search

Chunde / cuda-convnet2

Automatically exported from code.google.com/p/cuda-convnet2
Apache License 2.0
0 stars 0 forks source link

conv1 weights and biases become nan #14

Open GoogleCodeExporter opened 8 years ago

GoogleCodeExporter commented 8 years ago 
What steps will reproduce the problem?
1. Follow the steps in Compiling, Data, and TrainingExample for ILSVRC2012
2. I used same parameters for running convnet except --train-freq=10

What is the expected output? What do you see instead?
Keep training with correct weights. (Top-5 error reaches 0.7 before 13th epochs)
After 14th epochs, conv1 weights and biases become nan and top-5 error becomes 
0.99...

What version of the product are you using? On what operating system?
latest version of cuda-convnet2, Ubuntu 14.04

Please provide any additional information below.

Original issue reported on code.google.com by lywoo...@gmail.com on 1 Dec 2014 at 1:07