Mandylove1993
Mandylove1993
 直接把mmdet下面的mmcv最高版本改成1.5.0,就可以了
I also need weight connections too. Can you send me a copy? My email is [email protected]，Thank you！ @flymin
I meet this error too!,Have you resolved?
> when train utils epoch 8, an error occurs: /opt/conda/conda-bld/pytorch_1634272168290/work/aten/src/ATen/native/cuda/Loss.cu:115: operator(): block: [1488,0,0], thread: [32,0,0] Assertion `input_val >= zero && input_val
> ok, I try it，thanks I meet same error，are you solved? just upgrade pytorch to 1.12.1? Is it work?,Thanks!
> Assuming plain TensorRT library inference using C++ based on the screenshot. My understanding is we need to load the plugins by (1) loading the `libmmdeploy_tensorrt_ops.so` library, (2) calling `initLibNvInferPlugins`...
我也遇到了这个bevdepth/ops/voxel_pooling_train/src/voxel_pooling_train_forward_cuda.cu(60): error: no instance of overloaded function "atomicAdd" matches the argument list错误，，是不是和硬件有关？我用的3080，唉，试了很多pytorch版本了已经