPU only.

Solution

1. Step 1: Understand CUDA out of memory error

   This error means the GPU memory is full and cannot allocate more for the model inference.

2. Step 2: Choose the best fix

   Reducing batch size lowers memory usage, fixing the error. Increasing learning rate or using larger models increases memory use. Disabling CUDA slows inference drastically.

3. Final Answer:

   Reduce the batch size during inference. -> Option C

4. Quick Check:

   CUDA memory error fix = reduce batch size [OK]

Hint: Lower batch size to fix CUDA memory errors [OK]

Common Mistakes:

• Increasing learning rate to fix memory issues
• Using bigger models without memory check
• Disabling CUDA without considering speed impact

5. You want to deploy a custom object detection model on Jetson Nano. Which sequence of steps is correct for deployment?

hard

A. Train model -> Convert to TensorRT engine -> Load engine with tensorrt -> Run inference

B. Train model -> Run inference directly on Jetson Nano without conversion -> Convert to TensorRT engine

C. Convert to TensorRT engine -> Train model -> Load engine -> Run inference

D. Load engine -> Train model -> Convert to TensorRT engine -> Run inference

Solution

1. Step 1: Understand deployment workflow

   First, train the model on a powerful machine, then convert it to TensorRT engine for Jetson Nano optimized inference.

2. Step 2: Load and run inference

   After conversion, load the TensorRT engine on Jetson Nano using the tensorrt library and run inference.

3. Final Answer:

   Train model -> Convert to TensorRT engine -> Load engine with tensorrt -> Run inference -> Option A

4. Quick Check:

   Correct deployment order = A [OK]

Hint: Train first, then convert and load TensorRT engine [OK]

Common Mistakes:

• Trying to run inference before conversion
• Converting before training the model
• Loading engine before training