tagan icon indicating copy to clipboard operation
tagan copied to clipboard

An official PyTorch implementation of the paper "Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language", NeurIPS 2018

Results 6 tagan issues
Sort by recently updated
recently updated
newest added

Hi, thank for you this work. I was wondering why, during training, it is necessary to take two passes through the Generator, i.e. once in line 145 and once in...

hi! I got an error when I tried to run sh scripts/test_flowers.sh Traceback (most recent call last): File "test.py", line 42, in word_embedding = fasttext.load_model(args.fasttext_model) File "/home/zhaoliuqing/anaconda3/lib/python3.7/site-packages/fasttext/FastText.py", line 363, in...

Hi, in the tagan paper you mentioned that you have conducted a chi-square test on count values. Unfortunately, I cannot figure out how to use this test. May I have...

Hi, I wanted to run the code for images of size 256 as input instead of 128. I see that image size 128 is hardcoded in "train.py" while transforming into...

How we get the ground-truth images, when computing the Quantitative comparison of L2 error ? and Where can we get the supplementary paper of tagan?

I got an error when I tried to run test.py. Maximum supported image dimension is 65500 pixels Traceback (most recent call last): File "C:\Program Files\JetBrains\PyCharm 2017.3\helpers\pydev\pydevd.py", line 1683, in main()...