Blend image1 and image2 using 'factor'. Factor can be above 0.0. A value of 0.0 means only image1 is used. A value of 1.0 means only image

Get colormap The code of this function is copied from https://github.com/facebookresearch/Detectron/blob/main/detectron/utils/colormap.py

This function generates a header file containing the data from the numpy array provided.

It takes a mask and a bounding box, and returns a mask that is cropped to the bounding box Args: masks (paddle.Tensor): [h, w, n] tens

It takes a mask and a bounding box, and returns a mask that is cropped to the bounding box Args: masks (paddle.Tensor): [h, w, n] tens

Default batch collating function for :code:`paddle.io.DataLoader`, get input data as a list of sample datas, each element in list if the

PicoDet decode

process cpu data frame, merge by 'model_name', 'batch_size' Args: cpu_df ([type]): [description]

r""" Args: metrics (Tensor, float32): shape[B, n, L], n: num_gts, L: num_anchors topk (int): The number of top elements to look fo

Get the affine transform matrix, given the center/scale/rot/output_size. Args: center (np.ndarray[2, ]): Center of the bounding box (x, y

Args: num_classes (int): number of class Returns: color_map (list): RGB color list

Get result at the stage of inference. The output format is dictionary containing bbox or mask result. For example, bbox result is a list

Download from given url to root_dir. if file or directory specified by url is exists under root_dir, return the path directly, otherwise down

generate sine position embedding from a position tensor Args: pos_tensor (Tensor): Shape as `(None, n)`. num_pos_feats (int): pro

Inverse function of sigmoid. Args: x (Tensor): The tensor to do the inverse. eps (float): EPS avoid numerical

Modified tensor inspace using ones_ Args: tensor (paddle.Tensor): paddle Tensor Return: tensor

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

Visualization MaskDetector results

Pad image to a specified size. Args: size (list[int]): image target size fill_value (list[float]): rgb value

Pad image to a specified size. Args: size (list[int]): image target size fill_value (list[float]): rgb value

Pad image to a specified size. Args: size (list[int]): image target size fill_value (list[float]): rgb value

Pad image to a specified size. Args: size (list[int]): image target size fill_value (list[float]): rgb value

Check if user define dataset exists