Anas Zafar comments

Results 43 comments of


                                            Anas Zafar

How can I do fine-tuning?

@Juwan-s did you solve this issue?

Traceback-Error running demo.py

@ipbv Your nvcc and pytorch's cuda has different versions it seems

Traceback-Error running demo.py

@ipbv refer to the following issue: https://github.com/facebookresearch/detectron2/issues/567 Hopefully the fix mentioned will work out for you

“Not compiled with GPU support“ with images on README

CUDA is not found when building detectron2. You should make sure python -c 'import torch; from torch.utils.cpp_extension import CUDA_HOME; print(torch.cuda.is_available(), CUDA_HOME)' You can refer to this: https://detectron2.readthedocs.io/en/latest/tutorials/install.html#common-installation-issues

Caught RuntimeError in DataLoader worker process 0 while running test.py for COCO

Has anyone been able to solve this issue?

undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E

@armornik were you able to solve this?

Pretaining for 2D Backbone, with CMU Dataset

@Samleo8 did you understand how do the authors train the 2D backbone? Thanks

Strange values after converting 3D joint positions from world to camera coordinates

@GianMassimiani were you able to solve the problem?

CUDA error: out of memory

Trying using batch size BATCH_SIZE_PER_GPU: 16 or 8

Pytroch and tensorboardx versions are not compatible

@shui-tian-ju-shi what python version did you use?