Closed Usriscedjdj closed 3 months ago
Before training the model, you should extract face landmarks and store such meta information in the JSON file for face alignment during the data preprocessing phase.
Thank you for your answer! Now I have encountered a new problem, after generating the json file, such an error is displayed, is there a problem with the generated file? Thank you so much!
It seems that the image type is None, which means your script has not successfully read the image data. Please check your image read function to make sure your image path is correct.
My F ++ data set has been converted to a picture, how should I modify the code? When modifying the generated json file, is the json file used for training?