

The source code for CNN and FCN is adjusted for the training set path and can be used directly.
The training set is as follows:
We split the training set (S1) into 4 parts.
The file "S1_CNN_Training set" contains the dataset required for CNN training, which has already been classified and can be used directly.

File "S1_FCN_Training set_Label" contains the labels required for FCN model training;
The two files of 'S1 _ FCN _ Training set _ Set _ 1 ' and 'S1 _ FCN _ Training set _ Set _ 2 ' together contain 1400 images required for FCN model training, which need to be combined into one piece after downloading.

The "Improved_restnet-net50" model is required to run AMBBEM.