MCPcopy Create free account

hub / github.com/PKU-ICST-MIPL/FineSports_CVPR2024 / functions

Functions799 in github.com/PKU-ICST-MIPL/FineSports_CVPR2024

⨍ Functions 799◇ Types & classes 157↳ Endpoints 1
↓ 109 callersFunctionprint
(*args, **kwargs)
utils/misc.py:396
↓ 87 callersMethodto
(self, device)
models/detr/util/misc.py:337
↓ 84 callersFunctionprint
(*args, **kwargs)
models/BLIP/utils.py:217
↓ 42 callersMethodupdate
(self, val, n=1)
utils/utils.py:69
↓ 31 callersMethodto
(self, device)
utils/misc.py:371
↓ 26 callersFunction_n2p
(w, t=True)
models/BLIP/models/vit.py:207
↓ 25 callersMethodupdate
(self, **kwargs)
models/BLIP/utils.py:97
↓ 21 callersMethodget
Convenience function for accesssing box coordinates. Returns: a numpy array of shape [N, 4] representing box corners
evaluates/utils/np_box_list.py:82
↓ 20 callersMethodget_field
Accesses data associated with the specified field in the box collection. Args: field: a string parameter used to speficy a related field to
evaluates/utils/np_box_list.py:90
↓ 13 callersMethod__init__
(self, config, layer_num)
models/BLIP/models/med.py:321
↓ 13 callersMethodadd_meter
(self, name, meter)
models/BLIP/utils.py:132
↓ 13 callersFunctioncopy_weights
(layer_weight, weights_name, weights, weights_dict_copy)
models/backbones/ir_CSN_152.py:209
↓ 13 callersFunctioncopy_weights
(layer_weight, weights_name, weights, weights_dict_copy)
models/backbones/ir_CSN_50.py:211
↓ 13 callersMethodlog_every
(self, iterable, print_freq, header=None)
models/BLIP/utils.py:135
↓ 13 callersFunctionprint
(*args, **kwargs)
models/transformer/util/misc.py:362
↓ 12 callersMethod__init__
(self, config, layer_num)
models/BLIP/models/nlvr_encoder.py:357
↓ 12 callersMethodnum_boxes
Return number of boxes held in collections.
evaluates/utils/np_box_list.py:54
↓ 12 callersMethodupdate
(self, **kwargs)
utils/misc.py:156
↓ 11 callersMethodhas_field
(self, field)
evaluates/utils/np_box_list.py:62
↓ 11 callersFunctionload_conv3d
(state_dict, name_pt, sess, name_tf, bias=False, bn=True)
models/I3D_Backbone.py:361
↓ 10 callersMethodadd_field
Add data to a specified field. Args: field: a string parameter used to speficy a related field to be accessed. field_data: a numpy ar
evaluates/utils/np_box_list.py:65
↓ 9 callersFunctioncreate_vit
(vit, image_size, use_grad_checkpointing=False, ckpt_layer=0, drop_path_rate=0)
models/BLIP/models/blip.py:194
↓ 9 callersMethodget_masks
Convenience function for accessing masks. Returns: a numpy array of shape [N, height, width] representing masks
evaluates/utils/np_box_mask_list.py:56
↓ 9 callersFunctionload_mixed
(state_dict, name_pt, sess, name_tf, fix_typo=False)
models/I3D_Backbone.py:392
↓ 9 callersMethodtrain
Convert the model into training mode while keep layers freezed.
models/backbones/video_swin_transformer.py:589
↓ 7 callersMethodbackward
(ctx, *grads)
models/BLIP/models/blip_retrieval.py:300
↓ 7 callersFunctionconcat_all_gather
Performs all_gather operation on the provided tensors. *** Warning ***: torch.distributed.all_gather has no gradient.
