Hi, I quantized YOLOv5 by adding QuantStub and DeQuantStubs to all the ConvBnReLU2d in the network, exported to ONNX and folded the QDQ nodes into QLinearConv.
However, during inference, this is the result for the whole image:
Hi, I quantized YOLOv5 by adding QuantStub and DeQuantStubs to all the ConvBnReLU2d in the network, exported to ONNX and folded the QDQ nodes into QLinearConv.
However, during inference, this is the result for the whole image: