Functions — github.com/OpenGVLab/unmasked_teacher

CodeHub MCPcopy Create free account

hub / github.com/OpenGVLab/unmasked_teacher / functions

Functions1,198 in github.com/OpenGVLab/unmasked_teacher

⨍ Functions 1,198◇ Types & classes 228↳ Endpoints 1

↓ 1 callersFunctionsoftmax_focal_loss

(logits, targets, gamma, alpha, reduction='mean')

single_modality/action_detection/alphaction/layers/softmax_focal_loss.py:33

↓ 1 callersFunctionsort_by_field

Sort boxes and associated fields according to a scalar field. A common use case is reordering the boxes according to descending scores. Args:

single_modality/action_detection/alphaction/dataset/datasets/evaluation/ava/pascal_evaluation/np_box_mask_list_ops.py:139

↓ 1 callersFunctionspatial_sampling

Perform spatial sampling on the given video frames. If spatial_idx is -1, perform random scale, random crop, and random flip on the given

single_modality/datasets/kinetics.py:313

↓ 1 callersFunctionspatial_sampling

Perform spatial sampling on the given video frames. If spatial_idx is -1, perform random scale, random crop, and random flip on the given

single_modality/datasets/kinetics_sparse.py:301

↓ 1 callersFunctionstrip_prefix_if_present

(state_dict, prefix)

single_modality/action_detection/alphaction/utils/model_serialization.py:64

↓ 1 callersFunctionsync_save_result

gather results from multiple GPUs

multi_modality/dataset/utils.py:123

↓ 1 callersMethodtag_last_checkpoint

(self, last_filename)

single_modality/action_detection/alphaction/utils/checkpoint.py:101

↓ 1 callersFunctiontensor_normalize

Normalize a given tensor by subtracting the mean and dividing the std. Args: tensor (tensor): tensor to normalize. mean (tens

single_modality/datasets/kinetics.py:387

↓ 1 callersFunctiontensor_normalize

Normalize a given tensor by subtracting the mean and dividing the std. Args: tensor (tensor): tensor to normalize. mean (tens

single_modality/datasets/kinetics_sparse.py:375

↓ 1 callersMethodtop_k

single_modality/action_detection/alphaction/structures/bounding_box.py:266

↓ 1 callersFunctiontrain

( model, train_loaders, optimizer, tokenizer, epoch, global_step, device, sche

multi_modality/tasks/retrieval.py:28

↓ 1 callersFunctiontrain

( model, train_loaders, optimizer, tokenizer, epoch, global_step, device, sche

multi_modality/tasks/pretrain.py:26

↓ 1 callersFunctiontrain

( model, train_loaders, optimizer, tokenizer, epoch, global_step, device, sche

multi_modality/tasks/retrieval_mc.py:193

↓ 1 callersFunctiontrain

( model, train_loader, optimizer, tokenizer, epoch, global_step, device, sched

multi_modality/tasks/vqa.py:31

↓ 1 callersFunctiontrain_one_epoch

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

single_modality/action_detection/engine_for_finetuning.py:40

↓ 1 callersFunctiontrain_one_epoch

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

single_modality/engines/engine_for_pretraining.py:11

↓ 1 callersFunctiontrain_one_epoch

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

single_modality/engines/engine_for_finetuning.py:25

↓ 1 callersFunctiontrain_one_epoch

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

single_modality/engines/engine_for_pretraining_umt.py:11

↓ 1 callersFunctiontransform

single_modality/datasets/rand_augment.py:126

↓ 1 callersFunctiontrunc_normal_

(tensor, mean=0., std=1.)

single_modality/models/modeling_pretrain_umt.py:14

↓ 1 callersMethodupdate

(self, **kwargs)

single_modality/utils.py:88

↓ 1 callersMethodupdate

(self, update_info)

single_modality/action_detection/alphaction/structures/memory_pool.py:7

↓ 1 callersMethodupdateProgress

(self, progress)

multi_modality/tasks/vqa_utils.py:239

↓ 1 callersMethoduta_loss

forward to calculate the loss Args: student_output (torch.Tensor): The student output. Shape: [K,B,N,C]. clip_output

multi_modality/models/criterions.py:331

↓ 1 callersFunctionval_in_train

( model, dataset_names_val, data_loaders_val, tblogger, iteration,

single_modality/action_detection/alphaction/engine/trainer.py:146

↓ 1 callersFunctionvalidation_one_epoch

(data_loader, model, device, fp32=False)

single_modality/engines/engine_for_finetuning.py:145

↓ 1 callersMethodvalue

single_modality/action_detection/utils.py:71

↓ 1 callersMethodvideo_normalize

(self, tensor, mean, std)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:198

↓ 1 callersFunctionvit_large_patch16_384

(pretrained=False, **kwargs)

single_modality/models/modeling_finetune.py:357

↓ 1 callersMethodvtc_loss

forward to calculate the loss Args: vision_proj (torch.Tensor): The vision representation. Shape: [B,T,C]. text_proj

multi_modality/models/criterions.py:44

↓ 1 callersMethodvtm_loss

video-text matching loss. Args: multinomial_encoder (nn.Module): The multimodal_encoder. vtm_head (nn.Module): The he

