search

v-iashin / MDVC

PyTorch implementation of Multi-modal Dense Video Captioning (CVPR 2020 Workshops)
https://v-iashin.github.io/mdvc
143 stars 20 forks source link

I have two Issues - 1. I want to run this without GPU (i don't have GPU in Ubuntu) #22

Closed taruntiwarihp closed 3 years ago

taruntiwarihp commented 3 years ago

(mdvc) tarun@tarun-VirtualBox:~/Downloads/MDVC$ python main.py --device_ids 1 log_path: ./log/0601100925 model_checkpoint_path: ./log/0601100925 THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1565272271120/work/aten/src/THC/THCGeneral.cpp line=50 error=38 : no CUDA-capable device is detected Traceback (most recent call last): File "main.py", line 572, in main(cfg) File "main.py", line 177, in main torch.cuda.set_device(cfg.device_ids[0]) File "/home/tarun/miniconda3/envs/mdvc/lib/python3.7/site-packages/torch/cuda/init.py", line 281, in set_device torch._C._cuda_setDevice(device) File "/home/tarun/miniconda3/envs/mdvc/lib/python3.7/site-packages/torch/cuda/init.py", line 179, in _lazy_init torch._C._cuda_init() RuntimeError: cuda runtime error (38) : no CUDA-capable device is detected at /opt/conda/conda-bld/pytorch_1565272271120/work/aten/src/THC/THCGeneral.cpp:50

taruntiwarihp commented 3 years ago

2 - I want to test (run time) code with input using the camera itself (visual and audio) -> can you explain how can I get input from the camera or OpenCV, also share some code related to it

v-iashin commented 3 years ago
  1. The code is designed for GPU use only. If you want to run it on CPU, I suggest asking the community to help you or try to adapt it yourself.
  2. I don't have any ready-to-use code which you request and I am occupied with other stuff at the moment. You have Google to help you with this.
taruntiwarihp commented 3 years ago

Thanks for your help brother !