MCPcopy Create free account

hub / github.com/TARTRL/Deepfake_Detection / functions

Functions965 in github.com/TARTRL/Deepfake_Detection

↓ 2 callersMethodcell_forward
(self, x_left, x_right)
dfd/timm/models/pnasnet.py:155
↓ 2 callersFunctioncheck_dir
(dirname)
dfd/utils.py:61
↓ 2 callersFunctionconv2d_same
( x, weight: torch.Tensor, bias: Optional[torch.Tensor] = None, stride: Tuple[int, int] = (1, 1),
dfd/timm/models/layers/conv2d_same.py:14
↓ 2 callersFunctioncreate_conv2d_pad
(in_chs, out_chs, kernel_size, **kwargs)
dfd/timm/models/layers/conv2d_same.py:57
↓ 2 callersFunctioncreate_deepfake_loader_v3
( dataset, input_size, batch_size, is_training=False, use_prefetcher=T
dfd/timm/data/loader.py:724
↓ 2 callersFunctioncreate_deepfake_model_v4
Create a model Args: model_name (str): name of model to instantiate pretrained (bool): load pretrained ImageNet-1k weights if tru
dfd/timm/models/factory.py:190
↓ 2 callersFunctioncreate_deepfake_transform_v1
( input_size, is_training=False, use_prefetcher=False, color_jitter=0.4,
dfd/timm/data/transforms_factory.py:407
↓ 2 callersFunctiondistribute_bn
(model, world_size, reduce=False)
dfd/timm/utils.py:263
↓ 2 callersMethodfeature_channels
(self, location)
dfd/timm/models/efficientnet_blocks.py:126
↓ 2 callersMethodfeature_module
(self, location)
dfd/timm/models/efficientnet_blocks.py:123
↓ 2 callersFunctionfind_images_and_targets_v1
(folder, class_to_idx=None, leaf_name_only=True)
dfd/timm/data/dataset.py:45
↓ 2 callersMethodforward_features
(self, x)
dfd/timm/models/dla.py:311
↓ 2 callersFunctionget_all_images_list
(list_files)
dfd/timm/data/dataset.py:216
↓ 2 callersFunctionget_all_images_list_v3
(list_files)
dfd/timm/data/dataset.py:362
↓ 2 callersMethodget_cycle_length
(self, cycles=0)
dfd/timm/scheduler/tanh_lr.py:107
↓ 2 callersMethodget_output
(self, device)
dfd/timm/models/feature_hooks.py:28
↓ 2 callersFunctionget_padding_value
(padding, kernel_size, **kwargs)
dfd/timm/models/layers/conv2d_same.py:34
↓ 2 callersFunctionget_same_padding
(x: int, k: int, s: int, d: int)
dfd/timm/models/layers/padding.py:18
↓ 2 callersFunctionget_state_dict
(model)
dfd/timm/utils.py:32
↓ 2 callersFunctionload_class_map_v2
(class_names)
dfd/timm/data/dataset.py:210
↓ 2 callersFunctionmixup_target
(target, num_classes, lam=1., smoothing=0.0, device='cuda')
dfd/timm/data/mixup.py:10
↓ 2 callersFunctionnatural_key
See http://www.codinghorror.com/blog/archives/001018.html
dfd/timm/data/dataset.py:18
↓ 2 callersFunctionnew_dir
(dirname)
dfd/utils.py:77
↓ 2 callersFunctionone_hot
(x, num_classes, on_value=1., off_value=0., device='cuda')
dfd/timm/data/mixup.py:5
↓ 2 callersFunctionpad_same
(x, k: List[int], s: List[int], d: List[int] = (1, 1))
dfd/timm/models/layers/padding.py:28
↓ 2 callersMethodset_transform
(self, transform, transform_rotateds)
dfd/timm/data/dataset.py:275
↓ 2 callersFunctiontransform
(x, y, matrix)
dfd/timm/data/auto_augment.py:108
↓ 2 callersFunctiontransforms_deepfake_eval
( img_size=224, crop_pct=None, interpolation='bilinear', use_prefetcher=False,
dfd/timm/data/transforms_factory.py:186
↓ 2 callersFunctiontransforms_deepfake_eval_v3
( img_size=224, use_prefetcher=True )
dfd/timm/data/transforms_factory.py:225
↓ 2 callersFunctiontransforms_deepfake_train_v3
( img_size=600, color_jitter=0.4, use_prefetcher=False, flicker=0., ro
dfd/timm/data/transforms_factory.py:137
↓ 2 callersFunctionunwrap_model
(model)
dfd/timm/utils.py:25
↓ 2 callersMethodupdate_slow
(self, group)
dfd/timm/optim/lookahead.py:27
↓ 2 callersFunctionvalidate
(model, loader, loss_fn, args, log_suffix='')
dfd/runners/train.py:703
↓ 1 callersMethod__init__
(self, model, decay=0.9999, device='', resume='')
dfd/timm/utils.py:298
↓ 1 callersMethod__init__
(self, params, lr=1e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0)
dfd/timm/optim/radam.py:12
↓ 1 callersMethod__init__
( self, root, load_bytes=False, transform=None, cl
dfd/timm/data/dataset.py:79
↓ 1 callersMethod__init__
(self, cfg, in_chans=3, num_classes=1000, global_pool='avg', drop_rate=0.0)
dfd/timm/models/hrnet.py:524
↓ 1 callersMethod__init__
(self, block_args, num_classes=1000, in_chans=3, stem_size=16, num_features=1280, head_bias=True,
dfd/timm/models/mobilenetv3.py:75
↓ 1 callersMethod__init__
(self, cfg, num_classes=1000, in_chans=3, drop_rate=0.0, global_pool='avg')
dfd/timm/models/selecsls.py:111
↓ 1 callersMethod__init__
(self, inplanes, planes, stride=1, downsample=None, cardinality=1, base_width=64, sk_kwargs=N
dfd/timm/models/sknet.py:48
↓ 1 callersMethod__init__
(self, drop_prob=None)
dfd/timm/models/layers/drop.py:106
↓ 1 callersMethod__init__
(self, channels=None, kernel_size=3, gamma=2, beta=1)
dfd/timm/models/layers/eca.py:52
↓ 1 callersMethod__init__
Selective Kernel Attention Module Selective Kernel attention mechanism factored out into its own module.
