Functions — github.com/SJTU-LuHe/TransVOD

CodeHub MCPcopy Create free account

hub / github.com/SJTU-LuHe/TransVOD / functions

Functions415 in github.com/SJTU-LuHe/TransVOD

⨍ Functions 415◇ Types & classes 92

util/misc_multi.py:384

util/misc.py:115

util/misc.py:214

util/misc_multi.py:115

util/misc_multi.py:214

Method_load_from_state_dict

(self, state_dict, prefix, local_metadata, strict, missing_keys, unexpected_key

models/backbone.py:44

Method_set_aux_loss

(self, outputs_class, outputs_coord)

models/deformable_detr_multi.py:196

Methodadd_meter

(self, name, meter)

util/misc_multi.py:226

Functionall_gather

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[

util/misc_multi.py:124

util/misc.py:99

util/misc_multi.py:99

(image_set, args)

datasets/vid_single.py:166

(image_set, args)

datasets/vid_multi.py:235

(image_set, args)

datasets/coco_panoptic.py:88

(image_set, args)

datasets/coco.py:157

models/deformable_detr_single.py:444

models/deformable_detr_multi.py:450

Functionbuild_deforamble_transformer

models/deformable_transformer_single.py:432

Functioncollate_fn

util/misc.py:304

Functioncollate_fn

util/misc_multi.py:304

MethodcreateIndex

datasets/coco_video_parser.py:36

MethodcreateIndex

datasets/parsers/coco_video_parser.py:38

Methoddecompose

util/misc_multi.py:381

Functionevaluate

(model, criterion, postprocessors, data_loader, base_ds, device, output_dir)

engine_single.py:82

(self, srcs, masks, pos_embeds, query_embed=None, class_embed = None )

models/deformable_transformer_multi.py:156

(self, query , ref_query, query_pos = None, ref_query_pos = None)

models/deformable_transformer_multi.py:304

(self, query , ref_query, query_pos = None, ref_query_pos = None)

models/deformable_transformer_multi.py:331

(self, tgt, query_pos, reference_points, src, src_spatial_shapes, frame_start_index, src_padding_mask=None)

models/deformable_transformer_multi.py:370

(self, src, pos, reference_points, spatial_shapes, level_start_index, padding_mask=None)

models/deformable_transformer_multi.py:418

(self, src, spatial_shapes, level_start_index, valid_ratios, pos=None, padding_mask=None)

models/deformable_transformer_multi.py:451

(self, tgt, query_pos, reference_points, src, src_spatial_shapes, level_start_index, src_padding_mask=None)

models/deformable_transformer_multi.py:495

(self, tgt, reference_points, src, src_spatial_shapes, src_level_start_index, src_valid_ratios,

models/deformable_transformer_multi.py:532

(self, tgt, reference_points, src, src_spatial_shapes, src_level_start_index, src_valid_ratios,

models/deformable_transformer_multi.py:580

Performs the matching Params: outputs: This is a dict that contains at least these entries: "pred_logits":

models/matcher.py:45

The forward expects a NestedTensor, which consists of: - samples.tensor: batched images, of shape [batch_size x 3 x H x W]

models/deformable_detr_single.py:114

This performs the loss computation. Parameters: outputs: dict of tensors, see the output specification of the model for the fo

models/deformable_detr_single.py:332

Perform the computation Parameters: outputs: raw outputs of the model target_sizes: tensor of dimension [batch_siz

models/deformable_detr_single.py:398

models/deformable_detr_single.py:438

(self, srcs, masks, pos_embeds, query_embed=None)

models/deformable_transformer_single.py:126

(self, src, pos, reference_points, spatial_shapes, level_start_index, padding_mask=None)

models/deformable_transformer_single.py:220

(self, src, spatial_shapes, level_start_index, valid_ratios, pos=None, padding_mask=None)

models/deformable_transformer_single.py:253

(self, tgt, query_pos, reference_points, src, src_spatial_shapes, level_start_index, src_padding_mask=None)

models/deformable_transformer_single.py:296

(self, tgt, query_pos, reference_points, src, src_spatial_shapes, frame_start_index, src_padding_mask=None)

models/deformable_transformer_single.py:349

(self, tgt, reference_points, src, src_spatial_shapes, src_level_start_index, src_valid_ratios,

models/deformable_transformer_single.py:379

The forward expects a NestedTensor, which consists of: - samples.tensor: batched images, of shape [batch_size x 3 x H x W]

models/deformable_detr_multi.py:126

This performs the loss computation. Parameters: outputs: dict of tensors, see the output specification of the model for the fo

models/deformable_detr_multi.py:338

Perform the computation Parameters: outputs: raw outputs of the model target_sizes: tensor of dimension [batch_siz

models/deformable_detr_multi.py:404

models/deformable_detr_multi.py:444

(self, samples: NestedTensor)

models/segmentation.py:43

(self, x, bbox_mask, fpns)

models/segmentation.py:105

(self, q, k, mask=None)

models/segmentation.py:164

(self, results, outputs, orig_target_sizes, max_target_sizes)

models/segmentation.py:230

This function computes the panoptic prediction from the model's predictions. Parameters: outputs: This is a dict coming directl

