qianxiao111
qianxiao111
Hello, I have a question. How many images in the training dataset can be used to train an effective model? For example, domain X has 6000 undistorted images, domain Y...
If the source domain X contains high resolution images with a lot of scenes, such as animal, portraint, plant, landscape, architecture and so on, but the target domain Y contains...
If an image set A contains the undistorted images, image set B contains distorted images, which have different distorted types, such as gaussian blur, gaussian noise, JPEG, JP2K. The scenes...
when runing train_live.sh,the error is shown. Could you give me some advice? ![QQ图片20200812213238](https://user-images.githubusercontent.com/32053722/90065034-8d07b180-dce3-11ea-8809-b9956f39ea5d.png)
What is it about testing the same abnomal image with a trained model that gives different results(AUC) each time? How can I solve this problem? And, When a normal sample...