Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update README.md #20

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update README.md #20

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 6 additions & 6 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,14 +39,14 @@ Pre-trained networks are stored as `*.pkl` files that can be referenced using lo
# Generate videos using pre-trained model

python gen_videos.py --network models/easy-khair-180-gpc0.8-trans10-025000.pkl \
--seeds 0-3 --grid 2x2 --outdir=out --cfg Head --trunc 0.7
--seeds 0-3 --grid 2x2 --output=out --cfg Head --trunc 0.7

```

```.bash
# Generate images and shapes (as .mrc files) using pre-trained model

python gen_samples.py --outdir=out --trunc=0.7 --shapes=true --seeds=0-3 \
python gen_samples.py --output=out --trunc=0.7 --shapes=true --seeds=0-3 \
--network models/easy-khair-180-gpc0.8-trans10-025000.pkl
```

Expand All @@ -65,7 +65,7 @@ python gen_samples.py --outdir=out --trunc=0.7 --shapes=true --seeds=0-3 \
# Please refer to ./gen_interpolation.py for the implementation

python gen_interpolation.py --network models/easy-khair-180-gpc0.8-trans10-025000.pkl\
--trunc 0.7 --outdir interpolation_out
--trunc 0.7 --output interpolation_out
```


Expand Down Expand Up @@ -123,14 +123,14 @@ Examples of training using `train.py`:
# Train with StyleGAN2 backbone from scratch with raw neural rendering resolution=64, using 8 GPUs.
# with segmentation mask, trigrid_depth@3, self-adaptive camera pose loss regularizer@10

python train.py --outdir training-runs --img_data dataset/testdata_img.zip --seg_data dataset/testdata_seg.zip --cfg=ffhq --batch=32 --gpus 8\\
python train.py --output training-runs --img_data dataset/testdata_img.zip --seg_data dataset/testdata_seg.zip --cfg=ffhq --batch=32 --gpus 8\\
--gamma=1 --gamma_seg=1 --gen_pose_cond=True --mirror=1 --use_torgb_raw=1 --decoder_activation="none" --disc_module MaskDualDiscriminatorV2\\
--bcg_reg_prob 0.2 --triplane_depth 3 --density_noise_fade_kimg 200 --density_reg 0 --min_yaw 0 --max_yaw 180 --back_repeat 4 --trans_reg 10 --gpc_reg_prob 0.7


# Second stage finetuning to 128 neural rendering resolution (optional).

python train.py --outdir results --img_data dataset/testdata_img.zip --seg_data dataset/testdata_seg.zip --cfg=ffhq --batch=32 --gpus 8\\
python train.py --output results --img_data dataset/testdata_img.zip --seg_data dataset/testdata_seg.zip --cfg=ffhq --batch=32 --gpus 8\\
--resume=~/training-runs/experiment_dir/network-snapshot-025000.pkl\\
--gamma=1 --gamma_seg=1 --gen_pose_cond=True --mirror=1 --use_torgb_raw=1 --decoder_activation="none" --disc_module MaskDualDiscriminatorV2\\
--bcg_reg_prob 0.2 --triplane_depth 3 --density_noise_fade_kimg 200 --density_reg 0 --min_yaw 0 --max_yaw 180 --back_repeat 4 --trans_reg 10 --gpc_reg_prob 0.7\\
Expand Down Expand Up @@ -170,4 +170,4 @@ This is a research reference implementation and is treated as a one-time code dr

We thank Shuhong Chen for the discussion during Sizhe's internship.

This repo is heavily based off the [NVlabs/eg3d](https://github.com/NVlabs/eg3d) repo; Huge thanks to the EG3D authors for releasing their code!
This repo is heavily based off the [NVlabs/eg3d](https://github.com/NVlabs/eg3d) repo; Huge thanks to the EG3D authors for releasing their code!