MCPcopy Create free account

hub / github.com/YifanXu74/MQ-Det / functions

Functions2,105 in github.com/YifanXu74/MQ-Det

⨍ Functions 2,105◇ Types & classes 463↳ Endpoints 8
↓ 5 callersMethodget_groundtruth
(self, idx, call=False)
maskrcnn_benchmark/data/datasets/vg.py:241
↓ 5 callersFunctioninference
( model, data_loader, dataset_name, iou_types=("bbox",), box_only
maskrcnn_benchmark/engine/inference.py:502
↓ 5 callersFunctionmake_conv3x3
( in_channels, out_channels, dilation=1, stride=1, use_gn=False, use_relu=Fa
maskrcnn_benchmark/modeling/make_layers.py:44
↓ 5 callersFunctionpad_tensor_given_dim_length
(tensor, dim, length, padding_value=0, batch_first=True)
maskrcnn_benchmark/utils/shallow_contrastive_loss_helper.py:13
↓ 5 callersFunctionremove_small_boxes
Only keep boxes with both sides >= min_size Arguments: boxlist (Boxlist) min_size (int)
maskrcnn_benchmark/structures/boxlist_ops.py:78
↓ 5 callersFunctionround_filters
Calculate and round number of filters based on depth multiplier.
maskrcnn_benchmark/modeling/backbone/efficientdet.py:619
↓ 4 callersMethod__init__
(self, in_channels, out_channels, kernel_size,
maskrcnn_benchmark/modeling/backbone/efficientnet.py:100
↓ 4 callersMethod__init__
(self, in_channels=256, out_channels=256, conv_func=nn.C
maskrcnn_benchmark/modeling/rpn/dyhead.py:130
↓ 4 callersMethod__init__
(self, config)
maskrcnn_benchmark/modeling/rpn/modeling_bert.py:260
↓ 4 callersMethod__init__
( self, d_model=256, nhead=8, num_queries=300, num_encoder_layers=6,
groundingdino_new/models/GroundingDINO/transformer.py:41
↓ 4 callersMethod__setattr__
(self, name, value)
groundingdino_new/util/slconfig.py:332
↓ 4 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/utils/fuse_helper.py:201
↓ 4 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/utils/fuse_helper_cat.py:201
↓ 4 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/utils/fuse_helper_sim.py:201
↓ 4 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
groundingdino_new/models/GroundingDINO/fuse_modules.py:129
↓ 4 callersMethod_split_into_xyxy
(self)
maskrcnn_benchmark/structures/bounding_box.py:94
↓ 4 callersFunctionbox_cxcywh_to_xyxy
(x)
groundingdino_new/util/box_ops.py:9
↓ 4 callersMethodcategories
(self, no_background=True)
maskrcnn_benchmark/data/datasets/coco.py:204
↓ 4 callersFunctionclamp_values
(vector, min_val = -50000, max_val = 50000)
maskrcnn_benchmark/modeling/rpn/modeling_bert.py:34
↓ 4 callersFunctionconv_with_kaiming_uniform
(use_gn=False, use_relu=False, use_dyrelu=False)
maskrcnn_benchmark/modeling/make_layers.py:95
↓ 4 callersFunctioncreate_positive_map
construct a map such that positive_map[i,j] = True iff box i is associated to token j
maskrcnn_benchmark/data/datasets/modulated_coco_new.py:682
↓ 4 callersMethoddecode
(self, tokens)
maskrcnn_benchmark/modeling/language_backbone/simple_tokenizer.py:134
↓ 4 callersMethodevaluate
Run per image evaluation on given images and store results (a list of dict) in self.eval_imgs.
