MCPcopy Create free account

hub / github.com/TARTRL/Deepfake_Detection / functions

Functions965 in github.com/TARTRL/Deepfake_Detection

⨍ Functions 965◇ Types & classes 181
↓ 123 callersFunctionload_pretrained
(model, cfg=None, num_classes=1000, in_chans=3, filter_fn=None, strict=True)
dfd/timm/models/helpers.py:76
↓ 85 callersMethodformat
(self, record)
dfd/timm/utils.py:347
↓ 75 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/efficientnet.py:39
↓ 41 callersFunction_gen_efficientnet
Creates an EfficientNet model. Ref impl: https://github.com/tensorflow/tpu/blob/master/models/official/efficientnet/efficientnet_model.py Pap
dfd/timm/models/efficientnet.py:760
↓ 40 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/resnet.py:22
↓ 33 callersMethodfeat_mult
(self)
dfd/timm/models/layers/adaptive_avgmax_pool.py:91
↓ 24 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/gluon_resnet.py:20
↓ 21 callersFunctioncreate_conv2d
Select a 2d convolution implementation based on arguments Creates and returns one of torch.nn.Conv2d, Conv2dSame, MixedConv2d, or CondConv2d.
dfd/timm/models/layers/create_conv2d.py:11
↓ 14 callersFunctiondecode_arch_def
(arch_def, depth_multiplier=1.0, depth_trunc='ceil', experts_multiplier=1)
dfd/timm/models/efficientnet_builder.py:177
↓ 14 callersFunctionresolve_bn_args
(kwargs)
dfd/timm/models/efficientnet_blocks.py:22
↓ 14 callersMethodtransform
(self)
dfd/timm/data/dataset.py:651
↓ 12 callersMethod__init__
(self, stem_size, num_channels=42)
dfd/timm/models/nasnet.py:133
↓ 12 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/dla.py:23
↓ 11 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/mobilenetv3.py:22
↓ 11 callersFunction_create_model
(model_kwargs, default_cfg, pretrained=False)
dfd/timm/models/efficientnet.py:521
↓ 11 callersFunctionround_channels
Round number of filters based on depth multiplier.
dfd/timm/models/efficientnet_blocks.py:64
↓ 10 callersFunction_gen_mobilenet_v3
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:268
↓ 9 callersMethod__init__
(self)
dfd/timm/models/inception_v4.py:43
↓ 9 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/senet.py:25
↓ 9 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/hrnet.py:35
↓ 9 callersFunction_create_model
(variant, pretrained, model_kwargs)
dfd/timm/models/hrnet.py:741
↓ 8 callersMethod__init__
(self, in_chs, out_chs, kernel_size, stride=1, dilation=1, pad_type='', act_layer=nn.ReLU,
dfd/timm/models/efficientnet_blocks.py:114
↓ 8 callersFunctionconv_bn
(in_chs, out_chs, k=3, stride=1, padding=None, dilation=1)
dfd/timm/models/selecsls.py:56
↓ 8 callersMethodupdate_groups
(self, values)
dfd/timm/scheduler/scheduler.py:81
↓ 7 callersMethod__init__
(self, in_channels_left, out_channels_left, in_channels_right, out_channels_right, is_reducti
dfd/timm/models/pnasnet.py:232
↓ 7 callersMethod__init__
(self, scale=1.0, no_relu=False)
dfd/timm/models/inception_resnet_v2.py:198
↓ 7 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/res2net.py:20
↓ 7 callersFunction_check_args_tf
(kwargs)
dfd/timm/data/auto_augment.py:52
↓ 7 callersFunctiondrop_path
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for E
dfd/timm/models/layers/drop.py:84
↓ 7 callersMethodload_state_dict
(self, state_dict)
dfd/timm/optim/lookahead.py:66
↓ 7 callersMethodupdate
(self, val, n=1)
dfd/timm/utils.py:163
↓ 6 callersFunction_cfg
(url='')
dfd/timm/models/dpn.py:26
↓ 6 callersFunction_gen_efficientnet_condconv
Creates an EfficientNet-CondConv model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/condconv
dfd/timm/models/efficientnet.py:883
↓ 6 callersFunction_gen_efficientnet_edge
Creates an EfficientNet-EdgeTPU model Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/edgetpu
dfd/timm/models/efficientnet.py:854
↓ 6 callersFunction_gen_mixnet_m
Creates a MixNet Medium-Large model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet/mixnet Paper: https://ar
dfd/timm/models/efficientnet.py:946
↓ 6 callersFunctionmake_divisible
(v, divisor=8, min_value=None)
dfd/timm/models/efficientnet_blocks.py:55
↓ 6 callersMethodstate_dict
(self)
dfd/timm/optim/lookahead.py:52
↓ 6 callersMethodupdate
(self, model)
dfd/timm/utils.py:329
↓ 5 callersMethod__init__
(self, levels, channels, num_classes=1000, in_chans=3, cardinality=1, base_width=64, block=Dl
dfd/timm/models/dla.py:255
↓ 5 callersMethod__init__
Parameters ---------- block (nn.Module): Bottleneck class. - For SENet154: SEBottleneck - For SE-ResN
dfd/timm/models/senet.py:228
↓ 5 callersMethod__init__
(self, channels, spatial_kernel_size=7)
dfd/timm/models/layers/cbam.py:79
↓ 5 callersMethod__init__
(self, inplace: bool = False)
dfd/timm/models/layers/activations.py:100
↓ 5 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/selecsls.py:26
↓ 5 callersFunction_cfg
(url='', **kwargs)
dfd/timm/models/sknet.py:22
↓ 5 callersFunction_create_model
(variant, pretrained, model_kwargs)
dfd/timm/models/selecsls.py:158
↓ 5 callersFunction_parse_ksize
(ss)
dfd/timm/models/efficientnet_builder.py:13
↓ 5 callersFunction_randomly_negate
With 50% prob, negate the value
dfd/timm/data/auto_augment.py:175
↓ 5 callersFunctionefficientnet_init_weights
(model: nn.Module, init_fn=None)
dfd/timm/models/efficientnet_builder.py:578
↓ 5 callersFunctionresolve_se_args
(kwargs, in_chs, act_layer=None)
dfd/timm/models/efficientnet_blocks.py:40
↓ 4 callersMethod__init__
(self, small=False, num_init_features=64, k_r=96, groups=32, b=False, k_sec=(3, 4, 20, 3), in
dfd/timm/models/dpn.py:157
↓ 4 callersFunction_assert_default_kwargs
(kwargs)
dfd/timm/models/inception_v3.py:62
↓ 4 callersFunction_cfg
(url='')
dfd/timm/models/densenet.py:20
↓ 4 callersMethod_erase
(self, img, chan, img_h, img_w, dtype)
dfd/timm/data/random_erasing.py:61
↓ 4 callersFunction_gen_mnasnet_a1
Creates a mnasnet-a1 model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet Paper: https://arxiv.org/pdf/1807
dfd/timm/models/efficientnet.py:568
↓ 4 callersFunction_gen_mnasnet_b1
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:604
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, groups, reduction, stride=1, downsample_kernel_size=1, downs
dfd/timm/models/senet.py:347
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1, dilation=1, reduce_first=1, avg_down=False, down_k
dfd/timm/models/resnet.py:422
↓ 4 callersFunction_ntuple
(n)
dfd/timm/models/layers/helpers.py:10
↓ 4 callersFunction_pil_interp
(method)
dfd/timm/data/transforms.py:58
↓ 4 callersFunctioncheck_file
(filename)
dfd/utils.py:57
↓ 4 callersFunctioncreate_attn
(attn_type, channels, **kwargs)
dfd/timm/models/layers/create_attn.py:11
↓ 4 callersFunctionis_model
Check if a model name exists
dfd/timm/models/registry.py:67
↓ 4 callersFunctionis_model_in_modules
Check if a model exists within a subset of modules Args: model_name (str) - name of model to check module_names (tuple, list, set)
dfd/timm/models/registry.py:86
↓ 4 callersFunctionload_checkpoint
(model, checkpoint_path, use_ema=False, strict=True, ignore_keys=None)
dfd/timm/models/helpers.py:31
↓ 4 callersFunctionload_class_map
(filename, root='')
dfd/timm/data/dataset.py:62
↓ 4 callersFunctionmodel_entrypoint
Fetch a model entrypoint for specified model name
dfd/timm/models/registry.py:73
↓ 4 callersFunctionreduce_tensor
(tensor, n)
dfd/timm/utils.py:256
↓ 3 callersMethod__init__
(self, inplanes, planes, num_reps, stride=1, dilation=1, norm_layer=None, norm_kwargs=None, s
dfd/timm/models/gluon_xception.py:117
↓ 3 callersMethod__init__
(self, growth_rate=32, block_config=(6, 12, 24, 16), num_init_features=64, bn_size=4, drop_ra
dfd/timm/models/densenet.py:88
↓ 3 callersMethod_get_lr
(self, t)
dfd/timm/scheduler/tanh_lr.py:65
↓ 3 callersMethod_make_stage
(self, layer_config, num_inchannels, multi_scale_output=True)
dfd/timm/models/hrnet.py:651
↓ 3 callersMethod_make_transition_layer
(self, num_channels_pre_layer, num_channels_cur_layer)
dfd/timm/models/hrnet.py:609
↓ 3 callersFunctionadaptive_avgmax_pool2d
(x, output_size=1)
dfd/timm/models/layers/adaptive_avgmax_pool.py:24
↓ 3 callersFunctionget_condconv_initializer
(initializer, num_experts, expert_shape)
dfd/timm/models/layers/cond_conv2d.py:20
↓ 3 callersFunctionget_padding
(kernel_size: int, stride: int = 1, dilation: int = 1, **_)
dfd/timm/models/layers/padding.py:12
↓ 3 callersMethodget_params
Get parameters for ``crop`` for a random sized crop. Args: img (PIL Image): Image to be cropped. scale (tuple): range
dfd/timm/data/transforms.py:105
↓ 3 callersMethodstep
(self, closure=None)
dfd/timm/optim/radam.py:20
↓ 2 callersMethod__init__
(self, in_filters, out_filters, reps, strides=1, start_with_relu=True, grow_first=True)
dfd/timm/models/xception.py:67
↓ 2 callersMethod__init__
(self, block_args, num_classes=1000, num_features=1280, in_chans=3, stem_size=32, channel_mul
dfd/timm/models/efficientnet.py:260
↓ 2 callersMethod__init__
(self, block, layers, num_classes=1000, in_chans=3, cardinality=1, base_width=64, stem_width=
dfd/timm/models/resnet.py:349
↓ 2 callersMethod__init__
(self, output_size=1)
dfd/timm/models/layers/adaptive_avgmax_pool.py:53
↓ 2 callersMethod_add_noise
(self, lrs, t)
dfd/timm/scheduler/scheduler.py:87
↓ 2 callersFunction_create_model
(model_kwargs, default_cfg, pretrained=False)
dfd/timm/models/mobilenetv3.py:207
↓ 2 callersFunction_decode_and_center_crop
Crops to center of image with padding then scales image_size.
dfd/timm/data/tf_preprocessing.py:108
↓ 2 callersFunction_fixed_padding
(kernel_size, dilation)
dfd/timm/models/gluon_xception.py:76
↓ 2 callersFunction_gen_efficientnet_deepfake
Creates an EfficientNet model. Ref impl: https://github.com/tensorflow/tpu/blob/master/models/official/efficientnet/efficientnet_model.py Pap
dfd/timm/models/efficientnet.py:806
↓ 2 callersFunction_gen_mixnet_s
Creates a MixNet Small model. Ref impl: https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet/mixnet Paper: https://arxiv.org
dfd/timm/models/efficientnet.py:913
↓ 2 callersMethod_get_lr
(self, t)
dfd/timm/scheduler/cosine_lr.py:62
↓ 2 callersMethod_get_lr
(self, t)
dfd/timm/scheduler/step_lr.py:40
↓ 2 callersMethod_make_conv_level
(self, inplanes, planes, convs, stride=1, dilation=1)
dfd/timm/models/dla.py:289
↓ 2 callersMethod_make_layer
(self, block, inplanes, planes, blocks, stride=1)
dfd/timm/models/hrnet.py:636
↓ 2 callersMethod_normalize
(self, x)
dfd/timm/data/dataset.py:658
↓ 2 callersMethod_round_channels
(self, chs)
dfd/timm/models/efficientnet_builder.py:225
↓ 2 callersMethod_round_channels
(self, chs)
dfd/timm/models/efficientnet_builder.py:397
↓ 2 callersMethod_save
(self, save_path, model, optimizer, args, epoch, model_ema=None, metric=None, use_amp=False)
dfd/timm/utils.py:97
↓ 2 callersMethod_set_transforms
(self, x)
dfd/timm/data/dataset.py:644
↓ 2 callersFunction_split_channels
(num_chan, num_groups)
dfd/timm/models/layers/mixed_conv2d.py:14
↓ 2 callersFunctionaccuracy
Computes the precision@k for the specified values of k
dfd/timm/utils.py:170
↓ 2 callersFunctionadaptive_catavgmax_pool2d
(x, output_size=1)
dfd/timm/models/layers/adaptive_avgmax_pool.py:30
↓ 2 callersMethodbackward
(ctx, grad_output)
dfd/timm/models/layers/activations.py:70
next →1–100 of 965, ranked by callers