ap = voc_ap(rec, prec, [use_07_metric]) Compute VOC AP given precision and recall. If use_07_metric is true, uses the VOC 07 11 point met

rec, prec, ap = voc_eval(detpath, annopath, imagesetfile,

Arguments: target (annotation) : the target annotation to be made usable will be an ET.Element Returns:

M2Det: Multi-level Multi-scale single-shot object Detector

Create a summary writer logging to log_dir.

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

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

Generate argparser from config file automatically (experimental)

Convert prior_boxes to (cx, cy, w, h) representation for comparison to center-size form ground truth data. Args: boxes: (tensor) poin

Decode locations from predictions using priors to undo the encoding we did for offset regression at train time. Args: loc (tensor): lo

Custom collate fn for dealing with batches of images that have a different number of associated object annotations (bounding boxes). Argument

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

Encode the variances from the priorbox layers into the ground truth boxes we have matched (based on jaccard overlap) with the prior boxes. Arg

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

all_boxes is a list of length number-of-classes. Each list element is a list of length number-of-images. Each of those list e

Multibox Loss Args: predictions (tuple): A tuple containing loc preds, conf preds, and prior boxes from SSD net.

Args: loc_data: (tensor) Loc preds from loc layers Shape: [batch,num_priors*4] conf_data: (tensor) Sh

Log a histogram of the tensor of values.

Log a list of images.

Print information about the annotation file. :return:

Apply non-maximum suppression at test time to avoid detecting too many overlapping bounding boxes for a given object. Args: boxes: (te

Returns the original annotation of image at index Note: not using self.__getitem__(), as any transformations passed in could mess up

Returns the original image at an index in tensor form Note: not using self.__getitem__(), as any transformations passed in could mess

Returns the original image at an index in tensor form Note: not using self.__getitem__(), as any transformations passed in could mess

Pure Python NMS baseline.

Constructs a ResNet-101 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-152 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-18 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-34 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet

Constructs a ResNet-50 model. Args: pretrained (bool): If True, returns a model pre-trained on ImageNet