models/segmentation.py:262

models/backbone.py:54

(self, tensor_list: NestedTensor)

models/backbone.py:85

(self, tensor_list: NestedTensor)

models/backbone.py:119

(self, tensor_list: NestedTensor)

models/position_encoding.py:36

(self, tensor_list: NestedTensor)

models/position_encoding.py:73

:param query (N, Length_{query}, C) :param reference_points (N, Length_{query}, n_levels, 2), rang

models/ops/modules/ms_deform_attn.py:78

(ctx, value, value_spatial_shapes, value_level_start_index, sampling_locations, attention_weights, im2col_step

models/ops/functions/ms_deform_attn_func.py:23

Methodget_height_and_width

datasets/coco_panoptic.py:81

Methodget_ids_area

(masks, scores, dedup=False)

models/segmentation.py:307

Methodget_img_ids_from_ins_id

Get image ids from given instance id. Args: insId (int): The given instance id. Returns: list[int]: Image

datasets/coco_video_parser.py:131

Methodget_img_ids_from_ins_id

Get image ids from given instance id. Args: insId (int): The given instance id. Returns: list[int]: Im

datasets/parsers/coco_video_parser.py:136

Methodget_img_ids_from_vid

Get image ids from given video id. Args: vidId (int): The given video id. Returns: list[int]: Image id

datasets/parsers/coco_video_parser.py:110

Methodget_ins_ids_from_vid

Get instance ids from given video id. Args: vidId (int): The given video id. Returns: list[int]: Instance

datasets/coco_video_parser.py:122

Methodget_ins_ids_from_vid

Get instance ids from given video id. Args: vidId (int): The given video id. Returns: list[int]: Insta

datasets/parsers/coco_video_parser.py:125

Functionget_local_rank

util/misc_multi.py:429

Functionget_local_size

util/misc_multi.py:423

Functionget_sha

util/misc.py:284

Functionget_sha

util/misc_multi.py:284

Functionget_total_grad_norm

(parameters, norm_type=2)

util/misc.py:505

Functionget_total_grad_norm

(parameters, norm_type=2)

util/misc_multi.py:527

Methodget_vid_ids

Get video ids that satisfy given filter conditions. Default return all video ids. Args: vidIds (list[int]): The given v

datasets/coco_video_parser.py:88

Methodget_vid_ids

Get video ids that satisfy given filter conditions. Default return all video ids. Args: vidIds (list[int]): The giv

datasets/parsers/coco_video_parser.py:90

Methodglobal_avg

util/misc.py:104

Methodglobal_avg

util/misc_multi.py:104

Functioninit_distributed_mode

util/misc.py:423

Functioninit_distributed_mode

util/misc_multi.py:444

Methodis_center_of_bboxes_in_patch

datasets/transforms_multi.py:260

Methodload_vids

Get video information of given video ids. Default return all videos information. Args: ids (list[int]): The given video

datasets/coco_video_parser.py:140

Methodload_vids

Get video information of given video ids. Default return all videos information. Args: ids (list[int]): The given v

datasets/parsers/coco_video_parser.py:147

Methodlog_every

(self, iterable, print_freq, header=None)

util/misc_multi.py:229

Methodloss_boxes

Compute the losses related to the bounding boxes, the L1 regression loss and the GIoU loss targets dicts must contain the key "boxes" cont

models/deformable_detr_single.py:260

Methodloss_boxes

Compute the losses related to the bounding boxes, the L1 regression loss and the GIoU loss targets dicts must contain the key "boxes" cont

models/deformable_detr_multi.py:266

Methodloss_cardinality

Compute the cardinality error, ie the absolute error in the number of predicted non-empty boxes This is not really a loss, it is intended fo

models/deformable_detr_single.py:247

Methodloss_cardinality

Compute the cardinality error, ie the absolute error in the number of predicted non-empty boxes This is not really a loss, it is intended fo

models/deformable_detr_multi.py:253

Methodloss_labels

Classification loss (NLL) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

models/deformable_detr_single.py:220

Methodloss_labels

Classification loss (NLL) targets dicts must contain the key "labels" containing a tensor of dim [nb_target_boxes]

models/deformable_detr_multi.py:226

Methodloss_masks

Compute the losses related to the masks: the focal loss and the dice loss. targets dicts must contain the key "masks" containing a tensor

models/deformable_detr_single.py:281

Methodloss_masks

Compute the losses related to the masks: the focal loss and the dice loss. targets dicts must contain the key "masks" containing a tensor

models/deformable_detr_multi.py:287

util/misc_multi.py:108

util/misc.py:94

util/misc_multi.py:94

Functionms_deform_attn_backward

models/ops/src/ms_deform_attn.h:41

Functionms_deform_attn_cpu_backward

models/ops/src/cpu/ms_deform_attn_cpu.cpp:29

Functionms_deform_attn_cpu_forward

models/ops/src/cpu/ms_deform_attn_cpu.cpp:17

Functionms_deform_attn_forward

models/ops/src/ms_deform_attn.h:20

datasets/data_prefetcher_single.py:51

Functionplot_logs

Function to plot specific fields from training log(s). Plots both training and test results. :: Inputs - logs = list containing Path obje

util/plot_utils.py:21

← previous next →301–400 of 415, ranked by callers