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

About the computer configuration #10

Closed StacyIssac closed 3 years ago

StacyIssac commented 3 years ago

Hello, I would like to ask you about the computer configuration used in your trainning model and the approximate trainning time. :)

Svito-zar commented 3 years ago

Hi @StacyIssac . The model was trained on a computer with 1 GPU, namely NVIDIA TITAN Xp. A training epoch took 20 sec or so. 20 sec x 500 epochs is about 150 min Did I answer your question? Best, Taras