I-NAS for HSI classification.Require: Initialize number of training group , validation group , and operation set . | 1: for each pixel do | 2: Create the index according to each class of label. | 3: end for | 4: split the sample set carrying position information into training, validation and test dataset according to and . | 5: Mask the training, validation and test dataset respectively. | 6: Architecture search phase: | 7: initialize search epochs, learning rate and , the architecture variable , and the CNN weight . | 8: for every search epoch do | 9: ; | 10: . | 11: end for | 12: choose the best according to the performance on validation dataset. | 13: according to , acquire the best I-NAS architecture . | 14: Train and test the optimal I-NAS: | 15: initialize training epochs, the weight of and learning rate . | 16: for every training epoch do | 17: . | 18: end for | 19: for every test epoch do | 20: according to test dataset carrying position information, acquire the predict by I-NAS. | 21: end for | 22: obtain OA, AA, Kappa by evaluating the predict and test labels. |
|