howellyang@qcraft

icon company Tencent icon location Beijing icon location 专注于深度学习模型训练、剪枝、量化、部署，在视觉定位领域有一定的理解和工作经验。

Results 1 comments of howellyang@qcraft

Conv2d stride=2 accuracy mismatch between PyTorch and TensorRT

same problem with TRT 8.4 and Cuda 10.2; stride = 2 with padding create different results with onnx and tensorRT;