search

mit-han-lab / tinyengine

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
https://mcunet.mit.edu
MIT License
792 stars 130 forks source link

About the code that generates the codegen in face_mask_detection... #83

Open wslong36 opened 1 year ago

wslong36 commented 1 year ago

Hello team.

In face_mask_detection, I found that all the functions used in genModel.c are from the int_forward_op directory.

Could you upload the tflite model for face mask and the code that generates the codegen?

meenchen commented 1 year ago

Hi @wslong36,

The model architecture for face mask detection is basically the same as the person detection model (https://github.com/mit-han-lab/tinyengine/blob/main/assets/detection.tflite). The only difference is the number of classes for the output.

We generate the code with an internal model format (e.g., a JSON file) for this model, so it is not uploaded to this repo.