Quantize an onnx / yolo object Detection model to Int16
Budget: $10 – $30 USD
I am looking for a skilled developer who can write me a Python code quantize an ONNX object detection model (weights and bias) to Int16.
There should be some Quantization Frameworks like tensorflow, onnxruntime etc. to convert float32 to int16, but i could not find it. (i only found int8 converter but i need int16 conversion)
Ideal skills and experience for this project include:
- Proficiency in working with ONNX Yolo object detection models
- Experience with quantization processes and techniques
- Knowledge of Int16 data type and its implications in machine learning models
There should be some Quantization Frameworks like tensorflow, onnxruntime etc. to convert float32 to int16, but i could not find it. (i only found int8 converter but i need int16 conversion)
Ideal skills and experience for this project include:
- Proficiency in working with ONNX Yolo object detection models
- Experience with quantization processes and techniques
- Knowledge of Int16 data type and its implications in machine learning models