Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/MCG-NJU/VideoMAE
/ functions
Functions
287 in github.com/MCG-NJU/VideoMAE
⨍
Functions
287
◇
Types & classes
48
Function
_shear_level_to_arg
(level, _hparams)
rand_augment.py:220
Function
_solarize_add_level_to_arg
(level, _hparams)
rand_augment.py:275
Function
_solarize_increasing_level_to_arg
(level, _hparams)
rand_augment.py:269
Function
_translate_abs_level_to_arg
(level, hparams)
rand_augment.py:227
Function
_translate_rel_level_to_arg
(level, hparams)
rand_augment.py:234
Function
auto_contrast
(img, **__)
rand_augment.py:142
Function
auto_load_model
(args, model, model_without_ddp, optimizer, loss_scaler, model_ema=None)
utils.py:430
Method
avg
(self)
utils.py:58
Function
brightness
(img, factor, **__)
rand_augment.py:187
Function
clip_boxes_to_image
Clip an array of boxes to an image with the given height and width. Args: boxes (ndarray): bounding boxes to perform clipping.
video_transforms.py:254
Function
color
(img, factor, **__)
rand_augment.py:183
Function
color_jitter
Perfrom a color jittering on the input images. The channels of images should be in order BGR. Args: images (tensor): images to pe
video_transforms.py:314
Function
color_normalization
Perform color nomration on the given images. Args: images (tensor): images to perform color normalization. Dimension is `
video_transforms.py:455
Function
compute_video
(lst)
engine_for_finetuning.py:275
Function
contrast
(img, factor, **__)
rand_augment.py:179
Function
cosine_scheduler
(base_value, final_value, epochs, niter_per_ep, warmup_epochs=0, start_warmup_value=0, wa
utils.py:385
Function
create_ds_config
(args)
utils.py:482
Function
create_random_augment
Get video randaug transform. Args: input_size: The size of the input video in tuple. auto_augment: Parameters for randaug. A
video_transforms.py:621
Function
crop_clip
(clip, min_h, min_w, h, w)
functional.py:12
Function
equalize
(img, **__)
rand_augment.py:150
Method
extra_repr
(self)
modeling_finetune.py:31
Method
forward
(self, x)
modeling_finetune.py:28
Method
forward
(self, x)
modeling_finetune.py:45
Method
forward
(self, x)
modeling_finetune.py:79
Method
forward
(self, x)
modeling_finetune.py:124
Method
forward
(self, x, **kwargs)
modeling_finetune.py:150
Method
forward
(self, x)
modeling_finetune.py:282
Method
forward
(self, x, mask)
modeling_pretrain.py:107
Method
forward
(self, x, return_token_num)
modeling_pretrain.py:163
Method
forward
(self, x, mask)
modeling_pretrain.py:271
Method
get_classifier
(self)
modeling_finetune.py:254
Method
get_classifier
(self)
modeling_pretrain.py:81
Method
get_classifier
(self)
modeling_pretrain.py:156
Method
get_layer_id
(self, var_name)
optim_factory.py:45
Method
get_num_layers
(self)
modeling_pretrain.py:74
Method
get_num_layers
(self)
modeling_pretrain.py:149
Method
get_num_layers
(self)
modeling_pretrain.py:264
Method
get_scale
(self, layer_id)
optim_factory.py:42
Method
global_avg
(self)
utils.py:63
Function
horizontal_flip
Perform horizontal flip on the given images and corresponding boxes. Args: prob (float): probility to flip the images. images
video_transforms.py:156
Function
init_distributed_mode
(args)
utils.py:249
Function
invert
(img, **__)
rand_augment.py:146
Function
lighting_jitter
Perform AlexNet-style PCA jitter on the given images. Args: images (tensor): images to perform lighting jitter. Dimension is
video_transforms.py:407
Function
load_state_dict
(model, state_dict, prefix='', ignore_missing="relative_position_index")
utils.py:293
Method
median
(self)
utils.py:53
Function
multiple_samples_collate
Collate function for repeated augmentation. Each instance in the batch has more than one sample. Args: batch (tuple or list): dat
utils.py:513
Method
no_weight_decay
(self)
modeling_pretrain.py:78
