Args: in_channels (int): Input channels. num_classes (int, optional): Defaults to 2 (background and pedestrian).

Run all_gather on arbitrary picklable data (not necessarily tensors) Args: data: any picklable object Returns: list[dat

gallery_dataset/query_dataset: an instance of BaseDataset gallery_det (list of ndarray): n_det x [x1, x2, y1, y2, score] per image galler

gallery_det (list of ndarray): n_det x [x1, x2, y1, y2, score] per image gallery_feat (list of ndarray): n_det x D features per image que

Arguments: features (List[Tensor]) boxes (List[Tensor[N, 4]]) image_shapes (List[Tuple[H, W]])

Arguments: featmaps: OrderedDict[Tensor], and in featmap_names you can choose which featmaps to use

Args: inputs: feature matrix with shape (batch_size, feat_dim). labels: ground truth labels with shape (num_classes).

Warning: does not synchronize the deque!