search

GestureGeneration / Speech_driven_gesture_generation_with_autoencoder

This is the official implementation for IVA '19 paper "Analyzing Input and Output Representations for Speech-Driven Gesture Generation".
https://svito-zar.github.io/audio2gestures/
Apache License 2.0
107 stars 27 forks source link

How to specify using Independent Graphic card? #5

Closed whisperzh closed 4 years ago

whisperzh commented 4 years ago

I successfully get the samples trained, but it seems that i was using my intergrated graphic card. Could you help me

Svito-zar commented 4 years ago

I assume that your problem is that the training was not utilizing your GPU.

The following aspects are important to ensure that you use your GPU:

  1. Install Tensorflow which supports GPU: pip install tensorflow-gpu==1.14.0

  2. Specify the GPU to be used during the training: CUDA_VISIBLE_DEVICES=1 python train.py MODEL_NAME EPOCHS DATA_DIR N_INPUT ENCODE DIM

Hope that helps. If it does not - please provide more details about your issue.

whisperzh commented 4 years ago

OK, i understand how to do, THANK U for helping me. And i am still dealing with my environment, since i doesn't have CUDA. I'll let you know as soon as it works . Again Thank you!!

Svito-zar commented 4 years ago

I close this issue due to inactivity