Functions — github.com/Haochen-Wang409/HPM

hub / github.com/Haochen-Wang409/HPM / functions

Functions186 in github.com/Haochen-Wang409/HPM

⨍ Functions 186◇ Types & classes 24

↓ 104 callersFunctionprint

(*args, **kwargs)

util/misc.py:175

↓ 14 callersMethodload_state_dict

(self, state_dict)

util/misc.py:275

↓ 12 callersMethodstate_dict

(self)

util/misc.py:272

↓ 11 callersMethodupdate

(self, **kwargs)

util/misc.py:90

↓ 7 callersFunctionprint

(*args, **kwargs)

util/utils.py:174

↓ 6 callersMethod__init__

(self, embed_dim: int, # vision image_resolution: int,

models_clip.py:251

↓ 6 callersFunctionget_2d_sincos_pos_embed

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/

util/pos_embed.py:17

↓ 5 callersMethodload_state_dict

(self, state_dict)

util/utils.py:294

↓ 4 callersMethod_make_layer

(self, planes, blocks, stride=1)

models_clip.py:136

↓ 4 callersFunctionbuild_dataset

(is_train, args)

util/datasets.py:47

↓ 4 callersFunctionevaluate

(data_loader, model, device)

engine_finetune.py:102

↓ 4 callersMethodlog_every

(self, iterable, print_freq, header=None)

util/misc.py:122

↓ 3 callersFunctioninterpolate_pos_embed

(model, checkpoint_model)

util/pos_embed.py:72

↓ 3 callersFunctionis_dist_avail_and_initialized

()

util/misc.py:186

↓ 3 callersFunctionis_dist_avail_and_initialized

()

util/utils.py:185

↓ 3 callersMethodstate_dict

(self)

util/utils.py:291

↓ 3 callersMethodsynchronize_between_processes

(self)

util/misc.py:115

↓ 2 callersMethodadd_meter

(self, name, meter)

util/misc.py:119

↓ 2 callersFunctionbuild_model

(state_dict: dict)

models_clip.py:406

↓ 2 callersFunctionextract_features

(model, data_loader, use_cuda=True)

main_knn.py:105

↓ 2 callersMethodforward_decoder

(self, x, mask)

models_mae_learn_feature_loss.py:190

↓ 2 callersMethodforward_features

(self, x, mask=None)

models_vit.py:33

↓ 2 callersMethodforward_loss

imgs: [N, 3, H, W] pred: [N, mask, p*p*3] mask: [N, L], 0 is keep, 1 is remove,

models_mae.py:198

↓ 2 callersFunctionget_1d_sincos_pos_embed_from_grid

embed_dim: output dimension for each position pos: a list of positions to be encoded: size (M,) out: (M, D)

util/pos_embed.py:46

↓ 2 callersFunctionget_world_size

()

util/misc.py:194

↓ 2 callersFunctionnorm_cdf

(x)

util/utils.py:366

↓ 2 callersFunctionsetup_for_distributed

This function disables printing when not in master process

util/misc.py:169

↓ 2 callersFunctionsetup_for_distributed

This function disables printing when not in master process

util/utils.py:168

↓ 2 callersMethodstep

(self)

util/lars.py:20

↓ 2 callersFunctiontrain_one_epoch

(model: torch.nn.Module, criterion: torch.nn.Module, data_loader: Iterable, optimizer: tor

engine_finetune.py:24

↓ 2 callersFunctiontrunc_normal_

(tensor, mean=0., std=1., a=-2., b=2.)

util/utils.py:396

↓ 2 callersMethodupdate

(self, value, n=1)

util/misc.py:36

↓ 2 callersMethodupdate

(self, value, n=1)

util/utils.py:35

↓ 1 callersFunction_no_grad_trunc_normal_

(tensor, mean, std, a, b)

util/utils.py:364

↓ 1 callersMethodattention

(self, x: torch.Tensor)

models_clip.py:192

↓ 1 callersMethodbuild_attention_mask

(self)

models_clip.py:335

↓ 1 callersFunctionbuild_transform

(is_train, args)

util/datasets.py:60

↓ 1 callersFunctionconvert_weights

Convert applicable model parameters to fp16

models_clip.py:382

↓ 1 callersMethodencode_image

(self, image)

models_clip.py:347

↓ 1 callersMethodencode_text

(self, text)

models_clip.py:350

↓ 1 callersMethodforward

(self, image, text)

models_clip.py:365

↓ 1 callersMethodforward_decoder

(self, x, mask)

models_mae.py:169

↓ 1 callersMethodforward_decoder

(self, x, mask)

models_mae_learn_loss.py:191

↓ 1 callersMethodforward_encoder

(self, x, mask)

models_mae.py:131

↓ 1 callersMethodforward_encoder

(self, x, mask)

models_mae_learn_loss.py:154

↓ 1 callersMethodforward_encoder

(self, x, mask)

models_mae_learn_feature_loss.py:153

↓ 1 callersFunctionforward_features

(model, x, model_type)

engine_pretrain.py:163

↓ 1 callersFunctionforward_features_clip

(model, x)