Method
no_weight_decay
(self)
modeling_pretrain.py:153
Method
no_weight_decay
(self)
modeling_pretrain.py:268
Function
normalize
(clip, mean, std, inplace=False)
functional.py:77
Function
posterize
(img, bits_to_keep, **__)
rand_augment.py:173
Function
pretrain_videomae_base_patch16_224
(pretrained=False, **kwargs)
modeling_pretrain.py:311
Function
pretrain_videomae_huge_patch16_224
(pretrained=False, **kwargs)
modeling_pretrain.py:359
Function
pretrain_videomae_large_patch16_224
(pretrained=False, **kwargs)
modeling_pretrain.py:335
Function
pretrain_videomae_small_patch16_224
(pretrained=False, **kwargs)
modeling_pretrain.py:287
Function
random_crop
Perform random spatial crop on the given images and corresponding boxes. Args: images (tensor): images to perform random crop. The di
video_transforms.py:120
Function
random_resized_crop
Crop the given images to random size and aspect ratio. A crop of random size (default: of 0.08 to 1.0) of the original size and a random aspe
video_transforms.py:541
Function
random_resized_crop_with_shift
This is similar to random_resized_crop. However, it samples two different boxes (for cropping) for the first and last frame. It then linearly
video_transforms.py:576
Function
random_short_side_scale_jitter
Perform a spatial short scale jittering on the given images and corresponding boxes. Args: images (tensor): images to perform sca
video_transforms.py:44
Function
random_sized_crop_img
Performs Inception-style cropping (used for training).
video_transforms.py:657
Method
reset_classifier
(self, num_classes, global_pool='')
modeling_finetune.py:257
Method
reset_classifier
(self, num_classes, global_pool='')
modeling_pretrain.py:84
Method
reset_classifier
(self, num_classes, global_pool='')
modeling_pretrain.py:159
Function
resize_clip
(clip, size, interpolation='bilinear')
functional.py:26
Function
rotate
(img, degrees, **kwargs)
rand_augment.py:108
Function
save_model
(args, epoch, model, model_without_ddp, optimizer, loss_scaler, model_ema=None)
utils.py:405
Function
seed_worker
(worker_id)
utils.py:190
Function
sharpness
(img, factor, **__)
rand_augment.py:191
Function
shear_x
(img, factor, **kwargs)
rand_augment.py:64
Function
shear_y
(img, factor, **kwargs)
rand_augment.py:71
Function
solarize
(img, thresh, **__)
rand_augment.py:154
Function
solarize_add
(img, add, thresh=128, **__)
rand_augment.py:158
Method
synchronize_between_processes
Warning: does not synchronize the deque!
utils.py:39
Function
transforms_imagenet_train
If separate==True, the transforms are returned as a tuple of 3 separate transforms for use in a mixing dataset that passes * all data th
video_transforms.py:799
Function
translate_x_abs
(img, pixels, **kwargs)
rand_augment.py:94
Function
translate_x_rel
(img, pct, **kwargs)
rand_augment.py:78
Function
translate_y_abs
(img, pixels, **kwargs)
rand_augment.py:101
Function
translate_y_rel
(img, pct, **kwargs)
rand_augment.py:86
Function
uniform_crop
Perform uniform spatial sampling on the images and corresponding boxes. Args: images (tensor): images to perform uniform crop. The di
video_transforms.py:191
Method
value
(self)
utils.py:71
Function
vit_base_patch16_224
(pretrained=False, **kwargs)
modeling_finetune.py:298
Function
vit_base_patch16_384
(pretrained=False, **kwargs)
modeling_finetune.py:307
Function
vit_huge_patch16_224
(pretrained=False, **kwargs)
modeling_finetune.py:343
Function
vit_large_patch16_224
(pretrained=False, **kwargs)
modeling_finetune.py:316
Function
vit_large_patch16_384
(pretrained=False, **kwargs)
modeling_finetune.py:325
Function
vit_large_patch16_512
(pretrained=False, **kwargs)
modeling_finetune.py:334
Function
vit_small_patch16_224
(pretrained=False, **kwargs)
modeling_finetune.py:289
← previous
201–287 of 287, ranked by callers