Skip to content
This repository has been archived by the owner on Jun 13, 2024. It is now read-only.

关于数据增强的疑惑。 #167

Open
YuQi9797 opened this issue Jul 19, 2021 · 0 comments
Open

关于数据增强的疑惑。 #167

YuQi9797 opened this issue Jul 19, 2021 · 0 comments

Comments

@YuQi9797
Copy link

作者您好,关于数据增强,我想请教下。
https://github.com/microsoft/human-pose-estimation.pytorch/blob/master/experiments/coco/resnet50/384x288_d256x3_adam_lr1e-3.yaml#L14
配置文件中,ROT_FACTOR: 40SCALE_FACTOR: 0.3
然后数据集处理过程中
https://github.com/microsoft/human-pose-estimation.pytorch/blob/master/lib/dataset/JointsDataset.py#L93
s = s * np.clip(np.random.randn()*sf + 1, 1 - sf, 1 + sf)
r = np.clip(np.random.randn()*rf, -rf*2, rf*2) \ if random.random() <= 0.6 else 0

请问这里是否就是指的是数据随即缩放(1-0.3, 1+0.3) 即 随机缩放([0.7, 1.3]),同时随机旋转([-80°, 80°])呢?

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant