search

dsindex / syntaxnet

reference code for syntaxnet
196 stars 57 forks source link

GPU device not visible #26

Open enigmanx opened 7 years ago

enigmanx commented 7 years ago

Hi I tried to train my own model using './train_dragnn.sh -v -v &' but it doesn't use GPU device. I added this code in train_dragnn.py and it is only cpu device available:

from tensorflow.python.client import device_lib print device_lib.list_local_devices()

Tensorflow compiled with GPU support and when i create new python file i can list devices:

import tensorflow as tf from tensorflow.python.client import device_lib print device_lib.list_local_devices() Output: [name: "/cpu:0" device_type: "CPU" memory_limit: 268435456 locality { } incarnation: 3558873585769960542 , name: "/gpu:0" device_type: "GPU" memory_limit: 10574476084 locality { bus_id: 1 } incarnation: 8461732259736364275 physical_device_desc: "device: 0, name: Graphics Device, pci bus id: 0000:01:00.0" ]

So, maybe you can suggest me how to use my gpu in training process or maybe i need to put some flags to enable gpu support.

Regards, Vladimir