Jetson Nano deployment in Computer Vision - Model Metrics & Evaluation

Metrics & Evaluation - Jetson Nano deployment

Which metric matters for Jetson Nano deployment and WHY

When deploying models on Jetson Nano, key metrics include inference speed (latency), accuracy, and power consumption.
Inference speed matters because Jetson Nano has limited computing power, so the model must run fast enough for real-time use.
Accuracy ensures the model makes correct predictions.
Power consumption is important since Jetson Nano is often used in low-power or mobile setups.

Confusion matrix example for Jetson Nano deployed model

      Actual \ Predicted | Positive | Negative
      -------------------|----------|---------
      Positive           |    80    |   20    
      Negative           |    10    |   90    
    

This shows 80 true positives (TP), 20 false negatives (FN), 10 false positives (FP), and 90 true negatives (TN).
From this, precision = 80 / (80 + 10) = 0.89, recall = 80 / (80 + 20) = 0.80.

Precision vs Recall tradeoff in Jetson Nano deployment

For example, if Jetson Nano runs a security camera model detecting intruders:
- High recall means catching most intruders (few missed detections).
- High precision means few false alarms (few false intruder alerts).
If recall is low, intruders might be missed, which is bad.
If precision is low, many false alarms waste attention.
Depending on use, you may prioritize recall (security) or precision (reduce false alarms).

What good vs bad metric values look like for Jetson Nano deployment

Good metrics:

• Accuracy above 85% for reliable predictions.
• Inference latency under 100 milliseconds for smooth real-time use.
• Power consumption low enough to run on battery or limited power supply.

Bad metrics:

• Accuracy below 70%, causing many wrong predictions.
• Inference latency over 500 milliseconds, causing lag.
• High power use, draining battery quickly or overheating device.

Common pitfalls in Jetson Nano deployment metrics

• Ignoring latency: A model with high accuracy but slow speed is unusable in real-time.
• Overfitting: Model performs well on training data but poorly on real Jetson Nano inputs.
• Data leakage: Training data too similar to test data inflates accuracy falsely.
• Power spikes: Not measuring power use can cause device overheating or shutdown.
• Not testing in real environment: Metrics from desktop may not reflect Jetson Nano performance.

Self-check question

Your Jetson Nano model has 98% accuracy but only 12% recall on detecting intruders. Is it good for production? Why or why not?

Answer: No, it is not good. Although accuracy is high, recall is very low, meaning the model misses most intruders. For security, missing intruders is dangerous, so recall must be much higher.

Key Result

For Jetson Nano deployment, balance accuracy with fast inference speed and low power use to ensure real-time, reliable performance.

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