somepago / ama Goto Github PK

To,
The concerned ones ,
I was running the repository for cifar10 dataset , in the data.py file it is popping up an error in the line 30.
The issue says ,the very class "CIFAR10Anom" class does not have any 'class_to_idx' attribute .

How to get rid of this ???

I quote the whole error below :

wandb: Run data is saved locally in /home/genie/AMA/AMA/wandb/run-20220314_143815-2ey9xmj1
wandb: Run wandb offline to turn off syncing.

Chosen Seed: 5
Namespace(abnormal_classes=None, ae_recon_loss_type='wasserstein', anom_metric_type='f_anomloss', anom_pc=0.1, anom_recon_lambda=5.0, atyp_ratio=0.5, atyp_selec_style='inward', augment=False, batchsize=256, ch=128, corrup=False, corruption=0, cuda=0, dataroot='./data/CIFAR10/', dataset='cifar10', expt_name='cifar_experiments', gp_lambda=10, image_size=32, interpolation_in_recon=False, ip_lambda=0.2, learning_setting='ss', lr=0.0003, manualSeed=5, model_load_path='', ngpu=1, normal_class="['ship']", num_channels=3, num_epochs=100, nz=128, ood_model=False, recon_loss_type='wasserstein', regularizer_lambda=1.0, sampling=True, save_logs_epochs=1, save_model_epochs=30, save_model_root='logs', spectral_norm=1, start=0, update_ratio=5, use_penalty=True, val_split=0.05, workers=4)
Files already downloaded and verified
Traceback (most recent call last):
File "train.py", line 175, in
dataset_train, dataset_valid, dataset_test = data.load_data(dataset = opt.dataset, ood = opt.ood_model, anom_classes = anom_classes,anom_ratio=opt.anom_pc,corruption= opt.corruption, seed = opt.manualSeed, augmentation = opt.augment, learning_setting= opt.learning_setting, valid_split = opt.val_split)
File "/home/genie/AMA/AMA/data.py", line 237, in load_data
dataset_train = CIFAR10Anom(root=root,stage='train',
File "/home/genie/AMA/AMA/data.py", line 30, in init
if len(set(anom_classes) & set(self.class_to_idx.keys()))==0:
AttributeError: 'CIFAR10Anom' object has no attribute 'class_to_idx'
Traceback (most recent call last):
File "train.py", line 175, in
dataset_train, dataset_valid, dataset_test = data.load_data(dataset = opt.dataset, ood = opt.ood_model, anom_classes = anom_classes,anom_ratio=opt.anom_pc,corruption= opt.corruption, seed = opt.manualSeed, augmentation = opt.augment, learning_setting= opt.learning_setting, valid_split = opt.val_split)
File "/home/genie/AMA/AMA/data.py", line 237, in load_data
dataset_train = CIFAR10Anom(root=root,stage='train',
File "/home/genie/AMA/AMA/data.py", line 30, in init
if len(set(anom_classes) & set(self.class_to_idx.keys()))==0:
AttributeError: 'CIFAR10Anom' object has no attribute 'class_to_idx'

Thanks in advance.