Quantization in SPPELAN

levipereira / yolov9-qat

Implementation of YOLOv9 QAT optimized for deployment on TensorRT platforms.

Apache License 2.0

89 stars 11 forks source link

Quantization in SPPELAN #6

Open levipereira opened 7 months ago

levipereira commented 7 months ago

We're currently working on improving our YOLOv9 model by implementing quantization in the class SPPELAN(nn.Module): . We've observed that the current implementation is generating reformat operations.

Any contributions, suggestions, or shared experiences will be valued.

DXL64 commented 4 months ago

Have you done this? I have the same issue but with SPPF in yolov5.