expected str, bytes or os.PathLike object, not NoneType

[umairjavaid]

Getting the above issue after running the following commands

!git clone https://github.com/clovaai/wsolevaluation.git os.chdir("wsolevaluation") !bash dataset/prepare_cub.sh

!python main.py --dataset_name CUB \ --architecture vgg16 \ --wsol_method cam \ --experiment_name cub_vgg16 \ --pretrained TRUE \ --num_val_sample_per_class 0 \ --large_feature_map TRUE \ --batch_size 32 \ --epochs 50 \ --lr 0.000227913316 \ --lr_decay_frequency 15 \ --weight_decay 1.00E-04 \ --override_cache FALSE \ --workers 4 \ --box_v2_metric True \ --iou_threshold_list 30 50 70 \ --eval_checkpoint_type last

[umairjavaid]

Start epoch 0 ... Evaluate epoch 0, split val Computing and evaluating cams. Traceback (most recent call last): File "main.py", line 416, in main() File "main.py", line 387, in main trainer.evaluate(epoch=0, split='val') File "main.py", line 309, in evaluate cam_performance = cam_computer.compute_and_evaluate_cams() File "/content/wsolevaluation/inference.py", line 90, in compute_and_evaluate_cams cam_path = ospj(self.log_folder, 'scoremaps', image_id) File "/usr/lib/python3.6/posixpath.py", line 80, in join a = os.fspath(a) TypeError: expected str, bytes or os.PathLike object, not NoneType

[junsukchoe]

I followed your instruction, but unfortunately I could not reproduce your error. Could you let me know which of the two variables (self.log_folder and image_id) is NoneType?

[coallaoh]

Closing the issue, assuming the question was answered :) Please re-open the issue as necessary.