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.