Wanglong Lu

> multi-machine,multi-gpu: > > 2022-05-21 09:28:21.116 [ERROR] Traceback (most recent call last): 2022-05-21 09:28:21.116 [ERROR] File "/root/share/program/lama-main/bin/train.py", line 76, in 2022-05-21 09:28:21.116 [ERROR] main() 2022-05-21 09:28:21.117 [ERROR] File "/root/share/program/lama-main/saicinpainting/utils.py", line...

Hi, @doantientai @damlasena. Is there anyone who finds that numpy_calculate_frechet_distance will cost a lot of time? For example, when I want to vilify the model performance, it cost me almost...

BTW, I use the V100 32GB device with 8 CPUs

Hi @rosinality , Would that hurt the generation quality if I directly use the torch.nn.functional.conv2d() instead of the conv2d_gradfix? I am waiting for your reply! Thank you!

Hi @lmxyy , Thanks! Yes, the Colab runs well. I run on a PC with 2.90 GHz Intel R CoreTM i7-10700F CPU, 16 GB memory, NVIDIA GeForce RTX 2080 GPU....

Hi @lmxyy , Thank you so much! I tried and install the siga pip package. The interactive session results are shown below: Python 3.7.10 (default, Feb 26 2021, 18:47:35) [GCC...

Hi @dinusha94 , thank you so much for your attention to our project. It sounds like you may have input the wrong image path for target or exemplar folders. 1....

Hi @dinusha94 I found the problem here, it is because I hard-coded the three paths. Could you download the exemplar_style_mixing.py again and try again? Thanks!

Hi @dinusha94 , Thanks for the good questions. First, face alignment is needed, because the training data (FFHQ) are from aligned images, and the capacity of the GAN-based model is...

Hi @dinusha94 , oh, I realized that you could directly use guided_recovery.py. Please take a look at the README for more details. Thanks!