Numpy and Tensorflow implementation of SMPL model. GitHub link: SMPL.
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 paper.
- Download the model file here.
python preprocess.py /PATH/TO/THE/DOWNLOADED/MODELto preprocess the official model.
preprocess.pywill create a new file
smpl_tf.pyboth rely on
model.pkl. NOTE: the official pickle model contains
chumpyto extract official model. You need to modify chumpy’s cource code a little bit to make it compatible to
preprocess.py(and Python 3). Here is an instruction in Chinese about this.
python smpl_tf.pyto see the example.