zhongyy / Face-Transformer

Face Transformer for Recognition
MIT License
252 stars 54 forks source link

What's the meaning of "The content of “property” file for “ms1m_retinaface” dataset is as follows: "93431,112,112"" #39

Open Cassieyy opened 1 year ago

Cassieyy commented 1 year ago

Hii, thank you for your excellent work! I used your shared code to train my personal dataset, but I am curious about the significance of the number "93431" in the "property" file for the "ms1m_retinaface" dataset.

The content of the file is as follows: "93431,112,112", where the last two numbers represent the image size after pre-processing. Could you please explain the meaning of the first number? Thank you in advance, and I look forward to your response!

huangwei2913 commented 1 year ago

In the numbers 93431, 112, 112, the first number represents the number of categories, the second number represents the width of the image, and the third number represents the height of the image.

Cassieyy commented 1 year ago

您的邮件已收到哦我会及时处理哒~

justin4ai commented 10 months ago

@huangwei2913 Hello, thanks for your information. So you mean first we need to download 24G dataset then extract some of them according to those numbers?

huangwei2913 commented 10 months ago

@justin4ai What I mean is that you can specify any number of images, as long as their image width and height are both the required 112 pixels for training.