Functions — github.com/TPCD/DCCL

CodeHub MCPcopy Create free account

hub / github.com/TPCD/DCCL / functions

Functions480 in github.com/TPCD/DCCL

⨍ Functions 480◇ Types & classes 94

methods/partitioning/kmeans_subset.py:39

Method__enter__

project_utils/infomap_cluster_utils.py:26

(self, exc_type, exc_val, exc_tb)

project_utils/infomap_cluster_utils.py:30

Method__getitem__

(self, indices)

project_utils/data_utils.py:59

Method__getitem__

Args: index (int): Index Returns: tuple: (sample, target) where target is class_index of the target class.

data/pets.py:123

Method__getitem__

data/food.py:109

Method__getitem__

data/imagenet.py:19

Method__getitem__

data/data_utils.py:49

Method__getitem__

data/cifar.py:35

Method__getitem__

data/cub.py:118

Method__getitem__

Args: index (int): Index Returns: tuple: (sample, target) where target is class_index of the target class.

data/fgvc_aircraft.py:96

Method__getitem__

data/herbarium_19.py:19

Method__getitem__

Args: index (int): Index Returns: tuple: (sample, target) where target is class_index of the target class.

data/flower.py:125

Method__getitem__

data/stanford_cars.py:51

Method__getitem__

methods/clustering/feature_vector_dataset.py:36

(self, num_features, num_samples, temp=0.05, momentum=0.2, use_hard=False, args=None)

project_utils/cluster_memory_utils.py:85

(self, fields=None, win=None, env=None, opts={}, port=8097, server="localhost")

project_utils/visualization_utils.py:860

(self, envs=None, port=8097, server="localhost")

project_utils/visualization_utils.py:903

Args: fields: Currently unused plot_type: The name of the plot type, in Visdom Examples:

project_utils/visualization_utils.py:917

Args: fields: Currently unused plot_type: The name of the plot type, in Visdom

project_utils/visualization_utils.py:950

Multiple lines can be added to the same plot with the "name" attribute (see example) Args: fields: Currently

project_utils/visualization_utils.py:1003

(self, fields=None, win=None, env=None, opts={}, update_type=valid_update_types[0], port=8097

project_utils/visualization_utils.py:1077

(self, name='task', verbose=True)

project_utils/infomap_cluster_utils.py:22

(self, feats, k, knn_method='faiss-cpu', device=0, verbose=True)

project_utils/infomap_cluster_utils.py:419

(self, base_transform, n_views=2)

project_utils/contrastive_utils.py:158

(self, device, temperature=0.07, contrast_mode='all', base_temperature=0.07, )

project_utils/contrastive_utils.py:171

(self, dataset, root=None, transform=None)

project_utils/data_utils.py:47

(self, warmup_epochs, *args, **kwargs)

project_utils/schedulers.py:88

/path/to/log_file.txt

project_utils/cluster_and_log_utils.py:123

project_utils/general_utils.py:14

(self, length, save_path=None)

project_utils/general_utils.py:212

(self, threshold=5e-4, patience_epochs=5, mode='min', threshold_mode='rel')

project_utils/general_utils.py:306

(self, data_source, num_instances=4)

project_utils/sampler.py:47

(self, data_source, num_instances=4)

project_utils/sampler.py:110

project_utils/cluster_utils.py:120

project_utils/cluster_utils.py:137

(self, vit_backbone_model, grad_from_block=11)

model/attribute_transformer.py:13

(self, vit_backbone_model, grad_from_block=11)

model/attribute_transformer.py:88

(self, vit_backbone_model, num_attribute=28, feat_channal=197, grad_from_block=11)

model/attribute_transformer.py:201

(self, vit_backbone_model, num_attribute=28, feat_channal=197, grad_from_block=11)

model/attribute_transformer.py:235

(self, vit_backbone_model, num_attribute=28, feat_channal=197, grad_from_block=11)

model/attribute_transformer.py:269

(self, vit_backbone_model, num_attribute=28, feat_channal=197, grad_from_block=11)

model/attribute_transformer.py:311

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11)

model/attribute_transformer.py:357

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11)

model/attribute_transformer.py:408

(self, input_feature_dim, norm_type='bn')

model/attribute_transformer.py:458

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11)

model/attribute_transformer.py:481

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11)

model/attribute_transformer.py:529

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11)

model/attribute_transformer.py:576

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11)

model/attribute_transformer.py:621

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11)

model/attribute_transformer.py:665

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11)

model/attribute_transformer.py:706

(self, vit_backbone_model, num_attribute=28, attribute_feat_channal=8, grad_from_block=11, device=None)

