MCPcopy Create free account

hub / github.com/beibuwandeluori/DFGC_Detection / functions

Functions401 in github.com/beibuwandeluori/DFGC_Detection

⨍ Functions 401◇ Types & classes 93
Method__getitem__
(self, index)
data_preparation/generate_adversarial/attack_ensemble_example4.py:84
Method__init__
(self, is_rotation=True)
utils/utils.py:9
Method__init__
(self)
utils/utils.py:78
Method__init__
(self, model_name, header)
utils/utils.py:94
Method__init__
(self, in_channels, out_channels, kernel_size, stride=1, dilation=1, groups=1, bias=True)
submission_Det/utils.py:228
Method__init__
(self, kernel_size, stride, padding=0, dilation=1, return_indices=False, ceil_mode=False)
submission_Det/utils.py:296
Method__init__
(self, kernel_size, stride, image_size=None, **kwargs)
submission_Det/utils.py:319
Method__init__
(self, blocks_args=None, global_params=None)
submission_Det/efficientnet.py:180
Method__init__
(self, modelchoice, num_out_classes=2, dropout=0.0)
submission_Det/efficientnet.py:448
Method__init__
(self, img_folder, face_info, input_size=300)
submission_Det/model.py:17
Method__init__
(self, input_size=[224, 224])
submission_Det/model.py:69
Method__init__
(self, is_rotation=True)
dataset/utils.py:22
Method__init__
(self, landmarks, face, channels=4)
dataset/DeepFakeMask.py:49
Method__init__
(self, root_path='/pubdata/chenby/dataset/Celeb-DF-v2_chenhan/Celeb-DF-v2-face', data_type='train',
dataset/dataset.py:97
Method__init__
(self, modelchoice, num_out_classes=2, dropout=0.0)
network/models.py:37
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/train_baseline_model/resnet18/resnet18.py:32
Method__init__
(self, root_path="", video_names=[], phase='train', num_class=2, transform=None)
data_preparation/train_baseline_model/resnet18/celeb_df_v2_dataset.py:22
Method__init__
(self, videos_path, batch_size=32, transform=None, num_class=2, scale=1.3, frame_subsample_c
data_preparation/train_baseline_model/resnet18/data_utils.py:89
Method__init__
(self, video_path, transform=None)
data_preparation/train_baseline_model/resnet18/data_utils.py:114
Method__init__
(self, face_images, transform=None)
data_preparation/train_baseline_model/resnet18/data_utils.py:138
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/train_baseline_model/vgg19_vgg19_bn/vgg19_bn.py:32
Method__init__
(self, root_path="", video_names=[], phase='train', num_class=2, transform=None, size=(256, 2
data_preparation/train_baseline_model/vgg19_vgg19_bn/celeb_df_v2_dataset.py:37
Method__init__
(self, root_path="", video_names=[], phase='train', num_class=2, transform=None)
data_preparation/train_baseline_model/vgg19_vgg19_bn/celeb_df_v2_dataset.py:194
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/train_baseline_model/vgg19_vgg19_bn/vgg19.py:32
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/train_baseline_model/resnet34_resnet50_vgg16_vgg16_bn/resnet34.py:32
Method__init__
(self, root_path="", video_names=[], phase='train', num_class=2, transform=None)
data_preparation/train_baseline_model/resnet34_resnet50_vgg16_vgg16_bn/celeb_df_v2_dataset.py:41
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/train_baseline_model/resnet34_resnet50_vgg16_vgg16_bn/resnet50.py:32
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/train_baseline_model/resnet34_resnet50_vgg16_vgg16_bn/vgg16.py:32
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/train_baseline_model/resnet34_resnet50_vgg16_vgg16_bn/vgg16_bn.py:32
Method__init__
(self, mean, std)
data_preparation/generate_adversarial/attack_ensemble_example2.py:25
Method__init__
(self, permutation=[2, 1, 0])