dfd/timm/models/layers/selective_kernel.py:22
↓ 1 callersMethod__init__
(self)
dfd/timm/loss/cross_entropy.py:31
↓ 1 callersMethod__setstate__
(self, state)
dfd/timm/optim/radam.py:17
↓ 1 callersMethod_apply_basic
(self, img, mixing_weights, m)
dfd/timm/data/auto_augment.py:744
↓ 1 callersMethod_apply_blended
(self, img, mixing_weights, m)
dfd/timm/data/auto_augment.py:728
↓ 1 callersFunction_at_least_x_are_equal
At least `x` of `a` and `b` `Tensors` are equal.
dfd/timm/data/tf_preprocessing.py:79
↓ 1 callersMethod_build_tf_graph
(self)
dfd/timm/data/tf_preprocessing.py:209
↓ 1 callersMethod_calc_blended_weights
(self, ws, m)
dfd/timm/data/auto_augment.py:718
↓ 1 callersMethod_check_branches
(self, num_branches, blocks, num_blocks, num_inchannels, num_channels)
dfd/timm/models/hrnet.py:412
↓ 1 callersMethod_cleanup_checkpoints
(self, trim=0)
dfd/timm/utils.py:114
↓ 1 callersFunction_create_deepfake_model
(model_kwargs, default_cfg, pretrained=False)
dfd/timm/models/efficientnet.py:544
↓ 1 callersFunction_decode_and_random_crop
Make a random crop of image_size.
dfd/timm/data/tf_preprocessing.py:86
↓ 1 callersFunction_decode_block_str
Decode block definition string Gets a list of block arg (dicts) through a string notation of arguments. E.g. ir_r2_k3_s2_e1_i32_o16_se0.25_n
dfd/timm/models/efficientnet_builder.py:20
↓ 1 callersFunction_extract_tar_info
(tarfile, class_to_idx=None, sort=True)
dfd/timm/data/dataset.py:580
↓ 1 callersFunction_flip
Random horizontal image flip.
dfd/timm/data/tf_preprocessing.py:129
↓ 1 callersFunction_gen_fbnetc
FBNet-C Paper: https://arxiv.org/abs/1812.03443 Ref Impl: https://github.com/facebookresearch/maskrcnn-benchmark/blob/master/maskrcn
dfd/timm/models/efficientnet.py:695
↓ 1 callersFunction_gen_mnasnet_small
Creates a mnasnet-b1 model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet Paper: https://arxiv.org/pdf/1807
dfd/timm/models/efficientnet.py:640
↓ 1 callersFunction_gen_mobilenet_v2
Generate MobileNet-V2 network Ref impl: https://github.com/tensorflow/models/blob/master/research/slim/nets/mobilenet/mobilenet_v2.py Paper:
dfd/timm/models/efficientnet.py:669
↓ 1 callersFunction_gen_mobilenet_v3_rw
Creates a MobileNet-V3 model. Ref impl: ? Paper: https://arxiv.org/abs/1905.02244 Args: channel_multiplier: multiplier to number o
dfd/timm/models/mobilenetv3.py:230
↓ 1 callersFunction_gen_spnasnet
Creates the Single-Path NAS model from search targeted for Pixel1 phone. Paper: https://arxiv.org/abs/1904.02877 Args: channel_multipl
dfd/timm/models/efficientnet.py:725
↓ 1 callersFunction_get_pixels
(per_pixel, rand_color, patch_size, dtype=torch.float32, device='cuda')
dfd/timm/data/random_erasing.py:6
↓ 1 callersFunction_interpolation
(kwargs)
dfd/timm/data/auto_augment.py:44
↓ 1 callersFunction_kernel_valid
(k)
dfd/timm/models/layers/selective_kernel.py:14
↓ 1 callersMethod_load_checkpoint
(self, checkpoint_path)
dfd/timm/utils.py:312
↓ 1 callersMethod_make_block
(self, ba, block_idx, block_count)
dfd/timm/models/efficientnet_builder.py:228
↓ 1 callersMethod_make_block
(self, ba, block_idx, block_count)
dfd/timm/models/efficientnet_builder.py:400
↓ 1 callersMethod_make_branches
(self, num_branches, block, num_blocks, num_channels)
dfd/timm/models/hrnet.py:450
↓ 1 callersMethod_make_fuse_layers
(self)
dfd/timm/models/hrnet.py:457
↓ 1 callersMethod_make_head
(self, pre_stage_channels)
dfd/timm/models/hrnet.py:572
↓ 1 callersMethod_make_one_branch
(self, branch_index, block, num_blocks, num_channels, stride=1)
dfd/timm/models/hrnet.py:431
