search

NVlabs / AL-MDN

Official pytorch implementation of Active Learning for deep object detection via probabilistic modeling (ICCV 2021)
https://openaccess.thecvf.com/content/ICCV2021/html/Choi_Active_Learning_for_Deep_Object_Detection_via_Probabilistic_Modeling_ICCV_2021_paper.html
Other
168 stars 23 forks source link

Issue in running #13

Closed nabi-rony closed 2 years ago

nabi-rony commented 2 years ago

nit.constant(self.weight,self.gamma) Finished loading model! Traceback (most recent call last): File "C:\Users\fi42\Rony\AL-MDN\eval_voc.py", line 439, in mean_ap = test_net(args.save_folder, net, args.cuda, dataset, File "C:\Users\fi42\Rony\AL-MDN\eval_voc.py", line 385, in test_net detections = net(x).data File "C:\Users\fi42\anaconda3\envs\ACT\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(*input, kwargs) File "C:\Users\fi42\anaconda3\envs\ACT\lib\site-packages\torch\nn\parallel\data_parallel.py", line 166, in forward return self.module(*inputs[0], *kwargs[0]) File "C:\Users\fi42\anaconda3\envs\ACT\lib\site-packages\torch\nn\modules\module.py", line 1051, in _call_impl return forward_call(input, kwargs) File "C:\Users\fi42\Rony\AL-MDN\ssd_gmm.py", line 272, in forward output = self.detect( File "C:\Users\fi42\anaconda3\envs\ACT\lib\site-packages\torch\autograd\function.py", line 150, in call raise RuntimeError( RuntimeError: Legacy autograd function with non-static forward method is deprecated. Please use new-style autograd function with static forward method. (Example: https://pytorch.org/docs/stable/autograd.html#torch.autograd.Function)

Can you let me know what exact version of pytorch, python , cuda, you used? I tried several but got this error?

jwchoi384 commented 2 years ago

Hello @nabi-rony We used pytorch 1.1, python 3.6, CUDA 10.1.