multi_modality/models/criterions.py:83

FunctionPYBIND11_MODULE

single_modality/action_detection/alphaction/csrc/vision.cpp:7

FunctionROIAlign3d_backward

single_modality/action_detection/alphaction/csrc/ROIAlign3d.h:26

FunctionROIAlign3d_forward

Interface for Python

single_modality/action_detection/alphaction/csrc/ROIAlign3d.h:10

FunctionROIPool3d_backward

single_modality/action_detection/alphaction/csrc/ROIPool3d.h:25

FunctionROIPool3d_forward

single_modality/action_detection/alphaction/csrc/ROIPool3d.h:10

FunctionSigmoidFocalLoss_backward

single_modality/action_detection/alphaction/csrc/SigmoidFocalLoss.h:25

FunctionSigmoidFocalLoss_forward

Interface for Python

single_modality/action_detection/alphaction/csrc/SigmoidFocalLoss.h:10

FunctionSoftmaxFocalLoss_backward

single_modality/action_detection/alphaction/csrc/SoftmaxFocalLoss.h:25

FunctionSoftmaxFocalLoss_forward

Interface for Python

single_modality/action_detection/alphaction/csrc/SoftmaxFocalLoss.h:10

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

single_modality/utils.py:409

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

single_modality/action_detection/utils.py:347

single_modality/action_detection/datasets.py:18

(self, class_logits, proposals, avg_box_num)

single_modality/action_detection/alphaction/modeling/roi_heads/action_head/metric.py:27

(self, class_logits, avg_box_num)

single_modality/action_detection/alphaction/modeling/roi_heads/action_head/loss.py:40

single_modality/action_detection/alphaction/dataset/collate_batch.py:39

(self, videos, target)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:14

(self, clip, target, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:36

(self, clip, target, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:86

(self, clip, target, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:104

(self, clip, target, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:141

(self, clip, target, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:172

(self, clip, target, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:186

(self, clip, target, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:204

(self, clip, target, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:219

(self, clip, target, tranform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/video_transforms.py:240

(self, object_boxes, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/object_transforms.py:7

(self, objects, _)

single_modality/action_detection/alphaction/dataset/transforms/object_transforms.py:19

(self, object_boxes, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/object_transforms.py:25

(self, object_boxes, transform_randoms)

single_modality/action_detection/alphaction/dataset/transforms/object_transforms.py:37

Args: img (PIL Image): Image to be cropped and resized. Returns: PIL Image: Randomly cropped and resized imag

single_modality/datasets/video_transforms.py:766

single_modality/datasets/video_transforms.py:911

Args: img (PIL.Image or numpy.ndarray): List of images to be cropped in format (h, w, c) in numpy.ndarray Returns:

single_modality/datasets/video_transforms.py:922

single_modality/datasets/video_transforms.py:957

single_modality/datasets/video_transforms.py:987

Args: img (PIL.Image or numpy.ndarray): List of images to be cropped in format (h, w, c) in numpy.ndarray Returns:

single_modality/datasets/video_transforms.py:1006

Args: img (PIL.Image or numpy.ndarray): List of images to be cropped in format (h, w, c) in numpy.ndarray Returns:

single_modality/datasets/video_transforms.py:1050

Args: img (PIL.Image or numpy.ndarray): List of images to be cropped in format (h, w, c) in numpy.ndarray Returns:

single_modality/datasets/video_transforms.py:1106

Args: img (PIL.Image or numpy.ndarray): List of images to be cropped in format (h, w, c) in numpy.ndarray Returns:

single_modality/datasets/video_transforms.py:1140

Args: clip (list): list of PIL.Image Returns: list PIL.Image : list of transformed PIL.Image

single_modality/datasets/video_transforms.py:1215

Args: clip (Tensor): Tensor clip of size (T, C, H, W) to be normalized. Returns: Tensor: Normalized Tensor cl

single_modality/datasets/video_transforms.py:1270

single_modality/datasets/build.py:45

(self, img_tuple)

single_modality/datasets/transforms.py:18

(self, img_tuple)

single_modality/datasets/transforms.py:43

(self, img_tuple)

single_modality/datasets/transforms.py:52

(self, tensor_tuple)

single_modality/datasets/transforms.py:67

(self, img_tuple)

single_modality/datasets/transforms.py:83

(self, img_tuple)

single_modality/datasets/transforms.py:94

(self, img_tuple)

single_modality/datasets/transforms.py:111

(self, img_tuple)

single_modality/datasets/transforms.py:126

(self, img_tuple)

single_modality/datasets/transforms.py:194

(self, pic_tuple)

single_modality/datasets/transforms.py:212

single_modality/datasets/transforms.py:230

Args: clip (list of numpy.ndarray): clip (list of images) to be converted to tensor.

single_modality/datasets/volume_transforms.py:26

Args: clip (list of numpy.ndarray): clip (list of images) to be converted to tensor.

single_modality/datasets/volume_transforms.py:81

single_modality/datasets/volume_transforms.py:129

(self, x, target)

single_modality/datasets/mixup.py:209

(self, batch, _=None)

single_modality/datasets/mixup.py:299

single_modality/datasets/masking_generator.py:18

single_modality/datasets/masking_generator.py:43

(self, img_list)

single_modality/datasets/rand_augment.py:364

single_modality/datasets/rand_augment.py:468

single_modality/datasets/random_erasing.py:151

Method__contains__

single_modality/action_detection/alphaction/structures/memory_pool.py:32

multi_modality/utils/logger.py:234

Method__delitem__

single_modality/action_detection/alphaction/structures/memory_pool.py:26

Method__getattr__

multi_modality/utils/basic_utils.py:96

Method__getattr__

single_modality/utils.py:97

Method__getattr__

single_modality/action_detection/utils.py:97

Method__getattr__

single_modality/action_detection/alphaction/utils/metric_logger.py:52

← previous next →501–600 of 1,198, ranked by callers