Removes detections with lower object confidence score than 'conf_thres' and performs Non-Maximum Suppression to further filter detections.

Parses the yolo-v3 layer configuration file and returns module definitions

Get one generated image, and adapt it to the target scale

Get a batch of images and do the postprocessing

Read an image from a file. This function reads an image from given file. The image is CHW format and the range of its value is :math:`[0, 255

Save trained model.

Return: total_loss: the total loss during training accuracy: the mAP

In the current version, the validate dataset hasn't been set, so we use the first 500 samples of testing set instead.

Visualize bounding boxes inside image. Args: img (~numpy.ndarray): An array of shape :math:`(3, height, width)`. This is in R

Visualize a color image. Args: img (~numpy.ndarray): An array of shape :math:`(3, height, width)`. This is in RGB format and

Assigns ground truth to sampled proposals. This function samples total of :obj:`self.n_sample` RoIs from the combination of :obj:`roi

Assign ground truth supervision to sampled subset of anchors. Types of input arrays and output arrays are same. Here are notations.

input should be ndarray Propose RoIs. Inputs :obj:`loc, score, anchor` refer to the same anchor when indexed by the same ind

Parameters ---------- data_dir: the directory where NUS-WIDE data located. binary_top_k_classes: load data of top k c

Inputs: model: should be a python class refering to pytorch model (torch.nn.Module) data_collected: a list with train