Functions — github.com/WinstonJQ/YOLOv5-ROS

CodeHub MCPcopy Create free account

hub / github.com/WinstonJQ/YOLOv5-ROS / functions

Functions575 in github.com/WinstonJQ/YOLOv5-ROS

⨍ Functions 575◇ Types & classes 97 ↳ Endpoints 1

↓ 2 callersFunctiondownload_one

src/yolov5/utils/general.py:568

↓ 2 callersFunctionexif_transpose

Transpose a PIL image accordingly if it has an EXIF Orientation tag. Inplace version of https://github.com/python-pillow/Pillow/blob/master/s

src/yolov5/utils/dataloaders.py:69

↓ 2 callersFunctionexport_formats

src/yolov5/export.py:76

↓ 2 callersMethodfinish_run

src/yolov5/utils/loggers/comet/__init__.py:495

↓ 2 callersMethodfuse

src/yolov5/models/yolo.py:121

↓ 2 callersFunctionget_hash

src/yolov5/utils/dataloaders.py:51

↓ 2 callersFunctionget_run_info

src/yolov5/utils/loggers/wandb/wandb_utils.py:62

↓ 2 callersFunctiongithub_assets

(repository, version='latest')

src/yolov5/utils/downloads.py:69

↓ 2 callersFunctionimshow_cls

(im, labels=None, pred=None, names=None, nmax=25, verbose=False, f=Path('images.jpg'))

src/yolov5/utils/plots.py:391

↓ 2 callersFunctioninit_seeds

(seed=0, deterministic=False)

src/yolov5/utils/general.py:219

↓ 2 callersFunctionintersect_dicts

(da, db, exclude=())

src/yolov5/utils/general.py:234

↓ 2 callersFunctionis_docker

Check if the process runs inside a docker container.

src/yolov5/utils/general.py:81

↓ 2 callersFunctionis_kaggle

src/yolov5/utils/general.py:76

↓ 2 callersMethodis_within_threshold

判断目标是否在距离阈值范围内

src/filtered_target_tracker.py:64

↓ 2 callersMethodload_mosaic

src/yolov5/utils/dataloaders.py:664

↓ 2 callersMethodlog_asset_data

(self, asset, **kwargs)

src/yolov5/utils/loggers/comet/__init__.py:198

↓ 2 callersMethodlog_debug_samples

Log files (images) as debug samples in the ClearML task. arguments: files (List(PosixPath)) a list of file paths in PosixPat

src/yolov5/utils/loggers/clearml/clearml_utils.py:108

↓ 2 callersMethodlog_images

(self, files, name='Images', epoch=0)

src/yolov5/utils/loggers/__init__.py:356

↓ 2 callersMethodlog_model

(self, model_path, epoch=0, metadata={})

src/yolov5/utils/loggers/__init__.py:373

↓ 2 callersMethodlog_model

(self, path, opt, epoch, fitness_score, best_model=False)

src/yolov5/utils/loggers/comet/__init__.py:204

↓ 2 callersFunctionlog_tensorboard_graph

(tb, model, imgsz=(640, 640))

src/yolov5/utils/loggers/__init__.py:386

↓ 2 callersFunctionmain

(opt, callbacks=Callbacks())

src/yolov5/train.py:478

↓ 2 callersFunctionmain

src/yolov5/classify/train.py:296

↓ 2 callersMethodmap_val_table_path

Map the validation dataset Table like name of file -> it's id in the W&B Table. Useful for - referencing artifacts for evaluation.

src/yolov5/utils/loggers/wandb/wandb_utils.py:388

↓ 2 callersFunctionmodel_info

(model, verbose=False, imgsz=640)

src/yolov5/utils/torch_utils.py:271

↓ 2 callersFunctionnotebook_init

src/yolov5/utils/__init__.py:34

↓ 2 callersFunctionparse_opt

src/yolov5/train.py:432

↓ 2 callersMethodprint

src/yolov5/models/common.py:743

↓ 2 callersMethodprocess_batch

Return intersection-over-union (Jaccard index) of boxes. Both sets of boxes are expected to be in (x1, y1, x2, y2) format. Ar

src/yolov5/utils/metrics.py:134

↓ 2 callersFunctionprofile

YOLOv5 speed/memory/FLOPs profiler Usage: input = torch.randn(16, 3, 640, 640) m1 = lambda x: x * torch.sigmoid(x) m2 = n

src/yolov5/utils/torch_utils.py:150

↓ 2 callersFunctionsafe_download

(file, url, url2=None, min_bytes=1E0, error_msg='')

src/yolov5/utils/downloads.py:42

↓ 2 callersFunctionsave_one_box

(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=10, square=False, BGR=False, save=True)

