MCPcopy Create free account

hub / github.com/MasterBin-IIAU/Unicorn / functions

Functions1,452 in github.com/MasterBin-IIAU/Unicorn

⨍ Functions 1,452◇ Types & classes 215↳ Endpoints 16
↓ 221 callersFunctionprint
(*args, **kwargs)
external/lib/utils/misc.py:369
↓ 83 callersMethodcopy
(self)
external/lib/utils/tensor.py:14
↓ 79 callersMethodget
(self, name, frame_num=None)
external/lib/test/evaluation/data.py:142
↓ 76 callersMethodmax
(self)
external/lib/utils/misc.py:72
↓ 54 callersMethodwrite
(self, buf)
unicorn/utils/logger.py:43
↓ 49 callersMethodto
(self, device)
external/lib/utils/misc.py:288
↓ 45 callersMethodload
(self, gen_meta: Path)
external/lib/train/dataset/vos_base.py:26
↓ 29 callersMethodeval
(self, model, evaluator, weights)
unicorn/exp/base_exp.py:51
↓ 28 callersFunctionget_unicorn_datadir
get dataset dir of Unicorn. If environment variable named `UNICORN_DATADIR` is set, this function will return value of the environment variab
unicorn/data/dataloading.py:26
↓ 21 callersMethodupdate
(self, **kwargs)
external/lib/utils/misc.py:163
↓ 20 callersFunctiontime_synchronized
pytorch-accurate time
unicorn/utils/dist.py:281
↓ 19 callersMethod_iterable
(a)
external/lib/utils/tensor.py:35
↓ 17 callersMethodapply
(self, fn, *args, **kwargs)
external/lib/utils/tensor.py:31
↓ 16 callersFunctionis_main_process
()
unicorn/utils/dist.py:123
↓ 15 callersMethodupdate
(self, model)
unicorn/utils/ema.py:50
↓ 12 callersFunctionpreproc
add padding and swap dimension
unicorn/data/data_augment.py:194
↓ 12 callersMethodsave
(self, gen_meta: Path)
external/lib/train/dataset/vos_base.py:22
↓ 11 callersFunctionpostprocess
(prediction, num_classes, conf_thre=0.7, nms_thre=0.45, class_agnostic=False)
unicorn/utils/boxes.py:33
↓ 11 callersFunctionsynchronize
Helper function to synchronize (barrier) among all processes when using distributed training
unicorn/utils/dist.py:68
↓ 10 callersFunctionenv_settings
()
external/lib/test/evaluation/environment.py:107
↓ 10 callersFunctionget_exp
get Exp object by file or name. If exp_file and exp_name are both provided, get Exp by exp_file. Args: exp_file (str): file path
unicorn/exp/build.py:35
↓ 9 callersMethodempty
(self)
unicorn/tracker/quasi_dense_embed_tracker.py:44
↓ 9 callersFunctiongather
Run gather on arbitrary picklable data (not necessarily tensors). Args: data: any picklable object dst (int): destination ra
unicorn/utils/dist.py:224
↓ 9 callersMethodget_model
(self)
unicorn/exp/base_exp.py:27
↓ 9 callersFunctionload_text
(path, delimiter=' ', dtype=np.float32, backend='numpy')
external/lib/test/utils/load_text.py:37
↓ 9 callersMethodmerge
(self, cfg_list)
unicorn/exp/base_exp.py:63
↓ 9 callersFunctionpostprocess_inst
outputs: (bs, n_anchor_all, 85), locations: (n_anchor_all, 2), dynamic_params: (bs, n_anchor_all, 169) fpn_levels: (bs, n_anchor_all), mask_f
unicorn/utils/boxes.py:80
↓ 9 callersFunctiontest_task
(task, gt_set, res_path, J_target=None, F_target=None, metric=('J', 'F'))
external/davis2017-evaluation/pytest/test_evaluation.py:17
↓ 8 callersMethodclear
(self)
unicorn/utils/metric.py:94
↓ 8 callersMethodflush
(self)
unicorn/utils/logger.py:53
↓ 8 callersFunctionget_local_rank
Returns: The rank of the current process within the local (per-machine) process group.
unicorn/utils/dist.py:98
↓ 8 callersMethodtrack
Overload this function in your tracker. This should track in the frame and update the model.
external/lib/test/tracker/basetracker.py:18
↓ 8 callersFunctionxyxy2cxcywh
(bboxes)
unicorn/utils/boxes.py:205
↓ 7 callersMethodget_sequences
(self)
external/davis2017-evaluation/davis2017/davis.py:100
↓ 7 callersMethodpull_item
idx is invalid
unicorn/data/datasets/lasot.py:176
↓ 7 callersMethodtrain
(self)
unicorn/core/trainer.py:90
↓ 6 callersMethod__init__
(self, in_channels, out_channels, ksize=1, stride=1, act="silu")
unicorn/models/backbone/network_blocks.py:191
↓ 6 callersMethod__init__
(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.)
