search

btgraham / SparseConvNet-archived

Spatially-sparse convolutional networks. Allows processing of sparse 2, 3 and 4 dimensional data.Build CNNs on the square/cubic/hypercubic or triangular/tetrahedral/hyper-tetrahedral lattices.
https://github.com/btgraham/SparseConvNet/wiki
406 stars 122 forks source link

Memory leak? #5

Open yeahrmek opened 8 years ago

yeahrmek commented 8 years ago

I am trying to apply SparseConvNet to ModelNet40 dataset (http://modelnet.cs.princeton.edu/ModelNet40.zip).

It seems that there is some memory leakage. After about 60 epochs the memory consumptino grows up from ~5Gb to ~15Gb,

My code can be found here https://github.com/yeahrmek/3DRetrieval (it is a fork of this project). There modelNet.cpp is a copy of shrec2015.cpp modified to be used with ModelNet dataset. I also modified OffSurfaceModelPicture class constructor to correctly load ModelNet OFF files (in some off files in ModelNet the first line is concatenated with the second)

yupinghuinuaa commented 7 years ago

hey, I am a graduate student in NUAA, China. I have download the code from Ben Graham in the kaggle competition of diabetic retinopathy, sadlly I failured many times to run the code. have you run the code successfully?would you mind tell me how did you debug the program? Are you running in ubuntu environment? and another question is that do you know thewhat the file of .gitignore represent for?Thank you very much