Open Source Converter

Overview

This page outlines the process for converting YOLOv5s PyTorch models to TensorFlow Lite (TFLite) format using an open-source converter. It includes steps for setting up the YOLOv5 environment, applying necessary patches, and performing model conversions to both int8 and fp32 TFLite formats.

YOLOv5s Model Convert

• Source Link: http://github.com/ultralytics/yolov5

• Model Name: YOLOv5s

Setting Up YOLOv5 Environment

1. Clone the repository:

   git clone http://github.com/ultralytics/yolov5
   cd yolov5
   git reset --hard 485da42
   

2. Install Python packages and dependencies:

   pip3 install -r requirements.txt
   

3. Apply Patch

   git apply export_fp32.patch
   

   Note

   This patch modifies the export script to support exporting the model in FP32 (32-bit float) TFLite format instead of FP16 (16-bit float). The changes include:

   • Changing the output filename to indicate FP32 format.

   • Updating the supported types to use tf.float32 for higher precision.

YOLOv5 PyTorch Model Conversion to int8/fp32 TFLite Formats

• int8 format:

  python3 export.py --weights yolov5s.pt --img-size 640 640 --include tflite --int8
  

• fp32 format:

  python3 export.py --weights yolov5s.pt --img-size 640 640 --include tflite
  

Note

The export.py script is used to convert the YOLOv5 model from PyTorch format to TFLite format. The script accepts several parameters:

• –weights specifies the path to the PyTorch model weights.

• –img-size sets the input image size for the model.

• –include determines the output formats, including TFLite.

• –int8 is used to convert the model to int8 quantized format. If not specified, the model will be converted to fp32 format by default.