Functions — github.com/CDTrans/CDTrans

CodeHub MCPcopy Create free account

hub / github.com/CDTrans/CDTrans / functions

Functions356 in github.com/CDTrans/CDTrans

⨍ Functions 356◇ Types & classes 70

↓ 1 callersFunctionhard_example_mining

For each anchor, find the hardest positive and negative sample. Args: dist_mat: pytorch Variable, pair wise distance between samples, shape

loss/triplet_loss.py:51

↓ 1 callersMethodload_param_finetune

(self, model_path)

model/make_model.py:260

↓ 1 callersMethodload_param_finetune

(self, model_path)

model/make_model.py:383

↓ 1 callersFunctionmake_loss

(cfg, num_classes)

loss/make_loss.py:14

↓ 1 callersFunctionmake_optimizer

(cfg, model, center_criterion)

solver/make_optimizer.py:4

↓ 1 callersFunctionmkdir_if_missing

utils/iotools.py:14

↓ 1 callersFunctionnormalize

Normalizing to unit length along the specified dimension. Args: x: pytorch Variable Returns: x: pytorch Variable, same shape as in

loss/triplet_loss.py:5

↓ 1 callersFunctionobtain_label

(logger, val_loader, model, distance='cosine', threshold=0)

processor/processor_uda.py:32

↓ 1 callersMethodprint_dataset_statistics

(self, train, valid)

datasets/office_home.py:59

↓ 1 callersMethodprint_dataset_statistics

(self, train, test)

datasets/domainnet.py:64

↓ 1 callersMethodprint_dataset_statistics

(self, train, test)

datasets/office.py:64

↓ 1 callersFunctionrand_augment_ops

(magnitude=10, hparams=None, transforms=None)

datasets/autoaugment.py:603

↓ 1 callersMethodreset_parameters

loss/arcface.py:28

↓ 1 callersMethodreset_parameters

loss/arcface.py:62

↓ 1 callersMethodreset_parameters

loss/metric_learning.py:55

↓ 1 callersFunctionresize_pos_embed

(posemb, posemb_new, hight, width)

model/backbones/vit_pytorch.py:654

↓ 1 callersFunctionresize_pos_embed

(posemb, posemb_new, hight, width)

model/backbones/vit_pytorch_uda.py:566

↓ 1 callersFunctionresnet101_ibn_a

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

model/backbones/resnet_ibn_a.py:179

↓ 1 callersFunctionresnet50_ibn_a

Constructs a ResNet-50 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

model/backbones/resnet_ibn_a.py:168

↓ 1 callersMethodsample_list

datasets/sampler_ddp.py:171

↓ 1 callersFunctionse_resnet101_ibn_a

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

model/backbones/se_resnet_ibn_a.py:208

↓ 1 callersFunctionset_seed

↓ 1 callersFunctionshared_random_seed

Returns: int: a random number that is the same across all workers. If workers need a shared RNG, they can use this shared see

datasets/sampler_ddp.py:99

↓ 1 callersMethodtrack_ranking

(self, qf, gf, gallery_tids, unique_tids)

utils/metrics.py:333

↓ 1 callersMethodtrack_ranking

(self, qf, gf, gallery_tids, unique_tids)

utils/metrics.py:421

↓ 1 callersFunctiontransform

datasets/autoaugment.py:109

↓ 1 callersFunctionupdate_feat

(cfg, epoch, model, train_loader1,train_loader2, device,feat_memory1,feat_memory2, label_memory1,label_memory2

processor/processor_uda.py:96

datasets/preprocessing.py:24

datasets/autoaugment.py:337

datasets/autoaugment.py:500

datasets/autoaugment.py:616

datasets/autoaugment.py:753

(self, bn_feat, targets)

loss/arcface.py:65

(self, bn_feat, targets)

loss/metric_learning.py:58

(self, global_feat, labels, normalize_feature=False)

loss/triplet_loss.py:121

Method__getitem__

datasets/bases.py:78

utils/meter.py:4

(self, logger, dataset='office-home')

utils/metrics.py:131

(self, num_query, max_rank=50, feat_norm=True, reranking=False)

utils/metrics.py:190

(self, num_query, max_rank=50, feat_norm=True, reranking=False)

utils/metrics.py:234

(self, cfg, num_query, max_rank=50, feat_norm=False, reranking=False)

utils/metrics.py:263

(self, num_query, max_rank=50, feat_norm=True)

utils/metrics.py:400

(self, num_query, max_rank=50, feat_norm=True, reranking=False, reranking_track=False)

utils/metrics.py:470

(self, num_classes, camera_num, view_num, cfg, factory)

model/make_model.py:165

(self, num_classes, camera_num, view_num, cfg, factory)

model/make_model.py:272

(self, inplanes, planes, ibn=False, stride=1, downsample=None)

model/backbones/resnet_ibn_a.py:38

(self, last_stride, block, layers, frozen_stages=-1,num_classes=1000)

model/backbones/resnet_ibn_a.py:79

(self, inplanes, planes, stride=1, downsample=None, reduction=16)

model/backbones/se_resnet_ibn_a.py:33

(self, inplanes, planes, stride=1, downsample=None, ibn=False, reduction=16)

model/backbones/se_resnet_ibn_a.py:66

(self, last_stride,block, layers, frozen_stages=-1, num_classes=1000)

model/backbones/se_resnet_ibn_a.py:108

(self, drop_prob=None)

model/backbones/vit_pytorch.py:67

(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.)