unicorn/models/backbone/swin_transformer.py:21
↓ 6 callersFunctionbitget
(byteval, idx)
external/davis2017-evaluation/davis2017/utils.py:16
↓ 6 callersMethodcopy
(self)
external/lib/test/evaluation/data.py:168
↓ 6 callersFunctionwrite_results
(filename, results)
unicorn/evaluators/mot_evaluator.py:49
↓ 6 callersFunctionxyxy2xywh
(bbox)
external/qdtrack/qdtrack/core/evaluation/mot_pcan.py:13
↓ 5 callersMethod__init__
(self, *transforms)
external/lib/train/data/transforms.py:35
↓ 5 callersMethod_get_sequence_path
(self, seq_id)
unicorn/data/datasets/lasot.py:109
↓ 5 callersFunctionbuild_dataloader
Build PyTorch DataLoader. In distributed training, each GPU/process has a dataloader. In non-distributed training, there is only one dataload
external/qdtrack/qdtrack/datasets/builder.py:13
↓ 5 callersFunctioncal_similarity
(key_embeds, ref_embeds, method='dot_product', temper
external/qdtrack/qdtrack/core/track/similarity.py:5
↓ 5 callersFunctionconvert_bn_model_to_gn
Recursively traverse module and its children to replace all instances of ``torch.nn.modules.batchnorm._BatchNorm`` with :class:`torch.nn.Grou
unicorn/exp/unicorn_det.py:321
↓ 5 callersMethodconvert_to_coco_format
(self, outputs, info_imgs, ids)
unicorn/evaluators/mot_evaluator.py:616
↓ 5 callersFunctionenv_settings
()
external/lib/train/admin/environment.py:39
↓ 5 callersMethodevaluate
(self, results, metric=['track'], logger=None,
external/qdtrack/qdtrack/datasets/tao_dataset.py:176
↓ 5 callersMethodevaluate_prediction
(self, data_dict, statistics)
unicorn/evaluators/mot_evaluator.py:648
↓ 5 callersMethodformat_results
Format the results to json (standard format for COCO evaluation). Args: results (list[tuple | numpy.ndarray]): Testing results of
external/qdtrack/qdtrack/datasets/tao_dataset.py:139
↓ 5 callersFunctionget_world_size
()
unicorn/utils/dist.py:82
↓ 5 callersFunctionimshow_tracklets
(img, bboxes, labels=None, ids=None,
external/qdtrack/qdtrack/models/trackers/tao_tracker.py:337
↓ 5 callersFunctionislist
(a)
external/lib/utils/tensor.py:221
↓ 5 callersMethodmake_group_layer
starts with conv layer then has `num_blocks` `ResLayer`
unicorn/models/backbone/darknet.py:59
↓ 5 callersMethodupdate
(self, val)
external/lib/train/admin/stats.py:14
↓ 4 callersMethod__init__
(self, loader)
unicorn/data/data_prefetcher.py:23
↓ 4 callersFunction_convert_dict
(input_dict)
external/lib/test/evaluation/running.py:41
↓ 4 callersMethod_get_frame
(self, seq_path, frame_id)
unicorn/data/datasets/got10k.py:179
↓ 4 callersMethod_get_frame
(self, seq_path, frame_id)
unicorn/data/datasets/lasot.py:142
↓ 4 callersMethod_get_sequence_path
(self, seq_id)
unicorn/data/datasets/got10k.py:149
↓ 4 callersMethod_make_layer
(self, block, planes, blocks, stride=1, dilate=False)
unicorn/models/backbone/resnet.py:182
↓ 4 callersFunction_mirror
(image, boxes, prob=0.5, mask=None)
unicorn/data/data_augment.py:170
↓ 4 callersFunction_mirror_joint
(image, boxes, mask=None)
unicorn/data/data_augment.py:183
↓ 4 callersFunction_resnet
(arch, block, layers, pretrained, progress, **kwargs)
unicorn/models/backbone/resnet.py:230
↓ 4 callersMethodaccumulate
Accumulate per image evaluation results and store the result in self.eval. Does not support changing parameter settings from those u
unicorn/layers/fast_coco_eval_api.py:124
↓ 4 callersFunctionaggregate_eval_results
(summary, metrics, cats, mh,
external/qdtrack/qdtrack/core/evaluation/mot_pcan.py:106
↓ 4 callersFunctionaugment_hsv
(img, hgain=0.015, sgain=0.7, vgain=0.4)
unicorn/data/data_augment.py:21
↓ 4 callersMethodbackward
(ctx, grad)
unicorn/models/condinst/conv_with_kaiming_uniform.py:120
