ivonatau

Results 9 issues of ivonatau

If you use any vertical videos for face extraction, by default pictures are stretched and rotated. As a workaround, the following few lines should be added to `MTCNN_video_face_detection_alignment.ipynb` file: ```...

Hi I tried all the pretrained models from OneDrive but it is not possible to extract them. The .tar files are corrupted.

Hi, I tried running `convert_weight.py` in a couple of different environments but I get the following error: ``` File "/stylegan2/dnnlib/tflib/network.py", line 278, in __setstate__ assert state["version"] in [2, 3, 4]...

Hi, How can I change the input size of an image? Currently other input sizes e.g. (256x64) result in assertion error `the height of out must be 1`

Hi, Thanks for sharing your exciting research. What is the license for usage? Is it MIT?

Hi all, I was training the model on birds dataset as well as my own data and very soon in training for both datasets (e.g from epoch 5) I start...

Is it possible to initialise student network with other weights than random? If my understanding is correct, the flag `--ckpt` affects both teacher and student. I'd like to load student...

Hi! Thank you for an amazing repository. I successfully converted my StyleGAN2-ada rosinality checkpoint, by running the following line: ``` python convert_rosinality_ckpt.py --ckpt {path_to_rosinality_stylegan2_ckpt} --ckpt-mnet output/mnet.ckpt --ckpt-snet output/snet.ckpt --cfg-path output/config.json...

Is it possible to make the code work with .pkl trained using StyleGAN2-ADA ? The default code throws an error: ``` --------------------------------------------------------------------------- TypeError Traceback (most recent call last) in 2...