Numpy and Tensorflow implementation of SMPL model.

I wrote this because the author-provided implementation was mainly based on chumpy, which is kind of unpopular. Meanwhile, the official one cannot run on GPU.

My 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.

1. Download the model file here.
2. Run python preprocess.py /PATH/TO/THE/DOWNLOADED/MODEL to preprocess the official model. preprocess.py will create a new file model.pkl. smpl_np.py and smpl_tf.py both rely on model.pkl.
3. Run python smpl_np.py to see the example.