Numpy and Tensorflow implementation of SMPL model. For any questions, feel free to contact me.
I wrote this because the author-provided implementation was mainly based on chumpy in Python 2, which is kind of unpopular. Meanwhile, the official one cannot run on GPU.
This numpy version is faster (since some computation is re-wrote in a vectorized manner) and easier to understand (hope so), and the tensorflow version can run on GPU.
For more details about SMPL model, see SMPL.
- Download the model file here.
- Run
python preprocess.py /PATH/TO/THE/DOWNLOADED/MODEL
to preprocess the official model.preprocess.py
will create a new filemodel.pkl
.smpl_np.py
andsmpl_tf.py
both rely onmodel.pkl
. NOTE: the official pickle model containschumpy
object, soprerocess.py
requireschumpy
to extract official model. You need to modify chumpy's cource code a little bit to make it compatible topreprocess.py
(and Python 3). Here is an instruction in Chinese about this. - Run
python smpl_np.py
orpython smpl_tf.py
to see the example.