engine_pretrain.py:187

↓ 1 callersFunctionforward_features_dino

(model, x)

engine_pretrain.py:171

↓ 1 callersMethodforward_learning_loss

loss_pred: [N, L, 1] mask: [N, L], 0 is keep, 1 is remove, loss_target: [N, L]

models_mae_learn_loss.py:298

↓ 1 callersMethodgenerate_mask

(self, loss_pred, mask_ratio=0.75, images=None, guide=True, epoch=0, total_epoch=200)

models_mae_learn_loss.py:259

↓ 1 callersFunctionget_2d_sincos_pos_embed_from_grid

(embed_dim, grid)

util/pos_embed.py:35

↓ 1 callersFunctionget_args_parser

()

main_finetune.py:42

↓ 1 callersFunctionget_args_parser

()

main_knn.py:28

↓ 1 callersFunctionget_args_parser

()

main_pretrain.py:43

↓ 1 callersFunctionget_args_parser

()

main_linprob.py:39

↓ 1 callersFunctionget_grad_norm_

(parameters, norm_type: float = 2.0)

util/misc.py:279

↓ 1 callersFunctionget_grad_norm_

(parameters, norm_type: float = 2.0)

util/utils.py:298

↓ 1 callersFunctionget_layer_id_for_vit

Assign a parameter with its layer id Following BEiT: https://github.com/microsoft/unilm/blob/master/beit/optim_factory.py#L33

util/lr_decay.py:63

↓ 1 callersFunctionget_rank

()

util/misc.py:200

↓ 1 callersFunctionget_rank

()

util/utils.py:199

↓ 1 callersFunctionget_world_size

()

util/utils.py:193

↓ 1 callersMethodinitialize_parameters

(self)

models_clip.py:306

↓ 1 callersMethodinitialize_weights

(self)

models_mae.py:70

↓ 1 callersMethodinitialize_weights

(self)

models_mae_learn_loss.py:91

↓ 1 callersMethodinitialize_weights

(self)

models_mae_learn_feature_loss.py:90

↓ 1 callersFunctionis_main_process

()

util/misc.py:206

↓ 1 callersFunctionis_main_process

()

util/utils.py:205

↓ 1 callersFunctionknn_classifier

(train_features, train_labels, test_features, test_labels, k, T, num_classes=1000)

main_knn.py:154

↓ 1 callersFunctionmain

(args)

main_finetune.py:158

↓ 1 callersFunctionmain

(args)

main_knn.py:201

↓ 1 callersFunctionmain

(args)

main_pretrain.py:131

↓ 1 callersFunctionmain

↓ 1 callersMethodpatchify

imgs: (N, 3, H, W) x: (N, L, patch_size**2 *3)

models_mae.py:102

↓ 1 callersMethodpatchify

imgs: (N, 3, H, W) x: (N, L, patch_size**2 *3)

models_mae_learn_loss.py:125

↓ 1 callersFunctionsave_on_master

(*args, **kwargs)

util/misc.py:210

↓ 1 callersFunctionsave_on_master

(*args, **kwargs)

util/utils.py:209

↓ 1 callersFunctiontrain_one_epoch

(model: torch.nn.Module, data_loader: Iterable, optimizer: torch.optim.Optimizer,

engine_pretrain.py:22

↓ 1 callersMethodupdate

mask_transform.py:116

Method__call__

(self, loss, optimizer, clip_grad=5., parameters=None, create_graph=False, update_grad=True, retain_graph=Fals

util/misc.py:256

Method__call__

(self, loss, optimizer, clip_grad=None, parameters=None, create_graph=False, update_grad=True)

(self, input_size, mask_ratio, regular=False, block=False)

mask_transform.py:18

Method__init__

(self, args, is_train=True)

mask_transform.py:84

Method__init__

(self, global_pool=False, **kwargs)

models_vit.py:22

Method__init__

(self, inplanes, planes, stride=1)

models_clip.py:20

Method__init__

(self, spacial_dim: int, embed_dim: int, num_heads: int, output_dim: int = None)

models_clip.py:66

Method__init__

(self, layers, output_dim, heads, input_resolution=224, width=64)

models_clip.py:109

Method__init__

(self, d_model: int, n_head: int, attn_mask: torch.Tensor = None)

models_clip.py:179

Method__init__

(self, width: int, layers: int, heads: int, attn_mask: torch.Tensor = None)

models_clip.py:203

Method__init__

(self, input_resolution: int, patch_size: int, width: int, layers: int, heads: int, output_dim: int)

models_clip.py:214

Method__init__

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=1024, depth=24, num_heads=16,

models_mae.py:24

Method__init__

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=1024, depth=24, num_heads=16,

models_mae_learn_loss.py:28

Method__init__

(self, img_size=224, patch_size=16, in_chans=3, embed_dim=1024, depth=24, num_heads=16,

models_mae_learn_feature_loss.py:28

Method__init__

(self, params, lr=0, weight_decay=0, momentum=0.9, trust_coefficient=0.001)

util/lars.py:15

next →1–100 of 186, ranked by callers