This repo contains the code relating to the paper submitted to CVPR 2020 (Paper ID: 7884) with the instructions for training and testing our models on the JTA dataset.
Input | Prediction |
---|---|
- run
python demo.py --ex=1
(python >= 3.6)- please wait some seconds: it will display some precomputed results. You can change the
ex
number from 1 to 3 to see different results
- please wait some seconds: it will display some precomputed results. You can change the
cd
into the foldernms3d
and runpython setup.py install
(python >= 3.6). Make sure to add your cuda directory to your environment variables.
- Download the JTA dataset
in
<your_jta_path>
- Run
python to_poses.py --out_dir_path='poses' --format='torch'
(link) to generate the<your_jta_path>/poses
directory - Run
python to_imgs.py --out_dir_path='frames' --img_format='jpg'
(link) to generate the<your_jta_path>/frames
directory - Download our precomputed codes from here
and unzip them into
<your_jta_path>
- Modify the
conf/default.yaml
configuration file specifying the path to the JTA dataset directoryJTA_PATH: <your_jta_path>
- run
python train.py --exp_name=default
(python >= 3.6)
- run
python show.py --exp_name=default
(python >= 3.6)- Note that, before showing the results, you must have completed at least one training epoch; however, to achieve results comparable to those reported in the paper, it is advisable to carry out a training of at least 100 epochs
- Download the pretrained weights and extract them into the project folder
- Modify the
conf/pretrained.yaml
configuration file specifying the path to the JTA dataset directoryJTA_PATH: <your_jta_path>
- run
python show.py --exp_name=pretrained
(python >= 3.6)