maskrcnn_benchmark/data/datasets/evaluation/lvis/lvis_eval.py:252
↓ 4 callersMethodextract_query
(self, images=None, targets=None, query_images=None, # default_dict(list) ,list[te
maskrcnn_benchmark/modeling/detector/generalized_vl_rcnn_new.py:233
↓ 4 callersFunctiongather_candidates
(all_candidates)
maskrcnn_benchmark/engine/evolution.py:25
↓ 4 callersMethodget_loss
(self, loss, outputs, targets, indices, num_boxes, **kwargs)
groundingdino_new/models/GroundingDINO/loss.py:106
↓ 4 callersFunctionget_world_size
()
groundingdino_new/util/misc.py:573
↓ 4 callersFunctiongroup_norm
(out_channels, affine=True, divisor=1)
maskrcnn_benchmark/modeling/make_layers.py:31
↓ 4 callersFunctionim_detect_bbox_aug
(model, images, device, captions=None, positive_map_label_to_token=None)
maskrcnn_benchmark/data/datasets/evaluation/box_aug.py:12
↓ 4 callersFunctionis_dist_avail_and_initialized
()
groundingdino_new/util/misc.py:565
↓ 4 callersFunctionis_str
Whether the input is an string instance. Note: This method is deprecated since python 2 is no longer supported.
groundingdino_new/util/slio.py:102
↓ 4 callersFunctionload_from_yaml_file
(yaml_file)
maskrcnn_benchmark/data/datasets/tsv.py:33
↓ 4 callersMethodload_imgs
Load categories with the specified ids. If ids=None load all images. Args: ids (int array): integer array of image ids
maskrcnn_benchmark/data/datasets/lvis.py:149
↓ 4 callersFunctionmake_anchor_generator_complex
(config)
maskrcnn_benchmark/modeling/rpn/anchor_generator.py:157
↓ 4 callersFunctionmake_fc
Caffe2 implementation uses XavierFill, which in fact corresponds to kaiming_uniform_ in PyTorch
maskrcnn_benchmark/modeling/make_layers.py:80
↓ 4 callersFunctiononline_update
( model, data_loader, device="cuda", cfg=None, num_turns = 1,
maskrcnn_benchmark/engine/inference.py:383
↓ 4 callersFunctionsetup_logger
Initialize the detectron2 logger and set its verbosity level to "INFO". Args: output (str): a file name or a directory to save log.
groundingdino_new/util/logger.py:32
↓ 4 callersMethodsummarize
Compute and display summary metrics for evaluation results.
maskrcnn_benchmark/data/datasets/evaluation/lvis/lvis_eval.py:550
↓ 4 callersMethodsummary
(self)
groundingdino_new/util/utils.py:531
↓ 4 callersMethodto
(self, device)
maskrcnn_benchmark/structures/bounding_box.py:213
↓ 3 callersMethod__getitem__
Args: index (int): Index Returns: tuple: Tuple (image, target). target is the object returned by ``coco
maskrcnn_benchmark/data/datasets/modulated_coco_new.py:406
↓ 3 callersMethod__init__
(self, cfg)
maskrcnn_benchmark/modeling/roi_heads/box_head/roi_box_feature_extractors.py:106
↓ 3 callersMethod__init__
Arguments: pre_nms_top_n (int) post_nms_top_n (int) nms_thresh (float) min_size (int)
maskrcnn_benchmark/modeling/rpn/inference.py:22
↓ 3 callersMethod__init__
(self, backbone, position_embedding)
groundingdino_new/models/GroundingDINO/backbone/backbone.py:147
↓ 3 callersFunction_accumulate_predictions_from_multiple_gpus
(predictions_per_gpu)
maskrcnn_benchmark/engine/inference.py:293
↓ 3 callersMethod_ensure_lineidx_loaded
(self)
maskrcnn_benchmark/data/datasets/tsv.py:129
↓ 3 callersFunction_get_activation_fn
Return an activation function given a string
groundingdino_new/models/GroundingDINO/utils.py:188
