Kornia v0.5.4 发布!新增多个数据增广 Container

来源: 投稿
作者: osc_35102927
2021-06-13

本次Kornia 的更新中,主要增加对Canny的支持以及新增了多种图像处理容器(例如,视频容器,图像增广容器)。

例如对于数据增广中的各种常见格式(mask, bbox, keypoints),以及图像变换的inverse:

aug_list = AugmentationSequential(
    K.ColorJitter(0.1, 0.1, 0.1, 0.1, p=1.0),
    K.RandomAffine(360, [0.1, 0.1], [0.7, 1.2], [30., 50.], p=1.0),
    K.RandomPerspective(0.5, p=1.0),
    data_keys=["input", "bbox", "keypoints", "mask"],  # Just to define the future input here.
    return_transform=False,
    same_on_batch=False,
)
# forward the operation
out_tensors = aug_list(img_tensor, bbox, keypoints, mask)
# Inverse the operation
out_tensor_inv = aug_list.inverse(*out_tensor)

此外,我们新增了PatchAugmentSequential来支持更多最新的图像增强方法。

[0.5.4] - 2021-06-11

Added

  • Add Canny edge detection (#1020)
  • Added Batched forward function (#1058)
  • Added denormalize homography function (#1061)
  • Added more augmentations containers (#1014)
  • Added calibration module and Undistort 2D points function (#1026)
  • Added patch augmentation container (#1095)

Fixed

Changed

  • Resize regardless of number of dims, considering the last two dims as image (#1047)
  • Raise error if converting to unit8 image to gray with float weights (#1057)
  • Filter 2D->2d, 3D->3d (#1069)
  • Removed augmentation functional module. (#1067)
  • Make Morphology compatible with both OpenCV and Scipy (#1084)
展开阅读全文
1 收藏
分享
加载中
更多评论
0 评论
1 收藏
分享
返回顶部
顶部