search

IceClear / CLIP-IQA

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images
Other
342 stars 20 forks source link

evaluate() got an unexpected keyword argument 'gpu_collect' while training clipiqa_coop_koniq #18

Open ganeshpulivendula1985 opened 1 year ago

ganeshpulivendula1985 commented 1 year ago

python tools/train.py configs/clipiqa/clipiqa_coop_koniq.py

2023-10-16 08:47:54,004 - mmedit - INFO - workflow: [('train', 1)], max: 500 iters 2023-10-16 08:47:54,004 - mmedit - INFO - Checkpoints will be saved to C:\Users\pdo-labuser\CLIP-IQA\work_dirs\clipiqa_coop_koniq by HardDiskBackend. [>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 2015/2015, 17.2 task/s, elapsed: 117s, ETA: 0sTraceback (most recent call last): File "tools/train.py", line 146, in main() File "tools/train.py", line 135, in main train_model( File "c:\users\pdo-labuser\clip-iqa\mmedit\apis\train.py", line 106, in train_model _non_dist_train( File "c:\users\pdo-labuser\clip-iqa\mmedit\apis\train.py", line 362, in _non_dist_train runner.run(data_loaders, cfg.workflow, cfg.total_iters) File "C:\Users\pdo-labuser\anaconda3\envs\clipiqa\lib\site-packages\mmcv\runner\iter_based_runner.py", line 134, in run iter_runner(iter_loaders[i], **kwargs) File "C:\Users\pdo-labuser\anaconda3\envs\clipiqa\lib\site-packages\mmcv\runner\iter_based_runner.py", line 67, in train self.call_hook('after_train_iter') File "C:\Users\pdo-labuser\anaconda3\envs\clipiqa\lib\site-packages\mmcv\runner\base_runner.py", line 309, in call_hook getattr(hook, fn_name)(self) File "c:\users\pdo-labuser\clip-iqa\mmedit\core\evaluation\eval_hooks.py", line 48, in after_train_iter self.evaluate(runner, results) File "c:\users\pdo-labuser\clip-iqa\mmedit\core\evaluation\eval_hooks.py", line 57, in evaluate eval_res = self.dataloader.dataset.evaluate( TypeError: evaluate() got an unexpected keyword argument 'gpu_collect'

Please help with resolution

IceClear commented 1 year ago

I did not meet such a problem. It seems that you are not using the right env. You may switch to another repo for test. See #13

lmc2000 commented 4 months ago

I also meet such a problem File "tools/train.py", line 146, in main() File "tools/train.py", line 135, in main train_model( File "/home/www/application/models/CLIP-IQA/mmedit/apis/train.py", line 106, in train_model _non_dist_train( File "/home/www/application/models/CLIP-IQA/mmedit/apis/train.py", line 362, in _non_dist_train runner.run(data_loaders, cfg.workflow, cfg.total_iters) File "/home/www/application/miniconda3/envs/clipiqa/lib/python3.8/site-packages/mmcv/runner/iter_based_runner.py", line 134, in run iter_runner(iter_loaders[i], **kwargs) File "/home/www/application/miniconda3/envs/clipiqa/lib/python3.8/site-packages/mmcv/runner/iter_based_runner.py", line 67, in train self.call_hook('after_train_iter') File "/home/www/application/miniconda3/envs/clipiqa/lib/python3.8/site-packages/mmcv/runner/base_runner.py", line 309, in call_hook getattr(hook, fn_name)(self) File "/home/www/application/models/CLIP-IQA/mmedit/core/evaluation/eval_hooks.py", line 48, in after_train_iter self.evaluate(runner, results) File "/home/www/application/models/CLIP-IQA/mmedit/core/evaluation/eval_hooks.py", line 57, in evaluate eval_res = self.dataloader.dataset.evaluate( TypeError: evaluate() got an unexpected keyword argument 'gpu_collect'