↓ 3 callersFunction_isArrayLike
(obj)
maskrcnn_benchmark/data/datasets/lvis.py:16
↓ 3 callersFunction_isArrayLike
(obj)
maskrcnn_benchmark/data/datasets/evaluation/lvis/lvis.py:14
↓ 3 callersMethod_load_helper
(self, _dict, ids)
maskrcnn_benchmark/data/datasets/lvis.py:122
↓ 3 callersMethod_load_helper
(self, _dict, ids)
maskrcnn_benchmark/data/datasets/evaluation/lvis/lvis.py:120
↓ 3 callersFunction_run
(command)
groundingdino_new/util/misc.py:365
↓ 3 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/modeling/rpn/qv_fuse.py:36
↓ 3 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/utils/fuse_helper_q.py:522
↓ 3 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/utils/fuse_helper.py:460
↓ 3 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/utils/fuse_helper_cat.py:467
↓ 3 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/utils/fuse_helper_sim.py:460
↓ 3 callersMethod_shape
(self, tensor: torch.Tensor, seq_len: int, bsz: int)
maskrcnn_benchmark/utils/fuse_helper_q_noparam.py:522
↓ 3 callersMethodadd_word
(self, word)
maskrcnn_benchmark/modeling/language_backbone/word_utils.py:20
↓ 3 callersFunctionboxlist_nms
Performs non-maximum suppression on a boxlist, with scores specified in a boxlist field via score_field. Arguments: boxlist
maskrcnn_benchmark/structures/boxlist_ops.py:10
↓ 3 callersFunctionbuild_model
(args, cfg)
groundingdino_new/models/__init__.py:11
↓ 3 callersFunctioncalc_tf_padding
Calculate TF-same like padding size. Parameters: ---------- x : tensor Input tensor. kernel_size : int C
maskrcnn_benchmark/modeling/backbone/efficientnet.py:40
↓ 3 callersFunctioncheck_for_positive_overflow
(target, ind_to_class, tokenizer, max_seq_length=256)
maskrcnn_benchmark/data/datasets/od_to_grounding.py:104
↓ 3 callersFunctionconv1x1_block
1x1 version of the standard convolution block. Parameters: ---------- in_channels : int Number of input channels.
maskrcnn_benchmark/modeling/backbone/efficientnet.py:147
↓ 3 callersFunctionconvert_grounding_to_od_logits
(logits, box_cls, positive_map, score_agg=None)
maskrcnn_benchmark/modeling/rpn/inference.py:772
↓ 3 callersFunctionconvert_object_detection_to_grounding_optimized_for_od
ind_to_class: {0: "__background__", 1 : "person" ...} target: restricted_negative_list : for datasets with restricted negatives, sam
maskrcnn_benchmark/data/datasets/od_to_grounding.py:149
↓ 3 callersFunctionconvert_to_xywh
(boxes)
maskrcnn_benchmark/data/datasets/evaluation/lvis/lvis_eval.py:998
↓ 3 callersFunctioncrop
(image, target, region)
groundingdino_new/datasets/transforms.py:17
↓ 3 callersFunctionexists
(val)
groundingdino_new/models/GroundingDINO/bertwarper.py:17
↓ 3 callersMethodextract_query
(self, samples=None, targets=None, query_images=None, # default_dict(list) ,list[tens
groundingdino_new/models/GroundingDINO/groundingdino.py:341
↓ 3 callersMethodforward
(self, input)
maskrcnn_benchmark/layers/misc.py:118
↓ 3 callersFunctiongeneralized_box_iou
Generalized IoU from https://giou.stanford.edu/ The boxes should be in [x0, y0, x1, y1] format Returns a [N, M] pairwise matrix, w
maskrcnn_benchmark/layers/set_loss.py:31
↓ 3 callersMethodget_ann_ids
Get ann ids that satisfy given filter conditions. Args: img_ids (int array): get anns for given imgs cat_ids (int a
