Run in GTX960M get error [InternalError (see above for traceback): Dst tensor is not initialized.]——out of memory

naturomics / CapsNet-Tensorflow

A Tensorflow implementation of CapsNet(Capsules Net) in paper Dynamic Routing Between Capsules

Apache License 2.0

3.8k stars 1.17k forks source link

Run in GTX960M get error [InternalError (see above for traceback): Dst tensor is not initialized.]——out of memory #39

Closed H-xie closed 6 years ago

H-xie commented 6 years ago

When run in windows + GTX960M，I get this error

InternalError (see above for traceback): Dst tensor is not initialized.

Some blogs told that it is caused by lack of GPU memory. But I cannot fix the problem. Wish some one could help me.

运行在Windows10 + GTX960M，出现错误

InternalError (see above for traceback): Dst tensor is not initialized.

我查了些博客，说是GPU 内存不足的时候，会出现这个错误。希望能够修复这个问题。

naturomics commented 6 years ago

Please read the README carefully, the default parameter batch_size is set to 128. Your GPU memory is too small for this setting, change it, eg. python main.py --batch_size 32 or a smaller batch_size