Closed radhesyam closed 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.
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
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