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

Does code work on CPU please tell me #5

Closed radhesyam closed 6 years ago

radhesyam commented 6 years ago

your cpu supports instructions that this tensorflow binary was not compiled to use: avx2 fma

taking longer time to train

Does it work on CPU please tell me

zilongzhong commented 6 years ago

I only used GPU for this project because each SSRN model contains about 360,000 parameters to train. More importantly, GPUs are essential for deep learning.

radhesyam commented 6 years ago

in Running SSRN_IN.py the following error encountered from Utils import zeroPadding, normalization, doPCA, modelStatsRecord, averageAccuracy, ssrn_SS_IN since Utils is folder i am getting import error