↓ 4 callersFunctionbboxes_iou
(bboxes_a, bboxes_b, xyxy=True)
unicorn/utils/boxes.py:154
↓ 4 callersFunctionbuild_position_encoding
(hidden_dim=256, sz=40)
unicorn/models/position_encoding.py:39
↓ 4 callersFunctiondb_eval_boundary
(annotation, segmentation, void_pixels=None, bound_th=0.008)
external/davis2017-evaluation/davis2017/metrics.py:40
↓ 4 callersMethodevaluate
COCO average precision (AP) Evaluation. Iterate inference on the test dataset and the results are evaluated by COCO API. NOT
unicorn/evaluators/bdd_evaluator.py:56
↓ 4 callersFunctionfuse_model
(model)
unicorn/utils/model_utils.py:66
↓ 4 callersMethodget_all_masks
(self, sequence, separate_objects_masks=False)
external/davis2017-evaluation/davis2017/davis.py:83
↓ 4 callersMethodget_eval_loader
(self, batch_size, is_distributed, testdev=False, legacy=False)
unicorn/exp/unicorn_det.py:273
↓ 4 callersFunctionget_label_map
boxes: (bs, 4)
unicorn/models/unicorn.py:521
↓ 4 callersFunctionget_num_devices
()
unicorn/utils/dist.py:41
↓ 4 callersFunctionget_prec_curve
(ave_success_rate_plot_center, valid_sequence)
external/lib/test/analysis/plot_results.py:207
↓ 4 callersFunctionget_root_logger
(log_file=None, log_level=logging.INFO)
external/qdtrack/qdtrack/utils/logger.py:6
↓ 4 callersMethodinitialize
Overload this function in your tracker. This should initialize the model.
external/lib/test/tracker/basetracker.py:14
↓ 4 callersMethodinitialize_biases
(self, prior_prob)
unicorn/models/unicorn_head.py:230
↓ 4 callersFunctionlaunch
Args: main_func: a function that will be called by `main_func(*args)` num_machines (int): the total number of machines ma
unicorn/core/launch.py:39
↓ 4 callersFunctionload_checkpoint
(ckpt_path, model)
unicorn/models/backbone/swin_transformer.py:632
↓ 4 callersFunctionplot_draw_save
(y, x, scores, trackers, plot_draw_styles, result_plot_path, plot_opts)
external/lib/test/analysis/plot_results.py:102
↓ 4 callersMethodpreprocess
(self, inputs, targets, tsize)
unicorn/exp/unicorn_det.py:232
↓ 4 callersFunctionsave_bb
(file, data)
external/lib/test/evaluation/running.py:29
↓ 4 callersMethodsave_ckpt
(self, ckpt_name, update_best_ckpt=False)
unicorn/core/trainer.py:528
↓ 4 callersFunctionsetup_logger
setup logger for training and testing. Args: save_dir(str): location to save log file distributed_rank(int): device rank when mult
unicorn/utils/logger.py:63
↓ 4 callersMethodtlwh_to_xyah
Convert bounding box to format `(center x, center y, aspect ratio, height)`, where the aspect ratio is `width / height`.
unicorn/tracker/byte_tracker.py:117
↓ 4 callersMethodupdate
Update a matched track :type new_track: STrack :type frame_id: int :type update_feature: bool :return:
unicorn/tracker/byte_tracker.py:73
↓ 4 callersFunctionwait_for_the_master
Make all processes waiting for the master to do some task.
unicorn/utils/dist.py:52
↓ 4 callersFunctionwrite_results_no_score
(filename, results)
unicorn/evaluators/mot_evaluator.py:62
↓ 3 callersMethod__call__
(self, results)
external/qdtrack/qdtrack/datasets/pipelines/transforms.py:87
↓ 3 callersMethod__init__
(self, *args, **kwargs)
external/qdtrack/qdtrack/datasets/pipelines/transforms.py:84
↓ 3 callersMethod__init__
(self, d_model=256)
unicorn/models/deformable_transformer.py:193
↓ 3 callersFunction_get_global_gloo_group
Return a process group based on gloo backend, containing all the ranks The result is cached.
unicorn/utils/dist.py:128
↓ 3 callersMethod_read_bb_anno
(self, seq_path)
unicorn/data/datasets/got10k.py:129
↓ 3 callersMethod_read_bb_anno
(self, seq_path)
unicorn/data/datasets/lasot.py:90
next →1–100 of 1,452, ranked by callers