src/yolov5/utils/plots.py:504

↓ 2 callersFunctionsmart_DDP

src/yolov5/utils/torch_utils.py:54

↓ 2 callersFunctionsmart_optimizer

(model, name='Adam', lr=0.001, momentum=0.9, decay=1e-5)

src/yolov5/utils/torch_utils.py:317

↓ 2 callersFunctionsmooth

src/yolov5/utils/metrics.py:23

↓ 2 callersFunctiontrain

(hyp, opt, device, callbacks)

src/yolov5/train.py:68

↓ 2 callersMethodupdate_target

使用指数平滑更新目标位置

src/filtered_target_tracker.py:71

↓ 2 callersFunctionxyn2xy

(x, w=640, h=640, padw=0, padh=0)

src/yolov5/utils/general.py:738

↓ 1 callersMethod__call__

(self, i, bgr=False)

src/yolov5/utils/plots.py:42

↓ 1 callersMethod__iter__

src/yolov5/utils/dataloaders.py:223

↓ 1 callersMethod_clip_augmented

src/yolov5/models/yolo.py:222

↓ 1 callersMethod_descale_pred

(self, p, flips, scale, img_size)

src/yolov5/models/yolo.py:205

↓ 1 callersMethod_find_yaml

src/yolov5/utils/dataloaders.py:984

↓ 1 callersMethod_forward_augment

src/yolov5/models/yolo.py:191

↓ 1 callersMethod_from_detection_model

(self, model, nc=1000, cutoff=10)

src/yolov5/models/yolo.py:253

↓ 1 callersMethod_from_yaml

src/yolov5/models/yolo.py:268

↓ 1 callersMethod_get_experiment

(self, mode, experiment_id=None)

src/yolov5/utils/loggers/comet/__init__.py:160

↓ 1 callersMethod_initialize_biases

(self, cf=None)

src/yolov5/models/yolo.py:233

↓ 1 callersMethod_load_metadata

(f=Path('path/to/meta.yaml'))

src/yolov5/models/common.py:574

↓ 1 callersMethod_make_grid

(self, nx=20, ny=20, i=0, torch_1_10=check_version(torch.__version__, '1.10.0'))

src/yolov5/models/yolo.py:79

↓ 1 callersMethod_make_grid

src/yolov5/models/tf.py:316

↓ 1 callersMethod_model_type

(p='path/to/model.pt')

src/yolov5/models/common.py:562

↓ 1 callersMethod_nms

(x, topk_all=100, iou_thres=0.45, conf_thres=0.25)

src/yolov5/models/tf.py:480

↓ 1 callersMethod_profile_one_layer

(self, m, x, dt)

src/yolov5/models/yolo.py:108

↓ 1 callersMethod_unzip

src/yolov5/utils/dataloaders.py:994

↓ 1 callersMethod_xywh2xyxy

src/yolov5/models/tf.py:464

↓ 1 callersMethodadd_assets_to_artifact

(self, artifact, path, asset_path, split)

src/yolov5/utils/loggers/comet/__init__.py:302

↓ 1 callersMethodadd_label_to_image

在图像上添加标注

src/replay_private.py:61

↓ 1 callersMethodadd_label_to_image

在图像上添加标注

src/replay.py:51

↓ 1 callersFunctionap_per_class

Compute the average precision, given the recall and precision curves. Source: https://github.com/rafaelpadilla/Object-Detection-Metrics. # Ar

src/yolov5/utils/metrics.py:31

↓ 1 callersFunctionaugment_hsv

(im, hgain=0.5, sgain=0.5, vgain=0.5)

src/yolov5/utils/augmentations.py:66

↓ 1 callersFunctionautobatch

(model, imgsz=640, fraction=0.8, batch_size=16)

src/yolov5/utils/autobatch.py:21

↓ 1 callersFunctionbbox_iou

(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7)

src/yolov5/utils/metrics.py:224

↓ 1 callersFunctionbox_candidates

(box1, box2, wh_thr=2, ar_thr=100, area_thr=0.1, eps=1e-16)

src/yolov5/utils/augmentations.py:298

↓ 1 callersMethodbuild_targets

(self, p, targets)

src/yolov5/utils/loss.py:177

↓ 1 callersFunctionbutter_lowpass

(cutoff, fs, order)

src/yolov5/utils/plots.py:174

↓ 1 callersMethodcache_labels

(self, path=Path('./labels.cache'), prefix='')

src/yolov5/utils/dataloaders.py:520

↓ 1 callersFunctioncheck_amp

src/yolov5/utils/general.py:520

↓ 1 callersFunctioncheck_anchors

(dataset, model, thr=4.0, imgsz=640)

src/yolov5/utils/autoanchor.py:30

↓ 1 callersFunctioncheck_comet_resume

Restores run parameters to its original state based on the model checkpoint and logged Experiment parameters. Args: opt (argparse.Nam

