Open richmondu opened 5 years ago
Should it be like this?Looking forward to the author's answer
Hello,
I am not allowed to share the .csv files to train the classifiers. These public databases should be downloaded from the corresponding providers (e.g.: Replay-Attack, Print-Attack).
@ifcoxs Yes it should be like that.
Regards,
应该是这样吗?期待作者的回答 你好,请问你的csv文件是从哪里下载的,可以分享一下吗
@lunana123 这个是用数据集生成的文件。通过main.py中获取摄像头的图像,然后提取特征的方法,可以推出作者提取了哪些特征向量以及提取方式;通过training_script.py中load_data(path_name, n_rows, n_cols)函数可以推出他是如何组织csv文件,然后送进分类器进行训练的。 我是这么理解的!
@lunana123, @ifcoxs can you tell the difference between the label(y_train) and pai_id(PAI_ID).
Thanks
@ee09115 since you are not allowed to share csv, could you explain on how to generate our own ones please ? Or at least give a fake sample of what should be placed there
Can you provide the CSV file training data used for training_script.py? joblib could not load the classifiers in Raspberry Pi 3B+ due to scikit-learn incompatible versions. I need to use scikit-learn 0.20.2 instead of 0.19.1 so I need to train the classifier with this version.
Thank you!