MCPcopy Create free account

hub / github.com/VinAIResearch/Warping-based_Backdoor_Attack-release / functions

Functions227 in github.com/VinAIResearch/Warping-based_Backdoor_Attack-release

↓ 13 callersFunctionprogress_bar
(current, total, msg=None)
utils/utils.py:55
↓ 8 callersFunctionPreActResNet18
(num_classes=10)
classifier_models/preact_resnet.py:104
↓ 8 callersFunctionget_dataloader
(opt, train=True, pretensor_transform=False)
utils/dataloader.py:142
↓ 6 callersFunctionResNet18
()
classifier_models/resnet.py:108
↓ 4 callersMethod__init__
(self, in_channels, out_channels)
classifier_models/shufflenetv2.py:58
↓ 4 callersMethod_make_dense_layers
(self, block, in_planes, nblock)
classifier_models/densenet.py:68
↓ 4 callersMethod_make_layer
(self, block, planes, num_blocks, stride)
classifier_models/senet.py:89
↓ 4 callersMethod_make_layer
(self, in_planes, out_planes, num_blocks, dense_depth, stride)
classifier_models/dpn.py:53
↓ 4 callersMethod_make_layer
(self, block, planes, num_blocks, stride)
classifier_models/preact_resnet.py:84
↓ 4 callersMethod_make_layer
(self, block, planes, num_blocks, stride)
classifier_models/resnet.py:88
↓ 4 callersMethodget_raw_mask
(self)
defenses/neural_cleanse/detecting.py:38
↓ 4 callersMethodget_raw_pattern
(self)
defenses/neural_cleanse/detecting.py:42
↓ 4 callersFunctionswish
(x)
classifier_models/efficientnet.py:12
↓ 3 callersMethod__init__
(self, in_c, out_c, ker_size=(3, 3), stride=1, padding=1, batch_norm=True, relu=True)
networks/blocks.py:6
↓ 3 callersMethod__init__
(self, in_planes, out_planes, stride=1)
classifier_models/pnasnet.py:25
↓ 3 callersMethod_make_layer
(self, num_blocks, stride)
classifier_models/resnext.py:58
↓ 3 callersMethod_make_layer
(self, planes, num_cells)
classifier_models/pnasnet.py:90
↓ 3 callersMethod_make_layer
(self, out_channels, num_blocks)
classifier_models/shufflenetv2.py:110
↓ 3 callersMethod_make_layer
(self, out_planes, num_blocks, groups)
classifier_models/shufflenet.py:68
↓ 3 callersFunctionget_arguments
()
defenses/fine_pruning/config.py:4
↓ 2 callersMethod__init__
(self, opt, train, transforms)
utils/dataloader.py:75
↓ 2 callersMethod__init__
(self, opt, expected_values, variance)
networks/models.py:12
↓ 2 callersMethod__init__
(self, block, num_blocks, num_classes=10)
classifier_models/senet.py:77
↓ 2 callersMethod__init__
(self, block, nblocks, growth_rate=12, reduction=0.5, num_classes=10)
classifier_models/densenet.py:37
↓ 2 callersMethod__init__
(self, in_planes, out_planes, stride, groups)
classifier_models/shufflenet.py:23
↓ 2 callersMethod__init__
(self, in_planes, planes, stride=1)
classifier_models/preact_resnet.py:17
↓ 2 callersMethod__init__
(self, block, num_blocks, num_classes=8)
classifier_models/resnet.py:76
↓ 2 callersMethod_downsample
(self, planes)
classifier_models/pnasnet.py:97
↓ 2 callersMethodsave_result_to_dir
(self, opt)
defenses/neural_cleanse/detecting.py:126
↓ 1 callersFunctionDPN92
()
classifier_models/dpn.py:83
↓ 1 callersFunctionPNASNetB
()
classifier_models/pnasnet.py:118
↓ 1 callersFunctionResNeXt29_2x64d
()
classifier_models/resnext.py:80
↓ 1 callersFunctionSENet18
()
classifier_models/senet.py:109
↓ 1 callersFunctionShuffleNetG2
()
classifier_models/shufflenet.py:88
↓ 1 callersMethod__init__
(self, opt)
defenses/neural_cleanse/detecting.py:93
↓ 1 callersMethod__init__
(self, in_planes, cardinality=32, bottleneck_width=4, stride=1)
classifier_models/resnext.py:15
↓ 1 callersMethod__init__
(self, cfg)
classifier_models/dpn.py:39
↓ 1 callersMethod__init__
(self, in_planes, out_planes, stride=1)
classifier_models/mobilenet.py:14
↓ 1 callersMethod__init__
(self, in_planes, out_planes, kernel_size, stride, expand_ratio=1, se_ratio=0.0, drop_rate=0.0)
classifier_models/efficientnet.py:19
↓ 1 callersMethod__init__
(self, in_planes, out_planes, expansion, stride)
classifier_models/mobilenetv2.py:14
↓ 1 callersMethod__init__
(self, in_planes, n1x1, n3x3red, n3x3, n5x5red, n5x5, pool_planes)
classifier_models/googlenet.py:8
↓ 1 callersMethod_convert_attributes
(self, bool_attributes)
utils/dataloader.py:129
↓ 1 callersMethod_get_classifier
(self, opt)
defenses/neural_cleanse/detecting.py:46
↓ 1 callersMethod_get_data_test_list
(self)
utils/dataloader.py:100
↓ 1 callersMethod_get_data_train_list
(self)
utils/dataloader.py:86
↓ 1 callersMethod_get_denormalize