src/yolov5/utils/loggers/comet/comet_utils.py:124

↓ 1 callersMethodcheck_dataset

(self, data_file)

src/yolov5/utils/loggers/comet/__init__.py:226

↓ 1 callersFunctioncheck_pil_font

(font=FONT, size=10)

src/yolov5/utils/plots.py:54

↓ 1 callersFunctioncheck_python

(minimum='3.7.0')

src/yolov5/utils/general.py:327

↓ 1 callersFunctioncheck_train_batch_size

(model, imgsz=640, amp=True)

src/yolov5/utils/autobatch.py:15

↓ 1 callersFunctioncheck_wandb_resume

src/yolov5/utils/loggers/wandb/wandb_utils.py:71

↓ 1 callersFunctionclassify_albumentations

(augment=True, size=224, scale=(0.08, 1.0),

src/yolov5/utils/augmentations.py:306

↓ 1 callersFunctionclean_str

src/yolov5/utils/general.py:622

↓ 1 callersFunctioncoco80_to_coco91_class

src/yolov5/utils/general.py:684

↓ 1 callersFunctioncompute_ap

Compute the average precision, given the recall and precision curves # Arguments recall: The recall curve (list) precision: Th

src/yolov5/utils/metrics.py:98

↓ 1 callersFunctionconstruct_dataset

Load in a clearml dataset and fill the internal data_dict with its contents.

src/yolov5/utils/loggers/clearml/clearml_utils.py:19

↓ 1 callersFunctioncopy_paste

(im, labels, segments, p=0.5)

src/yolov5/utils/augmentations.py:239

↓ 1 callersFunctioncreate_dataset_artifact

src/yolov5/utils/loggers/wandb/log_dataset.py:10

↓ 1 callersFunctiondenormalize

(x, mean=IMAGENET_MEAN, std=IMAGENET_STD)

src/yolov5/utils/augmentations.py:59

↓ 1 callersMethoddownload_dataset_artifact

(self, artifact_path)

src/yolov5/utils/loggers/comet/__init__.py:343

↓ 1 callersMethoddownload_model_artifact

download the model checkpoint artifact if the resume path starts with WANDB_ARTIFACT_PREFIX arguments: opt (namespace) -- Co

src/yolov5/utils/loggers/wandb/wandb_utils.py:287

↓ 1 callersMethodend_epoch

commit the log_dict, model artifacts and Tables to W&B and flush the log_dict. arguments: best_result (boolean): Boolean rep

src/yolov5/utils/loggers/wandb/wandb_utils.py:526

↓ 1 callersFunctionexif_size

src/yolov5/utils/dataloaders.py:59

↓ 1 callersFunctionexport_coreml

(model, im, file, int8, half, prefix=colorstr('CoreML:'))

src/yolov5/export.py:215

↓ 1 callersFunctionexport_edgetpu

(file, prefix=colorstr('Edge TPU:'))

src/yolov5/export.py:397

↓ 1 callersFunctionexport_engine

(model, im, file, half, dynamic, simplify, workspace=4, verbose=False, prefix=colorstr('TensorRT:'))

src/yolov5/export.py:238

↓ 1 callersFunctionexport_openvino

(file, metadata, half, prefix=colorstr('OpenVINO:'))

src/yolov5/export.py:185

↓ 1 callersFunctionexport_paddle

(model, im, file, metadata, prefix=colorstr('PaddlePaddle:'))

src/yolov5/export.py:200

↓ 1 callersFunctionexport_pb

(keras_model, file, prefix=colorstr('TensorFlow GraphDef:'))

src/yolov5/export.py:349

↓ 1 callersFunctionexport_saved_model

(model, im, file, dynamic,

src/yolov5/export.py:301

↓ 1 callersFunctionexport_tfjs

(file, prefix=colorstr('TensorFlow.js:'))

src/yolov5/export.py:422

↓ 1 callersFunctionexport_tflite

(keras_model, im, file, int8, data, nms, agnostic_nms, prefix=colorstr('TensorFlow Lite:'))

src/yolov5/export.py:366

↓ 1 callersFunctionexport_torchscript

(model, im, file, optimize, prefix=colorstr('TorchScript:'))

src/yolov5/export.py:113

↓ 1 callersFunctionfeature_visualization

x: Features to be visualized module_type: Module type stage: Module stage within model n: Maxim

src/yolov5/utils/plots.py:132

↓ 1 callersFunctionfile_date

(path=__file__)

src/yolov5/utils/general.py:262

↓ 1 callersMethodforward

(self, x, augment=False, profile=False, visualize=False)

src/yolov5/models/yolo.py:186

← previous next →101–200 of 575, ranked by callers