zilongzhong / SSRN

This is a tensorflow and keras based implementation of SSRNs in the IEEE T-GRS paper "Spectral-Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework".
Other
211 stars 74 forks source link

Use of index to assignment #10

Open sandeep-25 opened 5 years ago

sandeep-25 commented 5 years ago

Can you please tell the use of the following code:- assign_0 = value // Col + pad_length assign_1 = value % Col + pad_length new_assign[counter] = [assign_0, assign_1]

zilongzhong commented 5 years ago

These snippets are used for indexing newly sampled HSI cuboids.

TanmDL commented 5 years ago

okay, I got it. You are just converting the selected indices into specific image location in row and coloumn space. for an example, t = np.arange(16).reshape(4,4) indices = 7 # was selected for train the original image location of 7 values (1,3)
now indexToAssignment function will give the (row, column) position. Is it so? or am I missing somthing?

zilongzhong commented 5 years ago

That's correct.

On Wed, 16 Jan 2019 at 20:06, TanmDL notifications@github.com wrote:

okay, I got it. You are just converting the selected indices into specific image location in row and coloumn space. for an example, t = np.arange(16).reshape(4,4) indices = 7 # was selected for train the original image location of 7 values (1,3) now indexToAssignment function will give the (row, column) position. Is it so? or am I missing somthing?

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/zilongzhong/SSRN/issues/10#issuecomment-455003559, or mute the thread https://github.com/notifications/unsubscribe-auth/APQzzq8g4aFFG6knZn9eSjPiFkfu3G-Dks5vD8yMgaJpZM4ZhLFe .