(self, opt)
defenses/neural_cleanse/detecting.py:69
↓ 1 callersMethod_get_denormalize
(self, opt)
defenses/STRIP/STRIP.py:69
↓ 1 callersMethod_get_denormalizer
(self, opt)
networks/models.py:64
↓ 1 callersMethod_get_entropy
(self, background, dataset, classifier)
defenses/STRIP/STRIP.py:55
↓ 1 callersMethod_get_normalize
(self, opt)
defenses/neural_cleanse/detecting.py:80
↓ 1 callersMethod_get_normalize
(self, opt)
defenses/STRIP/STRIP.py:80
↓ 1 callersMethod_get_normalizer
(self, opt)
networks/models.py:43
↓ 1 callersMethod_make_layers
(self, in_planes)
classifier_models/mobilenet.py:40
↓ 1 callersMethod_make_layers
(self, cfg)
classifier_models/vgg.py:26
↓ 1 callersMethod_make_layers
(self, in_planes)
classifier_models/efficientnet.py:83
↓ 1 callersMethod_make_layers
(self, in_planes)
classifier_models/mobilenetv2.py:63
↓ 1 callersMethod_superimpose
(self, background, overlay)
defenses/STRIP/STRIP.py:49
↓ 1 callersFunctionconvert
(mask)
defenses/fine_pruning/fine-pruning-celeba.py:27
↓ 1 callersFunctioncreate_backdoor
(inputs, identity_grid, noise_grid, opt)
defenses/STRIP/STRIP.py:116
↓ 1 callersFunctioncreate_dir
(path_dir)
defenses/neural_cleanse/neural_cleanse.py:10
↓ 1 callersFunctioncreate_targets_bd
(targets, opt)
defenses/fine_pruning/fine-pruning-mnist.py:17
↓ 1 callersFunctioncreate_targets_bd
(targets, opt)
defenses/fine_pruning/fine-pruning-cifar10-gtsrb.py:17
↓ 1 callersFunctiondensenet_cifar
()
classifier_models/densenet.py:103
↓ 1 callersFunctioneval
( netC, optimizerC, schedulerC, test_dl, noise_grid, identity_grid, opt, )
eval.py:41
↓ 1 callersFunctioneval
( netC, optimizerC, schedulerC, test_dl, noise_grid, identity_grid, best_clean_acc
train.py:163
↓ 1 callersFunctioneval
(netC, identity_grid, noise_grid, test_dl, opt)
defenses/fine_pruning/fine-pruning-mnist.py:27
↓ 1 callersFunctioneval
(netC, identity_grid, noise_grid, test_dl, opt)
defenses/fine_pruning/fine-pruning-celeba.py:40
↓ 1 callersFunctioneval
(netC, identity_grid, noise_grid, test_dl, opt)
defenses/fine_pruning/fine-pruning-cifar10-gtsrb.py:37
↓ 1 callersFunctionget_argument
()
defenses/STRIP/config.py:4
↓ 1 callersFunctionget_dataset
(opt, train=True)
utils/dataloader.py:162
↓ 1 callersFunctionget_model
(opt)
eval.py:20
↓ 1 callersFunctionget_model
(opt)
train.py:20
↓ 1 callersFunctionget_transform
(opt, train=True, pretensor_transform=False)
utils/dataloader.py:36
↓ 1 callersFunctionmain
()
eval.py:106
↓ 1 callersFunctionmain
()
train.py:272
↓ 1 callersFunctionmain
()
utils/dataloader.py:188
↓ 1 callersFunctionmain
()
defenses/fine_pruning/fine-pruning-mnist.py:61
↓ 1 callersFunctionmain
()
defenses/fine_pruning/fine-pruning-celeba.py:76
↓ 1 callersFunctionmain
()
defenses/fine_pruning/fine-pruning-cifar10-gtsrb.py:71
↓ 1 callersFunctionmain
()
defenses/neural_cleanse/neural_cleanse.py:65
↓ 1 callersFunctionmain
()
defenses/STRIP/STRIP.py:198
↓ 1 callersMethodnormalize
(self, x)
defenses/STRIP/STRIP.py:102
↓ 1 callersFunctionoutlier_detection
(l1_norm_list, idx_mapping, opt)
defenses/neural_cleanse/neural_cleanse.py:22
↓ 1 callersMethodreset_state
(self, opt)
defenses/neural_cleanse/detecting.py:118
↓ 1 callersFunctionstrip
(opt, mode="clean")
defenses/STRIP/STRIP.py:125
↓ 1 callersFunctiontrain
(netC, optimizerC, schedulerC, train_dl, noise_grid, identity_grid, tf_writer, epoch, opt)
train.py:41
↓ 1 callersFunctiontrain
(opt, init_mask, init_pattern)
defenses/neural_cleanse/detecting.py:150
↓ 1 callersFunctiontrain_step
(regression_model, optimizerR, dataloader, recorder, epoch, opt)
defenses/neural_cleanse/detecting.py:174
FunctionDPN26
()
classifier_models/dpn.py:73
FunctionDenseNet121
()
classifier_models/densenet.py:87
FunctionDenseNet161
()
classifier_models/densenet.py:99
FunctionDenseNet169
()
classifier_models/densenet.py:91
FunctionDenseNet201
()
classifier_models/densenet.py:95
FunctionEfficientNetB0
()
classifier_models/efficientnet.py:103
FunctionPNASNetA
()
classifier_models/pnasnet.py:114
FunctionPreActResNet101
()
classifier_models/preact_resnet.py:116
FunctionPreActResNet152
()
classifier_models/preact_resnet.py:120
FunctionPreActResNet34
()
classifier_models/preact_resnet.py:108
FunctionPreActResNet50
()
classifier_models/preact_resnet.py:112
FunctionResNeXt29_32x4d
()
classifier_models/resnext.py:92
next →1–100 of 227, ranked by callers