maskrcnn_benchmark/data/datasets/lvis.py:72
↓ 3 callersMethodget_ann_ids
Get ann ids that satisfy given filter conditions. Args: img_ids (int array): get anns for given imgs cat_ids (int a
maskrcnn_benchmark/data/datasets/evaluation/lvis/lvis.py:70
↓ 3 callersFunctionget_same_padding_conv2d
Chooses static padding if you have specified an image size, and dynamic padding otherwise. Static padding is necessary for ONNX exporting of
maskrcnn_benchmark/modeling/backbone/efficientdet.py:609
↓ 3 callersFunctionimport_file
(module_name, file_path, make_importable=False)
maskrcnn_benchmark/utils/imports.py:12
↓ 3 callersMethodlegal
(self, cand)
maskrcnn_benchmark/engine/evolution.py:179
↓ 3 callersMethodload_anns
Load anns with the specified ids. If ids=None load all anns. Args: ids (int array): integer array of annotation ids Ret
maskrcnn_benchmark/data/datasets/lvis.py:130
↓ 3 callersMethodload_anns
Load anns with the specified ids. If ids=None load all anns. Args: ids (int array): integer array of annotation ids Ret
maskrcnn_benchmark/data/datasets/evaluation/lvis/lvis.py:128
↓ 3 callersFunctionmake_atss_loss_evaluator
(cfg, box_coder)
maskrcnn_benchmark/modeling/rpn/loss.py:1251
↓ 3 callersFunctionnested_tensor_from_tensor_list
(tensor_list: List[Tensor], image_sizes=None)
groundingdino_new/util/misc.py:474
↓ 3 callersMethodnum_rows
(self)
maskrcnn_benchmark/data/datasets/tsv.py:98
↓ 3 callersFunctionprint
(*args, **kwargs)
tools/test_grounding_net.py:70
↓ 3 callersFunctionprint
(*args, **kwargs)
maskrcnn_benchmark/utils/mdetr_dist.py:127
↓ 3 callersMethodprint_results
(self)
maskrcnn_benchmark/data/datasets/evaluation/lvis/lvis_eval.py:593
↓ 3 callersFunctionreduce_sum
(tensor)
maskrcnn_benchmark/utils/comm.py:148
↓ 3 callersFunctionsave_config
(cfg, path)
maskrcnn_benchmark/utils/miscellaneous.py:14
↓ 3 callersFunctionsmooth_l1_loss
very similar to the smooth_l1_loss from pytorch, but with the extra beta parameter
maskrcnn_benchmark/layers/smooth_l1_loss.py:6
↓ 3 callersFunctionsort_key_by_val
(dic)
maskrcnn_benchmark/data/datasets/vg.py:18
↓ 3 callersMethodstack_random_cand
(self, random_func, *, batchsize=10)
maskrcnn_benchmark/engine/evolution.py:221
↓ 3 callersMethodtext
(self)
groundingdino_new/util/slconfig.py:213
↓ 3 callersMethodupdate
(self, predictions)
maskrcnn_benchmark/data/datasets/refexp.py:32
↓ 3 callersMethodvalue
(self)
groundingdino_new/util/misc.py:89
↓ 3 callersMethodwith_pos_embed
(tensor, pos)
groundingdino_new/models/GroundingDINO/transformer.py:858
↓ 2 callersMethodNllSoftMaxLoss
(self, logits, target)
maskrcnn_benchmark/modeling/rpn/loss.py:584
↓ 2 callersMethod__get_negative_captions__
(self, idx, negative_size=7)
maskrcnn_benchmark/data/datasets/caption.py:108
↓ 2 callersMethod__getitem__
(self, idx)
maskrcnn_benchmark/data/datasets/caption.py:117
↓ 2 callersMethod__init__
Arguments: in_channels_list (list[int]): number of channels for each feature map that will be fed
maskrcnn_benchmark/modeling/backbone/fpn.py:13
↓ 2 callersMethod__init__
(self, cfg)
maskrcnn_benchmark/modeling/rpn/qv_fuse.py:186
↓ 2 callersMethod__init__
(self, cfg)
maskrcnn_benchmark/modeling/rpn/atss.py:16
← previousnext →101–200 of 2,105, ranked by callers