data_preparation/generate_adversarial/attack_ensemble_example2.py:50
Method__init__
(self, fake_path, is_one_hot=False, transforms=None,frame_num=5,use_mask=True)
data_preparation/generate_adversarial/attack_ensemble_example2.py:63
Method__init__
(self, model1, model2=None, model3=None,model4=None)
data_preparation/generate_adversarial/attack_ensemble_example2.py:110
Method__init__
(self, landmarks, face, channels=4)
data_preparation/generate_adversarial/get_dlib_mask.py:18
Method__init__
(self, mean, std)
data_preparation/generate_adversarial/attack_ensemble_example3.py:23
Method__init__
(self, permutation=[2, 1, 0])
data_preparation/generate_adversarial/attack_ensemble_example3.py:48
Method__init__
(self, fake_path, is_one_hot=False, transforms=None,frame_num=5,use_mask=True)
data_preparation/generate_adversarial/attack_ensemble_example3.py:61
Method__init__
(self, model1, model2=None, model3=None,model4=None)
data_preparation/generate_adversarial/attack_ensemble_example3.py:109
Method__init__
(self, mean, std)
data_preparation/generate_adversarial/attack_ensemble_example5.py:23
Method__init__
(self, permutation=[2, 1, 0])
data_preparation/generate_adversarial/attack_ensemble_example5.py:48
Method__init__
(self, fake_path, is_one_hot=False, transforms=None,frame_num=5,use_mask=True)
data_preparation/generate_adversarial/attack_ensemble_example5.py:61
Method__init__
(self, model1, model2=None, model3=None,model4=None)
data_preparation/generate_adversarial/attack_ensemble_example5.py:108
Method__init__
(self, mean, std)
data_preparation/generate_adversarial/attack_ensemble_example1.py:24
Method__init__
(self, permutation=[2, 1, 0])
data_preparation/generate_adversarial/attack_ensemble_example1.py:49
Method__init__
(self, fake_path, is_one_hot=False, transforms=None,frame_num=5,use_mask=True)
data_preparation/generate_adversarial/attack_ensemble_example1.py:62
Method__init__
(self, model1, model2=None, model3=None,model4=None)
data_preparation/generate_adversarial/attack_ensemble_example1.py:110
Method__init__
(self, eps=8/255.0, alpha=2/255.0, steps=40, low=0.8, high=1.2, div_prob=0.9, device=torch.device('cuda'))
data_preparation/generate_adversarial/attacker.py:41
Method__init__
(self, eps=8 / 255, steps=5, decay=1.0, low=0.8, high=1.2, div_prob=0.9, lpips=None, beta=1.0,
data_preparation/generate_adversarial/attacker.py:86
Method__init__
(self, mean, std)
data_preparation/generate_adversarial/attack_ensemble_example4.py:23
Method__init__
(self, permutation=[2, 1, 0])
data_preparation/generate_adversarial/attack_ensemble_example4.py:48
Method__init__
(self, fake_path, is_one_hot=False, transforms=None,frame_num=5,use_mask=True)
data_preparation/generate_adversarial/attack_ensemble_example4.py:61
Method__init__
(self, model1, model2=None, model3=None,model4=None)
data_preparation/generate_adversarial/attack_ensemble_example4.py:108
Method__init__
(self, in_channels, out_channels, kernel_size=1, stride=1, padding=0, dilation=1, bias=False)
data_preparation/generate_adversarial/models/xception.py:32
Method__init__
Constructor Args: num_classes: number of classes
data_preparation/generate_adversarial/models/xception.py:103
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/generate_adversarial/models/vgg19_bn.py:32
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/generate_adversarial/models/resnet34.py:32
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/generate_adversarial/models/resnet50.py:32
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/generate_adversarial/models/vgg16.py:32
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/generate_adversarial/models/vgg16_bn.py:32
