search

Hangz-nju-cuhk / Talking-Face-Generation-DAVS

Code for Talking Face Generation by Adversarially Disentangled Audio-Visual Representation (AAAI 2019)
MIT License
819 stars 173 forks source link

Use the pretrained model ,but got the wrong test result #4

Open zhuhaozh opened 6 years ago

zhuhaozh commented 6 years ago

My PC environment is python3.6+pytorch0.40. After I changed and only changed the str(01) to "01" in IdentityEncoder.py, this code(test_all.py) can run well, with some deprecated UserWarning,But the output is far from the actual result, Is that cause by environment problem? The following is the test result and real sample. test_sample4_fake_image_b_0_31 test_sample4_real_a_1

Hangz-nju-cuhk commented 6 years ago

We didn't test our code with python 3.6 and it is possible that this is the cause. At the same time, str(01) actually equals "1" instead of "01" in both python 2.7 and python 3.6.