LayneH / SAT-selective-cls

Self-Adaptive Traning for Selective Classification.
MIT License
2 stars 4 forks source link

train_gambler_split.txt not found #4

Open DingQiang2018 opened 2 years ago

DingQiang2018 commented 2 years ago

Hi! I ran bash run_catsdogs.sh and met an error as the following:

Namespace(arch='vgg16_bn', coverage=[100.0, 99.0, 98.0, 97.0, 95.0, 90.0, 85.0, 80.0, 75.0, 70.0, 60.0, 50.0, 40.0, 30.0, 20.0, 10.0], dataset='catsdogs', epochs=300, evaluate=False, gamma=0.5, gpu_id='1', loss='sat', lr=0.1, manualSeed=7350, momentum=0.9, pretrain=0, rewards=[2.2], sat_momentum=0.9, save='./log/catsdogs_vgg16_bn_sat_', schedule=[25, 50, 75, 100, 125, 150, 175, 200, 225, 250, 275], test_batch=200, train_batch=128, weight_decay=0.0005, workers=4)
==> Preparing dataset catsdogs
Traceback (most recent call last):
  File "train.py", line 590, in <module>
    main()
  File "train.py", line 155, in main
    trainset = dataset_utils.CatsDogs(root='~/datasets/cats_dogs', split='train', transform=transform_train, resize=64)
  File "/home/dingqiang/SAT-selective-cls/dataset_utils.py", line 88, in __init__
    with open(os.path.join(root, split + "_gambler_split.txt"), 'r') as fin:
FileNotFoundError: [Errno 2] No such file or directory: '~/datasets/cats_dogs/train_gambler_split.txt'

Could you help me solve this problem?

sandruskyi commented 1 year ago

Hi @DingQiang2018 ! Did you achieve to run the code for cats vs dogs? I have the same problem... Thank you!

DingQiang2018 commented 1 year ago

No, I gave up...