Method__init__
(self, input_dim, class_num, droprate, relu=False, bnorm=True, num_bottleneck=512, linear=Tru
data_preparation/generate_adversarial/models/vgg19.py:32
Method__init__
(self, margin=2.0)
loss/losses.py:37
Method__len__
(self)
submission_Det/model.py:29
Method__len__
(self)
dataset/dataset.py:228
Method__len__
(self)
data_preparation/train_baseline_model/resnet18/celeb_df_v2_dataset.py:113
Method__len__
(self)
data_preparation/train_baseline_model/resnet18/data_utils.py:109
Method__len__
(self)
data_preparation/train_baseline_model/resnet18/data_utils.py:133
Method__len__
(self)
data_preparation/train_baseline_model/resnet18/data_utils.py:149
Method__len__
(self)
data_preparation/train_baseline_model/vgg19_vgg19_bn/celeb_df_v2_dataset.py:186
Method__len__
(self)
data_preparation/train_baseline_model/vgg19_vgg19_bn/celeb_df_v2_dataset.py:255
Method__len__
(self)
data_preparation/train_baseline_model/resnet34_resnet50_vgg16_vgg16_bn/celeb_df_v2_dataset.py:132
Method__len__
(self)
data_preparation/generate_adversarial/attack_ensemble_example2.py:83
Method__len__
(self)
data_preparation/generate_adversarial/attack_ensemble_example3.py:81
Method__len__
(self)
data_preparation/generate_adversarial/attack_ensemble_example5.py:81
Method__len__
(self)
data_preparation/generate_adversarial/attack_ensemble_example1.py:82
Method__len__
(self)
data_preparation/generate_adversarial/attack_ensemble_example4.py:80
Functionaccuracy_score
(y_true, y_pred)
data_preparation/train_baseline_model/vgg19_vgg19_bn/metrics.py:36
Functionaccuracy_score
(y_true, y_pred)
data_preparation/train_baseline_model/resnet34_resnet50_vgg16_vgg16_bn/metrics.py:36
Methodbuild_mask
(self)
dataset/DeepFakeMask.py:83
Methodbuild_mask
(self)
dataset/DeepFakeMask.py:107
Methodbuild_mask
(self)
dataset/DeepFakeMask.py:136
Methodbuild_mask
(self)
dataset/DeepFakeMask.py:178
Methodbuild_mask
(self)
data_preparation/generate_adversarial/get_dlib_mask.py:52
Methodbuild_mask
(self)
data_preparation/generate_adversarial/get_dlib_mask.py:78
Methodencode
Encode a list of BlockArgs to a list of strings. Args: blocks_args (list[namedtuples]): A list of BlockArgs namedtuples of block
submission_Det/utils.py:437
Methodextract_endpoints
Use convolution layer to extract features from reduction levels i in [1, 2, 3, 4, 5]. Args: inputs (tensor): Input tensor
submission_Det/efficientnet.py:246
Functionf1_score
(y_true, y_pred)
data_preparation/train_baseline_model/resnet18/metrics.py:27
Functionf1_score
(y_true, y_pred)
data_preparation/train_baseline_model/vgg19_vgg19_bn/metrics.py:27
Functionf1_score
(y_true, y_pred)
data_preparation/train_baseline_model/resnet34_resnet50_vgg16_vgg16_bn/metrics.py:27
Methodforward
(self, x)
submission_Det/utils.py:56
Methodforward
(ctx, i)
submission_Det/utils.py:63
Methodforward
(self, x)
submission_Det/utils.py:75
Methodforward
(self, x)
submission_Det/utils.py:232
Methodforward
(self, x)
submission_Det/utils.py:269
Methodforward
(self, x)
submission_Det/utils.py:302
Methodforward
(self, x)
submission_Det/utils.py:338
Methodforward
MBConvBlock's forward function. Args: inputs (tensor): Input tensor. drop_connect_rate (bool): Drop connect rate (flo
submission_Det/efficientnet.py:106
Methodforward
EfficientNet's forward function. Calls extract_features to extract features, applies final linear layer, and returns logits. Args:
submission_Det/efficientnet.py:315
Methodforward
(self, x)
submission_Det/efficientnet.py:474
Methodforward
(self, input)
submission_Det/model.py:73
Methodforward
(self, x)
network/models.py:68
← previousnext →201–300 of 401, ranked by callers