Checkpoints file and table5_pidinet model
Closed this issue · 5 comments
Hello, where can I download the checkpoints file? I want to train a table5_pidinet model, but I have encountered some difficulties. Is it convenient for email to contact?
Namespace(ablation=False, checkinfo=False, config='carv4', datadir='/home/lu/pidinet-master/data/BSDS500/', dataset=['BSDS'], dil=True, epochs=20, eta=0.3, evaluate=None, evaluate_converted=False, gpu='0', iter_size=24, lmbda=1.1, lr=0.005, lr_steps=[10, 16], lr_type='multistep', model='pidinet', only_bsds=False, opt='adam', print_freq=10, resume=True, sa=True, save_freq=1, savedir='/home/lu/pidinet-master/table5_pidinet/', seed=1631092025, use_cuda=True, wd=0.0001, workers=4)
{'layer0': 'cd', 'layer1': 'ad', 'layer2': 'rd', 'layer3': 'cv', 'layer4': 'cd', 'layer5': 'ad', 'layer6': 'rd', 'layer7': 'cv', 'layer8': 'cd', 'layer9': 'ad', 'layer10': 'rd', 'layer11': 'cv', 'layer12': 'cd', 'layer13': 'ad', 'layer14': 'rd', 'layer15': 'cv'}
initialization done
conv weights: lr 0.005000, wd 0.000100 bn weights: lr 0.005000, wd 0.000010 relu weights: lr 0.005000, wd 0.000000
cuda is used, with 1 gpu devices
Threshold for ground truth: 76.800000 on BSDS_VOC
Threshold for ground truth: 76.800000 on BSDS_VOC
=> loading checkpoint from ''
no checkpoint loaded
Traceback (most recent call last):
File "main.py", line 418, in
main(f)
File "main.py", line 229, in main
train_loader, model, optimizer, epoch, running_file, args, lr_str)
File "main.py", line 264, in train
for i, (image, label) in enumerate(train_loader):
File "/home/lu/anaconda3/envs/python37/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 435, in next
data = self._next_data()
File "/home/lu/anaconda3/envs/python37/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1085, in _next_data
return self._process_data(data)
File "/home/lu/anaconda3/envs/python37/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 1111, in _process_data
data.reraise()
File "/home/lu/anaconda3/envs/python37/lib/python3.7/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)
FileNotFoundError: Caught FileNotFoundError in DataLoader worker process 0.
Original Traceback (most recent call last):
File "/home/lu/anaconda3/envs/python37/lib/python3.7/site-packages/torch/utils/data/_utils/worker.py", line 198, in _worker_loop
data = fetcher.fetch(index)
File "/home/lu/anaconda3/envs/python37/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/lu/anaconda3/envs/python37/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in
data = [self.dataset[idx] for idx in possibly_batched_index]
File "/home/lu/pidinet-master/edge_dataloader.py", line 117, in getitem
lb = np.array(Image.open(os.path.join(self.root, lb_file)), dtype=np.float32)
File "/home/lu/anaconda3/envs/python37/lib/python3.7/site-packages/PIL/Image.py", line 2968, in open
fp = builtins.open(filename, "rb")
FileNotFoundError: [Errno 2] No such file or directory: '/home/lu/pidinet-master/data/BSDS500/HED-BSDS/train/aug_gt_scale_0.5/315.0_1_0/55073.png'
python main.py --model pidinet --config carv4 --sa --dil --resume --iter-size 24 -j 4 --gpu 0 --epochs 20 --lr 0.005 --lr-type multistep --lr-steps 10-16 --wd 1e-4 --savedir /home/lu/pidinet-master/table5_pidinet/ --datadir /home/lu/pidinet-master/data/BSDS500/ --dataset BSDS
python main.py --model pidinet --config carv4 --sa --dil --resume --iter-size 24 -j 4 --gpu 0 --epochs 20 --lr 0.005 --lr-type multistep --lr-steps 10-16 --wd 1e-4 --savedir /home/lu/pidinet-master/table5_pidinet/ --datadir /home/lu/pidinet-master/data/BSDS500/ --dataset BSDS
The checkpoint files are in the google drive and can be downloaded by clicking the model names in the README table. Let me know if there are any question for downloading that.
The error seems like to show the png files of the dataset are not found. Could you please check your png files if they are put in the path correctly?
Thanks for your answer, I have solved this problem
how to solve?