wang

Why sparse convolutional inference time is longer

1

run python test_timeit.py: compare time with nn.Conv3d() nn.Conv3D() forward time is :0.000066 SparseConv3d() forward time is :0.001239 nn.Conv3D() backward time is :0.000870 SparseConv3d() backward time is :0.001930

onnx->trt 模型转换时，出现显存不够

1

小模型 rtmo-s_8xb32-600e_coco-640x640.onnx 转换时，出现： Tactic Device request: 9000MB Available: 7982MB. Device memory is insufficient to use tactic 为什么需要这么大的显存？

一个目标完全遮挡另一个目标时，分割标签应该怎么处理

1

### 问题确认 Search before asking - [x] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer. ### 请提出你的问题 Please ask your question 如：天空和鸟这种应该怎么处理，利用labelme2seg.py 时，应该怎么处理

### 问题确认 Search before asking - [x] 我已经搜索过问题，但是没有找到解答。I have searched the question and found no related answer. ### 请提出你的问题 Please ask your question paddlepaddle版本为paddle_inferenceV2.6_msvc2019_cu118_cudnn8.6_trt8.5； W0424 09:26:13.359738 15364 helper.h:127] CUDA lazy...