niehen6174
niehen6174
Hi.Thank you so much for your open source work. When I trained motion_deblur, I found that the effect in the paper could not be achieved. 1. I followed the dependency...
I am doing Real-time 3D semantic segmentation.And now I also want to train a network of ScanNet semantic segmentation. But there is a problem. I can't find the code for...
Hello, I would like to ask about GRU and LSTM. TensorRT is already supported in IRNNv2Layer. Why are tensorRT IRNNv2Layer not used in the onnx-tensorRT but split into many layers?
### Your current environment information ibibverbs not available, ibv_fork_init skipped Collecting environment information... PyTorch version: 2.1.1+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build...
Hello, I have a question about the GPU architecture that group gemm can use. I saw in the official examples that it only supports Ampere architecture or higher. Your code...