GANimation

GANimation copied to clipboard

Is this how you would run your sample images ?

2

python data/prepare_au_annotations.py -ia=sample_dataset/ -op=sample_output/?

jamesthesnake

Is there any demo file available for results, as I can only see training and testing scripts. @albertpumarola

RAJA-PARIKSHAT

Generator is different from that in paper

1

Fake image generation in ganimation.py is like this: # generate fake images fake_imgs, fake_img_mask = self._G.forward(real_img_a, real_cond_b) fake_img_mask = self._do_if_necessary_saturate_mask(fake_img_mask, saturate=self._opt.do_saturate_mask) fake_imgs_masked = fake_img_mask * real_img_a + (1 - fake_img_mask)...

sunshine2004

Pretrained Model

2

Can you please share the pretrained model link? I havent found out anywhere in the repo..

onzone

training process too slow

12

Hello, I use 1080Ti to train 200000 images, every image is 128*128. However, the speed of training is very slow, It takes me almost 4 hours to finish one epoch...

zzzzhuque

Can you share you train data in this paper?

1

Thank you very much!

xinyuxiao

how to sample the 20w images from EmotioNet

4

hello, thanks for your wonderful work. I have obtained the 95w images of EmotioNet, extracted the AUs with OpenFace and cropped the faces with face_recognition. The problem is, how to...

Honlan

How long does it take to apply for EmotionNet data set?

2

How long does it take to apply for EmotionNet data set?

c1a1o1

IndexError: During training 0-dim tensor error

2

While executing the train.py file, **IndexError: invalid index of a 0-dim tensor. Use `tensor.item()` in Python or `tensor.item()` in C++ to convert a 0-dim tensor to a number** The complete...

divyanshujhawar

Hi, I'm trying to implement the code on a custom dataset and followed the necessary step. My `dataset` directory consists of: `train_ids.csv` - containing the names of all images (128x128...

Prashant-mahajan