↓ 1 callersMethod_padding
(self, x)
dfd/timm/models/layers/median_pool.py:24
↓ 1 callersFunction_parse_args
()
dfd/runners/train.py:238
↓ 1 callersFunction_posterize_level_to_arg
(level, _hparams)
dfd/timm/data/auto_augment.py:222
↓ 1 callersFunction_pytorch_padding
(kernel_size, stride=1, dilation=1, **_)
dfd/timm/models/gluon_xception.py:63
↓ 1 callersFunction_scale_stage_depth
Per-stage depth scaling Scales the block repeats in each stage. This depth scaling impl maintains compatibility with the EfficientNet scaling
dfd/timm/models/efficientnet_builder.py:139
↓ 1 callersFunction_select_rand_weights
(weight_idx=0, transforms=None)
dfd/timm/data/auto_augment.py:600
↓ 1 callersFunction_solarize_level_to_arg
(level, _hparams)
dfd/timm/data/auto_augment.py:243
↓ 1 callersFunction_weight_init
(m)
dfd/timm/models/senet.py:59
↓ 1 callersFunctionadaptive_pool_feat_mult
(pool_type='avg')
dfd/timm/models/layers/adaptive_avgmax_pool.py:17
↓ 1 callersFunctionadd_weight_decay
(model, weight_decay=1e-5, skip_list=())
dfd/timm/optim/optim_factory.py:11
↓ 1 callersFunctionaugment_and_mix_transform
Create AugMix PyTorch transform :param config_str: String defining configuration of random augmentation. Consists of multiple sections separated
dfd/timm/data/auto_augment.py:771
↓ 1 callersFunctionaugmix_ops
(magnitude=10, hparams=None, transforms=None)
dfd/timm/data/auto_augment.py:698
↓ 1 callersFunctionauto_augment_policy
(name='v0', hparams=None)
dfd/timm/data/auto_augment.py:481
↓ 1 callersFunctionauto_augment_policy_original
(hparams)
dfd/timm/data/auto_augment.py:415
↓ 1 callersFunctionauto_augment_policy_originalr
(hparams)
dfd/timm/data/auto_augment.py:448
↓ 1 callersFunctionauto_augment_policy_v0
(hparams)
dfd/timm/data/auto_augment.py:348
↓ 1 callersFunctionauto_augment_policy_v0r
(hparams)
dfd/timm/data/auto_augment.py:381
↓ 1 callersFunctionauto_augment_transform
Create a AutoAugment transform :param config_str: String defining configuration of auto augmentation. Consists of multiple sections separate
dfd/timm/data/auto_augment.py:507
↓ 1 callersFunctionavg_pool2d_same
(x, kernel_size: List[int], stride: List[int], padding: List[int] = (0, 0), ceil_mode: boo
dfd/timm/models/layers/avg_pool2d_same.py:15
↓ 1 callersFunctionconvert_splitbn_model
Recursively traverse module and its children to replace all instances of ``torch.nn.modules.batchnorm._BatchNorm`` with `SplitBatchnorm2d`.
dfd/timm/models/layers/split_batchnorm.py:41
↓ 1 callersFunctioncreate_deepfake_transform
( input_size, is_training=False, use_prefetcher=False, color_jitter=0.4,
dfd/timm/data/transforms_factory.py:357
↓ 1 callersFunctioncreate_optimizer
(args, model, filter_bias_and_bn=True)
dfd/timm/optim/optim_factory.py:26
↓ 1 callersFunctioncreate_scheduler
(args, optimizer)
dfd/timm/scheduler/scheduler_factory.py:7
↓ 1 callersFunctioncreate_transform
( input_size, is_training=False, use_prefetcher=False, color_jitter=0.4,
dfd/timm/data/transforms_factory.py:484
↓ 1 callersMethodcumsum
(sequence)
dfd/timm/data/dataset.py:239
↓ 1 callersFunctiondel_file
(filename)
dfd/utils.py:69
↓ 1 callersFunctiondistorted_bounding_box_crop
Generates cropped_image using one of the bboxes randomly distorted. See `tf.image.sample_distorted_bounding_box` for more documentation. Arg
dfd/timm/data/tf_preprocessing.py:27
↓ 1 callersFunctiondownsample_avg
( in_channels, out_channels, kernel_size, stride=1, dilation=1, first_dilation=None, norm_layer=None)
dfd/timm/models/resnet.py:263
← previousnext →101–200 of 965, ranked by callers