model/backbones/vit_pytorch.py:141

(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0., dr

model/backbones/vit_pytorch.py:172

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768)

model/backbones/vit_pytorch.py:193

(self, backbone, img_size=224, feature_size=None, in_chans=3, embed_dim=768)

model/backbones/vit_pytorch.py:216

(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dim=768, depth=12, nu

model/backbones/vit_pytorch.py:249

(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dim=768, depth=12, nu

model/backbones/vit_pytorch.py:366

(self, img_size=224, patch_size=16, stride_size=20, in_chans=3, embed_dim=768)

model/backbones/vit_pytorch.py:488

(self, img_size=224, patch_size=16, stride_size=16, in_chans=3, num_classes=1000, embed_dim=768, depth=12,

model/backbones/vit_pytorch.py:529

(self, drop_prob=None)

model/backbones/vit_pytorch_uda.py:67

(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.)

model/backbones/vit_pytorch_uda.py:140

(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0., dr

model/backbones/vit_pytorch_uda.py:211

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768)

model/backbones/vit_pytorch_uda.py:245

(self, backbone, img_size=224, feature_size=None, in_chans=3, embed_dim=768)

model/backbones/vit_pytorch_uda.py:269

(self, img_size=224, patch_size=16, stride_size=20, in_chans=3, embed_dim=768)

model/backbones/vit_pytorch_uda.py:305

(self, img_size=224, patch_size=16, stride_size=20, in_chans=3, conv_channel= [24, 48, 96, 192], embed_dim=768

model/backbones/vit_pytorch_uda.py:344

(self, img_size=224, patch_size=16, stride_size=16, in_chans=3, num_classes=1000, embed_dim=768, depth=12,

model/backbones/vit_pytorch_uda.py:384

(self, channel, reduction=16)

model/backbones/se_module.py:5

(self, inplanes, planes, stride=1, downsample=None)

model/backbones/resnet.py:16

(self, inplanes, planes, stride=1, downsample=None)

model/backbones/resnet.py:48

(self, optimizer: torch.optim.Optimizer, param_group_field: str,

solver/scheduler.py:21

(self, optimizer: torch.optim.Optimizer, t_initial: int, t_

solver/cosine_lr.py:23

( self, optimizer, milestones, # steps gamma=0.1,

solver/lr_scheduler.py:16

(self, root_train='./datasets/reid_datasets/Corrected_Market1501', root_val='./datasets/reid_datasets/Correcte

datasets/office_home.py:21

(self, dataset, transform=None)

datasets/bases.py:71

(self, probability=0.5, sl=0.02, sh=0.4, r1=0.3, mean=(0.4914, 0.4822, 0.4465))

datasets/preprocessing.py:17

(self, root_train='./datasets/reid_datasets/Corrected_Market1501', root_val='./datasets/reid_datasets/Correcte

datasets/visda.py:21

(self, root_train='./datasets/reid_datasets/Corrected_Market1501', root_val='./datasets/reid_datasets/Correcte

datasets/domainnet.py:21

(self, root_train='./datasets/reid_datasets/Corrected_Market1501', root_val='./datasets/reid_datasets/Correcte

datasets/office.py:21

(self, root_train='./datasets/Corrected_Market1501', root_val='./datasets/Corrected_Market1501', verbose=True,

datasets/ourapi.py:18

(self, data_source, batch_size, num_instances)

datasets/sampler.py:17

(self, data_source, batch_size, num_instances)

datasets/sampler_ddp.py:121

(self, name, prob=0.5, magnitude=10, hparams=None)

datasets/autoaugment.py:319

datasets/autoaugment.py:497

(self, ops, num_layers=2, choice_weights=None)

datasets/autoaugment.py:611

(self, ops, alpha=1., width=3, depth=-1, blended=False)

datasets/autoaugment.py:703

(self, kernel_mul = 2.0, kernel_num = 5)

loss/mmd_loss.py:6

(self, num_classes=751, feat_dim=2048, use_gpu=True)

loss/center_loss.py:18

(self, in_features, num_classes, s=256, m=0.25)

loss/arcface.py:53

(self, num_classes, epsilon=0.1, use_gpu=True)

loss/softmax_loss.py:16

(self, margin=0.3, **kwargs)

loss/metric_learning.py:10

(self, in_features, num_classes, s=256, m=0.25)

loss/metric_learning.py:46

(self, in_features, out_features, s=30.0, m=0.30)

loss/metric_learning.py:134

(self, in_features, out_features, s=30.0, m=0.30)

loss/metric_learning.py:167

(self, margin=None, hard_factor=0.0)

loss/triplet_loss.py:113

datasets/sampler.py:39

datasets/sampler_ddp.py:147

datasets/bases.py:75

datasets/sampler.py:67

datasets/sampler_ddp.py:195

← previous next →101–200 of 356, ranked by callers