search

TachibanaYoshino / AnimeGAN

A Tensorflow implementation of AnimeGAN for fast photo animation ! This is the Open source of the paper 「AnimeGAN: a novel lightweight GAN for photo animation」, which uses the GAN framwork to transform real-world photos into anime images.
4.49k stars 660 forks source link

inference time so slow? #46

Closed trangtv57 closed 2 years ago

trangtv57 commented 3 years ago

hi, I am not sure where i'm wrong but when i try inference with test.py file as read.me file, each image need more than 2 second for build fake images. When reading your paper, image inference just 50ms, what im wrong. Does image size has big impact for slow inference, thanks you.

hellochy commented 3 years ago

请问这个问题解决了吗，我执行test，单张图片的推理时延y也在3,4秒左右

TachibanaYoshino commented 3 years ago

What the paper mentioned is the statistical time of the test dataset images, which is the average value. The size of the image will affect the inference time, especially when the GPU starts inference for the first time.