model/attribute_transformer.py:735

(self, hidden_dim, device=torch.cuda.device('cuda'))

model/attribute_transformer.py:784

(self, vit_backbone_model, dict_attribute, grad_from_block=11)

model/attribute_transformer.py:845

(self, vit_backbone_model, dict_attribute, grad_from_block=11)

model/attribute_transformer.py:882

(self, dict_attribute, in_dim, projected_dim, use_bn=False, use_independent_projection=True)

model/attribute_classifier.py:9

(self, in_dim, out_dim, use_bn=False, norm_last_layer=True, nlayers=3, hidden_dim=2048, bottleneck_dim=256)

model/attribute_classifier.py:85

(self, device, hidden_dim, sparse_inputs=False, act=nn.Tanh(), bias=True, dropout=0.6)

model/meta_graph.py:17

(self, hidden_dim, input_dim, sigma=2.0, proto_graph_vertex_num=16, meta_graph_vertex_num=128)

model/meta_graph.py:134

(self, drop_prob=None)

model/vision_transformer.py:40

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

model/vision_transformer.py:68

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

model/vision_transformer.py:95

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

model/vision_transformer.py:120

(self, img_size=[224], patch_size=16, in_chans=3, num_classes=0, embed_dim=768, depth=12, num

model/vision_transformer.py:137

(self, in_dim, out_dim, use_bn=False, norm_last_layer=True, nlayers=3, hidden_dim=2048, bottleneck_dim=256)

model/vision_transformer.py:265

(self, base_vit, num_classes=200)

model/vision_transformer.py:303

(self, dict_attribute, in_dim, projected_dim, norm_type='bn', use_independent_projection=True)

model/vision_transformer.py:331

(self, dict_attribute, in_dim, projected_dim, out_dim, norm_type='bn')

model/vision_transformer.py:409

(self, dict_attribute, in_dim, projected_dim, norm_type='bn', use_independent_projection=True)

model/vision_transformer.py:471

(self, dict_attribute, in_dim, projected_dim, norm_type='bn', use_independent_projection=True)

model/vision_transformer.py:548

(self, in_dim, class_num)

model/vision_transformer.py:653

(self, dict_attribute, in_dim, projected_dim, norm_type='bn', use_independent_projection=True)

model/vision_transformer.py:675

(self, dict_attribute, in_dim)

model/vision_transformer.py:750

(self, dict_attribute, in_dim)

model/vision_transformer.py:781

(self, dict_attribute, in_dim)

model/vision_transformer.py:816

( self, root: str, split: str = "trainval", target_types: Union[Sequence[str],

data/pets.py:58

( self, root: str, split: str = "train", transform: Optional[Callable] = None,

data/food.py:56

(self, root, transform)

data/imagenet.py:13

(self, labelled_dataset, unlabelled_dataset=None)

data/data_utils.py:20

(self, *args, **kwargs)

data/cifar.py:30

(self, root, train=True, transform=None, target_transform=None, loader=default_loader, download=True)

(self, root, class_type='variant', split='train', transform=None, target_transform=None, load

data/fgvc_aircraft.py:64

(self, *args, **kwargs)

data/herbarium_19.py:12

( self, root: str, split: str = "train", transform: Optional[Callable] = None,

data/flower.py:65

(self, train=True, limit=0, data_dir=car_root, transform=None, metas=meta_default_path)

data/stanford_cars.py:20

(self, alphastd, eigval, eigvec)

data/augmentations/randaugment.py:232

data/augmentations/randaugment.py:254

(self, n, m, args=None)

data/augmentations/randaugment.py:276

(self, temperature=0.07, contrast_mode='all', base_temperature=0.07)

methods/representation_learning/representation_learning.py:39

(self, base_transform, n_views=2)

methods/representation_learning/representation_learning.py:129

(self, k=3, tolerance=1e-4, max_iterations=100, init='k-means++', n_init=10, random_state=Non

methods/clustering/faster_mix_k_means_pytorch.py:49

Dataset loads feature vectors instead of images :param base_dataset: Dataset from which images would come :param feature_root

methods/clustering/feature_vector_dataset.py:12

(self, base_transform, n_views=2)

methods/partitioning/subset_len.py:34

(self, base_transform, n_views=2)

methods/partitioning/kmeans_subset.py:35

project_utils/sampler.py:32

project_utils/sampler.py:68

project_utils/sampler.py:132

project_utils/data_utils.py:23

project_utils/data_utils.py:56

project_utils/sampler.py:29

← previous next →201–300 of 480, ranked by callers