Callback to Show speed.

Constructor of Microsoft COCO helper class for reading and visualizing annotations. :param annotation_file (str): location of annotat

Initialize CocoEval using coco APIs for gt and dt :param cocoGt: coco object with ground truth annotations :param cocoDt: coc

fill basic information to initialize imdb :param image_set: train or val or trainval or test :param root_path: 'cache' and 'r

basic information about an image database :param name: name of image database will be used for any output :param root_path: r

This Iter will provide roi data to Fast R-CNN network :param roidb: must be preprocessed :param batch_size: must divide BATCH

This Iter will provide roi data to Fast R-CNN network :param feat_sym: to infer shape of assign_output :param roidb: must be

This Iter will provide roi data to Fast R-CNN network :param feat_sym: to infer shape of assign_output :param roidb: must be

Accumulate per image evaluation results and store the result in self.eval :param p: input params for evaluation :return: None

Convert annotation which can be polygons, uncompressed RLE, or RLE to binary mask. :return: binary mask (numpy 2D array)

append flipped images to an roidb flip boxes coordinates, images will be actually flipped when loading into network :param ro

determine overlaps between boxes and query_boxes :param boxes: n * 4 bounding boxes :param query_boxes: k * 4 bounding boxes :return:

make a directory to store all caches :return: cache path

given ground truth, prepare roidb :param box_list: [image_index] ndarray of [box_index][x1, x2, y1, y2] :param gt_roidb: [ima

Download COCO images from mscoco.org server. :param tarDir (str): COCO results directory name imgIds (list): images to

visualize all detections in one image :param im_array: [b=1 c h w] in rgb :param detections: [ numpy.ndarray([[x1 y1 x2 y2 score]]) for j

Run per image evaluation on given images and store results (a list of dict) in self.evalImgs :return: None

perform evaluation for single category and image :return: dict (single image results)

remove roidb entries without usable rois

get top N ROIs, used in online hard example mining :param rois: all_rois [n, 4]; e2e: [n, 5] with batch_index :param rois_per_image: tota

return ground truth image regions database :return: imdb[image_index]['boxes', 'gt_classes', 'ins_id', 'ins_seg', 'gt_overlaps', 'fli

access image at index in image database :param index: image index in image database :return: image path

given image index, find out full path :param index: index of a specific image :return: full path of this image

Install monitor on all executors

Transform the set of class-agnostic boxes into class-specific boxes by applying the predicted offsets (box_deltas) :param boxes: !importa