Closed PedroKBrant closed 7 months ago
Hi @PedroKBrant, I just merged some bug fixes. Furthermore, under the test folder, you can find a test_main.py with examples of how to use the code. If those don't help to solve your issue, let me know.
Thank you for the attention, I will pull the bugfixes and try to run this file first.
@FHellmann, just a quick question: when I run the train_pix2pix script, should the data_dir point to the FaceSegmentation folder?
You should train it on the folder (probably "FacialLandmarks478") with the images including a face and the corresponding mesh. Like this for example:
It is now working, thank you
Hello @FHellmann, thank you for making your code available. I tried to train the network myself but got an awkward result. The three images are: the original face from CelebA, the anonymization using your available model, and the model I trained (epoch 107), respectively. Any idea on what I did wrong would be greatly appreciated :)
Results
![1_resized](https://github.com/hcmlab/GANonymization/assets/34447224/740cb15d-3bc6-461b-9531-45e2d1939a3a) ![1_anon_baseline](https://github.com/hcmlab/GANonymization/assets/34447224/fd85c0bb-479e-4f79-a220-8bd604fe39c0) ![1_anon](https://github.com/hcmlab/GANonymization/assets/34447224/1bcbde6e-e858-4c95-8ab3-4db8f51b78a4)Oddly, my output results seem fine.
Output
![107-616998](https://github.com/hcmlab/GANonymization/assets/34447224/08102c46-6acd-415a-a94f-a7a3d29ec932)My conda env is CUDA Version: 12.2, python 3.8 and torch 2.1.2. I-m running on Ubuntu 22.04 lts on a RTX3090, 32 RAM.
I' have followed the instructions on README and prepared the dataset with the commands:
python main.py preprocess --input_path ../../../../../media/voxar/datasets/pkb/celeba_splitted/ --img_size 512 --test_size 0.1 --output_dir ../../../../../media/voxar/datasets/pkb/celeba_splitted
The training used this hyperparametes
python main.py train_pix2pix --data_dir lib/datasets/ --log_dir logs/ --models_dir baseline/ --output_dir results/ --dataset_name celeba_splitted/FaceSegmentation/
I have also changed detect_anomaly to False