models/BLIP/models/blip_retrieval.py:274
↓ 7 callersFunctiongather
Gather boxes from BoxList according to indices and return new BoxList. By default, gather returns boxes corresponding to the input index list, as
evaluates/utils/np_box_list_ops.py:95
↓ 7 callersFunctioninit_tokenizer
()
models/BLIP/models/blip.py:186
↓ 7 callersMethodmax
(self)
models/detr/util/misc.py:73
↓ 7 callersFunctionnested_tensor_from_tensor_list
(tensor_list: List[Tensor])
utils/misc.py:330
↓ 7 callersFunctionpre_caption
(caption,max_words=50)
models/BLIP/data/utils.py:10
↓ 7 callersFunctionprint
(*args, **kwargs)
models/detr/util/misc.py:362
↓ 7 callersMethodtranspose_for_scores
(self, x)
models/BLIP/models/nlvr_encoder.py:128
↓ 7 callersMethodtranspose_for_scores
(self, x)
models/BLIP/models/med.py:138
↓ 6 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
models/backbones/video_swin_transformer.py:40
↓ 6 callersMethod__init__
(self, encoder_layer, num_layers, norm=None)
models/transformer/transformer_layers.py:24
↓ 6 callersMethod__init__
Constructor. Args: categories: A list of dicts, each of which has the following keys - 'id': (required) an intege
evaluates/utils/object_detection_evaluation.py:61
↓ 6 callersFunctioncreate_dataset
(dataset, config, min_scale=0.5)
models/BLIP/data/__init__.py:14
↓ 6 callersFunctioncreate_loader
(datasets, samplers, batch_size, num_workers, is_trains, collate_fns)
models/BLIP/data/__init__.py:80
↓ 6 callersFunctioncreate_sampler
(datasets, shuffles, num_tasks, global_rank)
models/BLIP/data/__init__.py:72
↓ 6 callersFunctioncrop
(images, target, region)
datasets/video_transforms.py:20
↓ 6 callersMethodglobal_avg
(self)
models/BLIP/utils.py:120
↓ 6 callersMethodmax
(self)
utils/misc.py:68
↓ 6 callersMethodsynchronize_between_processes
(self)
models/BLIP/utils.py:128
↓ 6 callersMethodvalue
(self)
models/BLIP/utils.py:80
↓ 6 callersMethodwith_pos_embed
(self, tensor, pos: Optional[Tensor])
models/transformer/transformer.py:233
↓ 5 callersMethodadd_single_ground_truth_image_info
Adds groundtruth for a single image to be used for evaluation. Args: image_id: A unique string/integer identifier for the image.
evaluates/utils/object_detection_evaluation.py:72
↓ 5 callersFunctioncopy_bn
(layer, layer_name, weights, weights_dict_copy, use_affine=True)
models/backbones/ir_CSN_152.py:215
↓ 5 callersFunctioncopy_bn
(layer, layer_name, weights, weights_dict_copy, use_affine=True)
models/backbones/ir_CSN_50.py:217
↓ 5 callersMethodget_extra_fields
Return all non-box fields.
evaluates/utils/np_box_list.py:58
↓ 5 callersFunctionload_checkpoint
(model,url_or_filename)
models/BLIP/models/blip.py:215
↓ 5 callersFunctionnested_tensor_from_tensor_list
(tensor_list: List[Tensor])
models/detr/util/misc.py:294
↓ 5 callersFunctionsave_result
(result, result_dir, filename, remove_duplicate='')
models/BLIP/data/utils.py:47
↓ 4 callersMethod__init__
(self, num_classes, modality='rgb', dropout_prob=0,
models/I3D_Backbone.py:163
↓ 4 callersMethod__init__
(self, d_model=512, nhead=8, num_encoder_layers=6, num_decoder_layers=6, dim_feedforward=2048
models/transformer/transformer.py:16
↓ 4 callersMethod__init__
(self, detr, freeze_detr=False)
models/detr/segmentation.py:25
↓ 4 callersMethod_compute_tp_fp
Labels true/false positives of detections of an image across all classes. Args: detected_boxes: A float numpy array of shape [N, 4], repres
evaluates/utils/per_image_evaluation.py:170
↓ 4 callersFunction_expand
(tensor, length: int)
models/detr/segmentation.py:65
↓ 4 callersMethod_make_layer
(self, block, in_planes, planes,
models/backbones/ir_CSN_152.py:138
↓ 4 callersMethod_make_layer
(self, block, in_planes, planes,
models/backbones/ir_CSN_50.py:138
↓ 4 callersMethodadd_single_detected_image_info
Adds detections for a single image to be used for evaluation. Args: image_id: A unique string/integer identifier for the image.
