沧浪
The logs: RuntimeError: Expected to have finished reduction in the prior iteration before starting a new one. This error indicates that your module has parameters that were not used in...
Table 9: Complexity of five networks for SISR. | Methods | Parameters | Flops | | ---- | ---- |---- | | VDSR [22] | 665K | 10.90G | |...
We have encountered the same problem, the output accuracy is very different after exporting from the QDQ onnx model to the trt engine model. And I am a super-resolution model,...
nice, but the opencv 2.4 will get error about cv::VideoCapture. You can modify the Makefile LIBRARIES += opencv_imgcodecs opencv_videoio ...
> 这还是个挺核心的错误，用ProgramEntrance_1 不会有这个错误吗？好像都会调用到这个地方的 ProgramEntrance_1 不会报错
你好，都是官方代码，模型默认是 resnet18 唯一改动是：https://github.com/openppl-public/ppq/blob/master/ProgramEntrance_2.py#L234 这里用 calibration_dataloader = [torch.zeros(size=[1,3,224,224]) for _ in range(32)]