Onur-Andros Özbek

Hi. Is there a way to run the video demo file on videos for pncc and depth options?

No results

3

Hi. This is the output after a successful run: ``` creating the FLAME Decoder trained model found. load /home/onur/git-repos/DECA/data/deca_model.tar -- please check the results in TestSamples/examples/results 0it [00:00, ?it/s] ```...

How to generate images after training

2

Hi. I am using the provided code below: ``` import torch from imagen_pytorch import Unet, Imagen, ImagenTrainer # unet for imagen unet1 = Unet( dim = 32, cond_dim = 512,...

This is impossible to work with

4

Why is this library built with such an old version of Python? It is absolutely impossible to even get the pip installs working. I created a virtual OS with 16.04...

What is rewritten_bbox and what does it mean for it to be 50%

2

Hello guys. I don't quite understand what rewritten_bbox really means. Would appreciate it if I could get a rundown.

Not able to pickle weakref objects.

1

Hi. I'm using the celeb_a dataset from Kaggle because I want to test the pi-GAN and try it with a custom dataset should I get it working. After changing the...

Hi. When I try to run `python step1_recon_3d_face.py` I am getting this error: ``` raceback (most recent call last): File "/opt/conda/envs/pytorch-py3.6/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow.py", line 58, in from tensorflow.python.pywrap_tensorflow_internal import * File "/opt/conda/envs/pytorch-py3.6/lib/python3.6/site-packages/tensorflow/python/pywrap_tensorflow_internal.py",...

CUDA out of memory despite available memory

20

The following is my hardware makeup: ``` !nvidia-smi Tue Nov 15 08:49:04 2022 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 510.60.02 Driver Version: 510.60.02 CUDA Version: 11.6 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id...

Video output is shaking. Link to video and merge settings in description

3

Hi. These are my merging settings: ``` Loading new_SAEHD model... Initializing models: 100%|#############################################################################################################################################################################################################################| 4/4 [00:02

DeepFaceLab not seeing GPU on Linux container.

1

For example, when I do face detection, this is what it looks like: Extracting faces... Running on CPU1 Running on CPU0 3%|###8 | 10/320 [00:29