evaluates/utils/object_detection_evaluation.py:83
↓ 4 callersFunctionblip_retrieval
(pretrained='',**kwargs)
models/BLIP/models/blip_retrieval.py:264
↓ 4 callersFunctionbox_cxcywh_to_xyxy
(x)
models/detr/util/box_ops.py:9
↓ 4 callersFunctionbox_list_to_box_mask_list
Converts a BoxList containing 'masks' into a BoxMaskList. Args: boxlist: An np_box_list.BoxList object. Returns: An np_box_mask_list.Box
evaluates/utils/np_box_mask_list_ops.py:29
↓ 4 callersFunctioncosine_lr_schedule
Decay the learning rate
models/BLIP/utils.py:2
↓ 4 callersMethoddecompose
(self)
models/detr/util/misc.py:348
↓ 4 callersFunctionenhance_level_to_args
(MAX_LEVEL)
models/BLIP/transform/randaugment.py:208
↓ 4 callersFunctiongather
Gather boxes from np_box_mask_list.BoxMaskList according to indices. By default, gather returns boxes corresponding to the input index list, as w
evaluates/utils/np_box_mask_list_ops.py:110
↓ 4 callersMethodgenerate
(self, image, sample=False, num_beams=3, max_length=30, min_length=10, top_p=0.9, repetition_penalty=1.0)
models/BLIP/models/blip.py:128
↓ 4 callersMethodmax
(self)
models/transformer/util/misc.py:73
↓ 4 callersMethodmax
(self)
models/BLIP/utils.py:76
↓ 3 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
models/BLIP/models/vit.py:26
↓ 3 callersMethod_freeze_stages
(self)
models/backbones/video_swin_transformer.py:559
↓ 3 callersMethod_get_src_permutation_idx
(self, indices)
models/criterion.py:148
↓ 3 callersMethod_get_src_permutation_idx
(self, indices)
models/criterion.py:347
↓ 3 callersFunction_run
(command)
utils/misc.py:253
↓ 3 callersFunction_run
(command)
models/transformer/util/misc.py:261
↓ 3 callersFunction_run
(command)
models/detr/util/misc.py:261
↓ 3 callersFunctionarea
Computes area of boxes. Args: boxes: Numpy array with shape [N, 4] holding N boxes Returns: a numpy array with shape [N*1] representing
evaluates/utils/np_box_ops.py:25
↓ 3 callersFunctionarea
Computes area of masks. Args: masks: Numpy array with shape [N, height, width] holding N masks. Masks values are of type np.uint8 and val
evaluates/utils/np_mask_ops.py:27
↓ 3 callersFunctionblip_decoder
(pretrained='',**kwargs)
models/BLIP/models/blip.py:172
↓ 3 callersMethodevaluate
(self)
evaluates/evaluate_ava.py:160
↓ 3 callersFunctioninterpolate
Equivalent to nn.functional.interpolate, but with support for empty batch sizes. This will eventually be supported natively by PyTorch, and t
models/detr/util/misc.py:468
↓ 3 callersFunctioninterpolate_pos_embed
(pos_embed_checkpoint, visual_encoder)
models/BLIP/models/vit.py:281
↓ 3 callersFunctionis_dist_avail_and_initialized
()
utils/misc.py:404
↓ 3 callersFunctionis_dist_avail_and_initialized
()
models/transformer/util/misc.py:370
↓ 3 callersFunctionis_dist_avail_and_initialized
()
models/BLIP/utils.py:225
↓ 3 callersFunctionis_dist_avail_and_initialized
()
models/detr/util/misc.py:370
↓ 3 callersMethodto_cuda
(self, device)
models/BLIP/prompt_learner.py:187
↓ 3 callersMethodwith_pos_embed
(self, tensor, pos: Optional[Tensor])
models/transformer/transformer_layers.py:67
↓ 2 callersMethod__init__
(self, input_dim, hidden_dim, output_dim, num_layers)
models/criterion.py:481
↓ 2 callersMethod__init__
(self, feature_in)
models/backbones/ir_CSN_152.py:19
↓ 2 callersMethod__init__
(self, feature_in)
models/backbones/ir_CSN_50.py:16
↓ 2 callersFunction_copy_extra_fields
Copies the extra fields of boxlist_to_copy_from to boxlist_to_copy_to. Args: boxlist_to_copy_to: BoxList to which extra fields are copied.
evaluates/utils/np_box_list_ops.py:536
↓ 2 callersFunction_get_activation_fn
Return an activation function given a string
models/transformer/transformer_layers.py:366
↓ 2 callersFunction_get_activation_fn
Return an activation function given a string
models/transformer/transformer.py:310
↓ 2 callersFunction_get_clones
(module, N)
models/transformer/transformer_layers.py:14
↓ 2 callersFunction_get_clones
(module, N)
models/transformer/transformer.py:306
↓ 2 callersMethod_get_lr
(self, t)
utils/lr_scheduler.py:121
next →1–100 of 799, ranked by callers