Seanseattle
Seanseattle
@cwalt2014 Could you please share the source code or pretrained weights? Thank you. My Email: [email protected]
@xqyd, Hi, do you try to apply the environment map to the mesh in UE4/5?
Thank you! But I can not find this code right now, and I will try to release it in the future. The metrics of mCSD and mOCD are based on...
We used the pretrained models from [SPADE](https://github.com/NVlabs/SPADE) Github and tested with the dataset's evaluation method. This means we ignored the "don't care label". For FID, we used the updated PyTorch-version...
Hello, for style morphing, you can sample two latent codes and make an interpolation between two latent codes. For style mix, just combine the style codes to get latent code,...
Hi! The codes do not create the Encoder model at test mode as most pictures are generated from noise. https://github.com/Seanseattle/SMIS/blob/5d2b74794059ad1ddeb4573e2b1bf2d1fa29adb2/models/smis_model.py#L99 And we don't upload the Encoder pretrained model to the...
Hello. you can write a new dataset loader. There is an example at `data/custom_dataset.py`. Then set the `--dataset_mode` parameter as your dataset.
Please reference the README.
Hello, you can try [Paddle Lite](https://www.paddlepaddle.org.cn/lite) for deployment. This can speed up more than 19 FPS by running on the GPU of a mobile phone.
We used off-the-shelf human parser "Instance-level human parsing via part grouping network" for the DeepFashion dataset. And reorganize the map into eight categories: hair, face, skin (including hands and legs),...