Check if the dataset format is compatible and upload it as W&B artifact arguments: opt (namespace)-- Commandline arguments f

Create and return W&B artifact containing W&B Table of the dataset. arguments: dataset -- instance of LoadImagesAndLabels cl

Backward iterator method, very common in C++, but not required in Python

Random access iterator methods, but not required in Python

download the model checkpoint artifact if the path starts with WANDB_ARTIFACT_PREFIX arguments: path -- path of the dataset

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

Log metrics if any and finish the current W&B run

Generate .txt labels recording img_names Args: src_path: dataset path containing images and labelTxt folders. out_path: output txt

:param imgids: integer ids specifying img :return: loaded img objects

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

Runs Non-Maximum Suppression (NMS) on inference results_obb Args: prediction (tensor): (b, n_all_anchors, [cx cy l s obj num_cls theta_cls

parse the dota ground truth in the format: [(x1, y1), (x2, y2), (x3, y3), (x4, y4)]

poly:[x0,y0,x1,y1,x2,y2,x3,y3] to rrect:[x_ctr,y_ctr,w,h,angle]

Pack 'void *' into a string buffer. */

Check type equivalence in a name list like <name1>|<name2>|... Return 0 if equal, -1 if nb < tb, 1 if nb > tb */

Check type equivalence in a name list like <name1>|<name2>|... Return 0 if not equal, 1 if equal */

Compare two type names skipping the space characters, therefore "char*" == "char *" and "Class<int>" == "Class<int >", etc. Return 0 when the two

split a single image and ground truth :param name: image name :param rate: the resize scale for the image :param

BufferFormatCheck */

BufferFormatCheck */