somepago / ama Goto Github PK
View Code? Open in Web Editor NEWThe official codebase for Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders paper (UAI'21).
License: Apache License 2.0
The official codebase for Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders paper (UAI'21).
License: Apache License 2.0
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: Runwandb 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.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.