Replies: 1 comment
-
hi @cucum13er
|
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
What's the feature?
我最近在做的项目需要用到一个特殊的dataset,写了一个结构如下:
dataset的输出是{lr, ref-hr, hr},分别代表了low-resolution, reference-high-resolution, 和high-resolution images
然后在preprocessor的过程中,我发现其中有两个key可以选,一个是在config里面的pipeline,另一个是preprocessor的data_keys参数
例如我在config里面是这样写的:
dict(type='PackInputs',
keys=['lr', 'ref', 'hr', 'regis'],
meta_keys=['lr_path', 'ref_path', 'hr_path'],
data_keys=['lr', 'ref', 'hr', 'regis']
)
我发现在forward_train里面(base_edit_model.py)有两个输入,把inputs和data_samples都在模型里面。请问我应该用哪个train比较好?(keys好像会被打包进inputs, data_keys会被打包在data_samples)
谢谢!
Any other context?
No response
Beta Was this translation helpful? Give feedback.
All reactions