davidsonic / Interpretable_CNNs_via_Feedforward_Design

Official Implementation of Interpretable Convolutional Neural Networks via Feedforward Design Arxiv: https://arxiv.org/abs/1810.02786
11 stars 8 forks source link

MemoryError:Unable to allocate array with shape (39146090,75) and data type float64 #5

Open leader120 opened 4 years ago

leader120 commented 4 years ago

First,thanks for your code. I have run the code I don't find the feat.pkl , run Get_feature.py to get feat.pkl when i run Get_kernel.py ,my server have has MemoryError (my server has 128g physical memory) but , when i run about minst code don't happened memoryerror , It is happened at cifar code So, I'd like to ask if you have any memoryerror in your experiment, I think 128g physical memory already big enough

minzhang-1 commented 4 years ago

Yes, Getkernel.py uses memory over 128G. You may use incrementalpca to replace pca so that you can set batch number. But the test accuracy will be decreased by around 1%.