electron-rare/SMPLer-X
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md according to comments

Browse Source
This commit is contained in:
WEI CHEN
2023-10-23 18:10:46 +08:00
committed by GitHub
parent 8f41b62cc8
commit ab19fdab17
1 changed files with 15 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+15 -14
View File
@@ -12,7 +12,7 @@
</div>
## News
- [2023-10-23] More tools: smplx mesh overlay script and inference docker are added !
- [2023-10-23] Support visualization through SMPL-X mesh overlay and inference docker added.
- [2023-10-02] [arXiv](https://arxiv.org/abs/2309.17448) preprint is online!
- [2023-09-28] [Homepage](https://caizhongang.github.io/projects/SMPLer-X/) and [Video](https://youtu.be/DepTqbPpVzY) are online!
- [2023-07-19] Pretrained models are released.
@@ -41,6 +41,17 @@ pip install -v -e .
cd ../..
```
## Docker Support (Early Stage)
```
docker pull wcwcw/smplerx_inference:v0.2
docker run --gpus all -v <vid_input_folder>:/smplerx_inference/vid_input \
-v <vid_output_folder>:/smplerx_inference/vid_output \
wcwcw/smplerx_inference:v0.2 --vid <video_name>.mp4
# Currently any customization need to be applied to /smplerx_inference/smplerx/inference_docker.py
```
- We recently developed a docker for inference at docker hub.
- This docker image uses SMPLer-X-H32 as inference baseline and was tested at RTX3090 & WSL2 (Ubuntu 20.04).
## Pretrained Models
| Model | Backbone | #Datasets | #Inst. | #Params | MPE | Download | FPS |
@@ -177,9 +188,9 @@ sh slurm_inference.sh test_video mp4 24 smpler_x_h32
```
## 2D Smplx Overlay
- We provide a light pyrender script for mesh overlay projection.
- Overlay script uses result from above inference
- Use ffmpeg to split video to images to support overlay
We provide a lightweight visualization script for mesh overlay based on pyrender.
- Use ffmpeg to split video into images
- The visualization script takes inference results (see above) as the input.
```bash
ffmpeg -i {VIDEO_FILE} -f image2 -vf fps=30 \
{SMPLERX INFERENCE DIR}/{VIDEO NAME (no extension)}/orig_img/%06d.jpg \
@@ -215,16 +226,6 @@ sh slurm_test.sh {JOB_NAME} {NUM_GPU} {TRAIN_OUTPUT_DIR} {CKPT_ID}
- NUM_GPU = 1 is recommended for testing
- Logs and results will be saved to `SMPLer-X/output/test_{JOB_NAME}_ep{CKPT_ID}_{TEST_DATSET}`
## Docker Support (Early Stage)
```
docker pull wcwcw/smplerx_inference:v0.2
docker run --gpus all -v <vid_input_folder>:/smplerx_inference/vid_input \
-v <vid_output_folder>:/smplerx_inference/vid_output \
wcwcw/smplerx_inference:v0.2 --vid <video_name>.mp4
# Currently any customization need to be applied to /smplerx_inference/smplerx/inference_docker.py
```
- We recently developed a docker for inference at docker hub.
- This docker image uses SMPLer-X-H32 as inference baseline and was tested at RTX3090 & WSL2.
## FAQ
- `RuntimeError: Subtraction, the '-' operator, with a bool tensor is not supported. If you are trying to invert a mask, use the '~' or 'logical_not()' operator instead.`