Skip to content

Conversation

ShardulNalegave
Copy link
Contributor

Description

Added two examples showcasing how to use MobileNetV2 models using esp-tflite-micro.

  1. examples/mobilenet - Shows how to run a int8 quantized MobileNet V2 (alpha = 0.35) model.
    • Runs on embedded images, includes a script and tutorial to convert any jpg/png image to embedded.
  2. examples/mobilenet_custom - Shows how to run a model with a custom classifier head and int8 quantized MobileNet V2 (alpha = 0.35) base model.
    • Runs on embedded images, includes a script and tutorial to convert any jpg/png image to embedded.
    • Also includes a jupyter notebook to show how to train your own custom models

image

Testing

Tested by running and verifying outputs on ESP32S3-EYE

Checklist

Before submitting a Pull Request, please ensure the following:

  • 🚨 This PR does not introduce breaking changes.
  • All CI checks (GH Actions) pass.
  • Documentation is updated as needed.
  • Tests are updated or added as necessary.
  • Code is well-commented, especially in complex areas.
  • Git history is clean — commits are squashed to the minimum necessary.

@github-actions github-actions bot changed the title Mobilenet V2 Examples Mobilenet V2 Examples (TFMIC-55) Mar 14, 2025
- Added two examples showcasing how to use mobilenet v2 using `esp-tflite-micro`
- `examples/mobilenet` shows how to use int8 quantized mobilenet v2 model with alpha = 0.35
- `examples/mobilenet` shows how to use a model with a custom classifier head using mobilenetv2 as its base model
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant