Functions — github.com/ChongQingNoSubway/SelfReg-UNet

hub / github.com/ChongQingNoSubway/SelfReg-UNet / functions

Functions3,840 in github.com/ChongQingNoSubway/SelfReg-UNet

⨍ Functions 3,840◇ Types & classes 731

↓ 3 callersMethod__init__

( self, dim, num_heads=8, qkv_bias=False, attn_drop=0., proj_drop=0., locality_strength=1.)

src/train_acdc/lib/models_timm/convit.py:64

↓ 3 callersMethod__init__

( self, in_chs: int, out_chs: Optional[int] = None, kernel_siz

src/train_acdc/lib/models_timm/mobilevit.py:233

↓ 3 callersMethod__init__

(self, pool_size=3)

src/train_acdc/lib/models_timm/poolformer.py:84

↓ 3 callersMethod__init__

( self, cfg: RegNetCfg, in_chans=3, num_classes=1000, output_stride=32, global_pool='avg',

src/train_acdc/lib/models_timm/regnet.py:380

↓ 3 callersMethod__init__

( self, in_channel, out_channels, kernel_size, stride=1, padding=None, dilation=1, gro

src/train_acdc/lib/models_timm/layers/std_conv.py:32

↓ 3 callersMethod__init__

(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, bias=True, drop=0.)

src/train_acdc/lib/models_timm/layers/mlp.py:13

↓ 3 callersMethod__init__

(self, output_size=1)

src/train_acdc/lib/models_timm/layers/adaptive_avgmax_pool.py:62

↓ 3 callersMethod__init__

(self, in_channels, out_channels, bilinear=True)

src/train_acdc/unet/unet_parts.py:45

↓ 3 callersMethod__init__

(self, dim, factor, heads = 8, dim_head = 64, dropout = 0.)

src/train_acdc/modelsHiFormer/Encoder.py:13

↓ 3 callersMethod__init__

(self, optimizer, curr_iter, max_iter, lr_decay)

src/train_synase/utils/misc.py:101

↓ 3 callersMethod__init__

(self, in_channels, out_channels, bilinear=True)

src/train_synase/unet/unet_parts.py:45

↓ 3 callersMethod__init__

(self, dim, factor, heads = 8, dim_head = 64, dropout = 0.)

src/train_synase/modelsHiFormer/Encoder.py:13

↓ 3 callersFunction_cfg

(url='', **kwargs)

src/train_acdc/lib/models_timm/ghostnet.py:25

↓ 3 callersFunction_cfg

(url='', **kwargs)

src/train_acdc/lib/models_timm/efficientformer.py:26

↓ 3 callersFunction_cfg

(url='', **kwargs)

src/train_acdc/lib/models_timm/convmixer.py:13

↓ 3 callersFunction_cfg

(url='', **kwargs)

src/train_acdc/lib/models_timm/convit.py:41

↓ 3 callersFunction_cfg

(url='', **kwargs)

src/train_acdc/lib/models_timm/sequencer.py:23

↓ 3 callersFunction_create_convit

(variant, pretrained=False, **kwargs)

src/train_acdc/lib/models_timm/convit.py:338

↓ 3 callersFunction_create_convmixer

(variant, pretrained=False, **kwargs)

src/train_acdc/lib/models_timm/convmixer.py:106

↓ 3 callersFunction_create_efficientformer

(variant, pretrained=False, **kwargs)

src/train_acdc/lib/models_timm/efficientformer.py:515

↓ 3 callersFunction_create_ghostnet

Constructs a GhostNet model

src/train_acdc/lib/models_timm/ghostnet.py:243

↓ 3 callersFunction_create_sequencer2d

(variant, pretrained=False, **kwargs)

src/train_acdc/lib/models_timm/sequencer.py:359

↓ 3 callersFunction_gen_efficientnetv2_xl

Creates an EfficientNet-V2 Xtra-Large model Ref impl: https://github.com/google/automl/tree/master/efficientnetv2 Paper: `EfficientNetV2: Sm

src/train_acdc/lib/models_timm/efficientnet.py:1115

↓ 3 callersFunction_gen_fbnetv3

FBNetV3 Paper: `FBNetV3: Joint Architecture-Recipe Search using Predictor Pretraining` - https://arxiv.org/abs/2006.02049 FIXME untes

src/train_acdc/lib/models_timm/mobilenetv3.py:432

↓ 3 callersFunction_get_feature_info

(net, out_indices)

src/train_acdc/lib/models_timm/features.py:135

↓ 3 callersMethod_make_stage

(self, layer_config, num_in_chs, multi_scale_output=True)

src/train_acdc/lib/models_timm/hrnet.py:655

↓ 3 callersMethod_make_transition_layer

(self, num_channels_pre_layer, num_channels_cur_layer)

src/train_acdc/lib/models_timm/hrnet.py:613

↓ 3 callersFunction_mobilevitv2_block

(d, c, s, transformer_depth, patch_size=2, br=2.0, transformer_br=0.5)

src/train_acdc/lib/models_timm/mobilevit.py:118

↓ 3 callersFunctionadaptive_avgmax_pool2d

(x, output_size=1)

src/train_acdc/lib/models_timm/layers/adaptive_avgmax_pool.py:24

↓ 3 callersFunctionapply_rot_embed

(x: torch.Tensor, sin_emb, cos_emb)

src/train_acdc/lib/models_timm/layers/pos_embed.py:148

↓ 3 callersFunctionconv1x1

(cin, cout, stride=1, bias=False)

src/train_acdc/networks_trans/vit_seg_modeling_resnet_skip.py:33

↓ 3 callersFunctionconv1x1

(cin, cout, stride=1, bias=False)

src/train_synase/networks_trans/vit_seg_modeling_resnet_skip.py:33

↓ 3 callersFunctioncreate_aa

(aa_layer, channels, stride=2, enable=True)

src/train_acdc/lib/models_timm/resnet.py:328

↓ 3 callersFunctionfast_group_norm

( x: torch.Tensor, num_groups: int, weight: Optional[torch.Tensor] = None, bias: Optional[torc

src/train_acdc/lib/models_timm/layers/fast_norm.py:34

↓ 3 callersMethodflops

(self)

src/train_acdc/network/swin_transformer_unet_skip_expand_decoder_sys.py:451

↓ 3 callersMethodflops

(self)

src/train_synase/networks/swin_transformer_unet_skip_expand_decoder_sys.py:451

↓ 3 callersFunctionget_condconv_initializer

(initializer, num_experts, expert_shape)

src/train_acdc/lib/models_timm/layers/cond_conv2d.py:21

↓ 3 callersFunctionget_config

Get a yacs CfgNode object with default values.

src/train_synase/config.py:222

↓ 3 callersMethodget_output

(self, device)

src/train_acdc/lib/models_timm/features.py:115

↓ 3 callersFunctioninference

(args, model, testloader, test_save_path=None)

src/train_acdc/test_ACDC.py:16

↓ 3 callersFunctionis_dist_avail_and_initialized

()

src/train_acdc/levit/utils.py:188

↓ 3 callersFunctionis_dist_avail_and_initialized

()

src/train_synase/levit/utils.py:188

↓ 3 callersMethodload_from

(self, config)

src/train_acdc/network/vision_transformer.py:53

↓ 3 callersFunctionmanual_var

(x, dim: Union[int, Sequence[int]], diff_sqm: bool = False)

src/train_acdc/lib/models_timm/layers/evo_norm.py:52

↓ 3 callersFunctionoverride_kwargs

Override model level attn/self-attn/block kwargs w/ block level NOTE: kwargs are NOT merged across levels, block_kwargs will fully replace model

src/train_acdc/lib/models_timm/byobnet.py:1361

↓ 3 callersFunctionpixel_freq_bands

( num_bands: int, max_freq: float = 224., linear_bands: bool = True, dtype: to

src/train_acdc/lib/models_timm/layers/pos_embed.py:8

↓ 3 callersFunctionpowerset

Returns all the subsets of this set. This is a generator.

src/train_acdc/utils/utils.py:24

↓ 3 callersFunctionrandom_rot_flip

(image, label)

src/train_acdc/utils/dataset_ACDC.py:14

↓ 3 callersFunctionrandom_rot_flip

(image, label)

src/train_synase/utils/dataset_ACDC.py:14

↓ 3 callersFunctionrandom_rot_flip

(image, label)

src/train_synase/datasets/dataset_synapse.py:30

↓ 3 callersFunctionrandom_rotate

(image, label)

src/train_acdc/utils/dataset_ACDC.py:24

↓ 3 callersFunctionrandom_rotate

(image, label)

src/train_synase/utils/dataset_ACDC.py:24

↓ 3 callersFunctionrandom_rotate

(image, label)

src/train_synase/datasets/dataset_synapse.py:40

↓ 3 callersFunctionresolve_pretrained_cfg

(variant: str, pretrained_cfg=None)

src/train_acdc/lib/models_timm/helpers.py:482

↓ 3 callersFunctionrot

(x)

src/train_acdc/lib/models_timm/layers/pos_embed.py:144

↓ 3 callersFunctionsave_files

(files, folder)

src/train_acdc/utils/lesion/make_dataset.py:52

↓ 3 callersFunctionsave_files

(files, folder)

src/train_synase/utils/lesion/make_dataset.py:52

↓ 3 callersMethodstep

(self)

src/train_acdc/utils/misc.py:110

↓ 3 callersFunctiontest_single_volume

(image, label, net, classes, patch_size=[256, 256], test_save_path=None, case=None, z_spacing=1, class_names=N

src/train_synase/utils/utils.py:274

↓ 3 callersMethodtrain

(self, mode=True)

src/train_synase/levit/LeViTUNet128s.py:196

↓ 3 callersMethodtranspose_for_scores

(self, x)

src/train_acdc/networks_trans/vit_seg_modeling.py:68

↓ 3 callersMethodtranspose_for_scores

(self, x)

src/train_synase/networks_trans/vit_seg_modeling.py:68

↓ 2 callersFunctionBuild_LeViT_UNet_128s

(num_classes=4, distillation=True, pretrained=False, fuse=False)

src/train_acdc/levit/LeViTUNet128s.py:31

↓ 2 callersMethod__init__

(self, in_channels, out_channels, reps, strides=1, start_with_relu=True, grow_first=True)

src/train_acdc/lib/models_timm/xception.py:66

↓ 2 callersMethod__init__

(self, inplanes, planes, stride=1, dilation=1, start_with_relu=True, norm_layer=None)

src/train_acdc/lib/models_timm/gluon_xception.py:68

↓ 2 callersMethod__init__

( self, cfgs, num_classes=1000, width=1.0, in_chans=3, output_stride=32, global_pool='avg', drop_r

src/train_acdc/lib/models_timm/ghostnet.py:136

↓ 2 callersMethod__init__

(self, cfg, in_chans=3, num_classes=1000, global_pool='avg', drop_rate=0.0, head='classification')

src/train_acdc/lib/models_timm/hrnet.py:509

↓ 2 callersMethod__init__

( self, layers, in_chans=3, num_classes=1000, widt

src/train_acdc/lib/models_timm/tresnet.py:159

↓ 2 callersMethod__init__

( self, in_chans=3, num_classes=1000, global_pool='avg',

src/train_acdc/lib/models_timm/convnext.py:269

↓ 2 callersMethod__init__

( self, block, layers, num_classes=1000, in_chans=3, output_stride=32, global_pool='avg',

src/train_acdc/lib/models_timm/resnet.py:609

↓ 2 callersMethod__init__

(self, in_channels, use_scale=True, rd_ratio=1/8, rd_channels=None, rd_divisor=8, **kwargs)

src/train_acdc/lib/models_timm/layers/non_local_attn.py:23

↓ 2 callersMethod__init__

( self, channels, rd_ratio=1. / 16, rd_channels=None, rd_divisor=8, add_maxpool=False,

src/train_acdc/lib/models_timm/layers/squeeze_excite.py:28

↓ 2 callersMethod__init__

(self, embed_len_decoder: int)

src/train_acdc/lib/models_timm/layers/ml_decoder.py:93

↓ 2 callersMethod__init__

(self, block_size=4)

src/train_acdc/lib/models_timm/layers/space_to_depth.py:6

↓ 2 callersMethod_calc_window_shift

(self, target_window_size)

src/train_acdc/lib/models_timm/swin_transformer_v2_cr.py:360

↓ 2 callersFunction_cfg

(url='', **kwargs)

src/train_acdc/lib/pyramid_vig.py:19

↓ 2 callersFunction_cfg

(url='', **kwargs)

src/train_acdc/lib/models_timm/visformer.py:24

↓ 2 callersFunction_cfg

(url='', **kwargs)

src/train_acdc/lib/models_timm/tnt.py:23

↓ 2 callersMethod_collect

(self, x)

src/train_acdc/lib/models_timm/features.py:200

↓ 2 callersFunction_create_fc

(num_features, num_classes, use_conv=False)

src/train_acdc/lib/models_timm/layers/classifier.py:22

↓ 2 callersFunction_create_inception_resnet_v2

(variant, pretrained=False, **kwargs)

src/train_acdc/lib/models_timm/inception_resnet_v2.py:364

↓ 2 callersFunction_create_pool

(num_features, num_classes, pool_type='avg', use_conv=False)

src/train_acdc/lib/models_timm/layers/classifier.py:11

↓ 2 callersFunction_create_tnt

(variant, pretrained=False, **kwargs)

src/train_acdc/lib/models_timm/tnt.py:278

↓ 2 callersFunction_create_visformer

(variant, pretrained=False, default_cfg=None, **kwargs)

src/train_acdc/lib/models_timm/visformer.py:338

↓ 2 callersFunction_download_from_hf

(model_id: str, filename: str)

src/train_acdc/lib/models_timm/hub.py:80

↓ 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

src/train_acdc/lib/models_timm/efficientnet.py:1145

↓ 2 callersMethod_make_attention_mask

Method generates the attention mask used in shift case.

src/train_acdc/lib/models_timm/swin_transformer_v2_cr.py:365

↓ 2 callersMethod_make_conv_level

(self, inplanes, planes, convs, stride=1, dilation=1)

src/train_acdc/lib/models_timm/dla.py:308

↓ 2 callersMethod_make_head

(self, pre_stage_channels, incre_only=False)

src/train_acdc/lib/models_timm/hrnet.py:575

↓ 2 callersMethod_make_layer

(self, block, inplanes, planes, blocks, stride=1)

src/train_acdc/lib/models_timm/hrnet.py:640

↓ 2 callersMethod_make_pair_wise_relative_positions

Method initializes the pair-wise relative positions to compute the positional biases.

src/train_acdc/lib/models_timm/swin_transformer_v2_cr.py:194

↓ 2 callersFunction_module_list

(module, flatten_sequential=False)

src/train_acdc/lib/models_timm/features.py:121

↓ 2 callersMethod_pad

(self, img, mask)

src/train_acdc/utils/joint_transforms.py:163

↓ 2 callersMethod_pad

(self, img, mask)

src/train_acdc/utils/joint_transforms.py:208

↓ 2 callersMethod_pad

(self, img, mask)

src/train_synase/utils/joint_transforms.py:163

↓ 2 callersMethod_pad

(self, img, mask)

src/train_synase/utils/joint_transforms.py:208

↓ 2 callersFunction_resolve_pretrained_source

(pretrained_cfg)

src/train_acdc/lib/models_timm/helpers.py:134

↓ 2 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

src/train_acdc/lib/models_timm/efficientnet_builder.py:192

↓ 2 callersFunction_split_channels

(num_chan, num_groups)

src/train_acdc/lib/models_timm/layers/mixed_conv2d.py:14

↓ 2 callersFunction_trunc_normal_

(tensor, mean, std, a, b)

src/train_acdc/lib/models_timm/layers/weight_init.py:8

← previous next →301–400 of 3,840, ranked by callers