Tensor sizes are mismatched when matmul in test.py

[tan5o]

python /home/koya/git/GanHand/test.py --dataset_mode ycb_affordances_complete_scene --name ganhand_pretrained --load_epoch 13 --data_dir /home/koya/git/YCB_Affordance --mano_dir /home/koya/git/manopth/mano/models

I ran test.py based on README.md.
But, I encountered an error.

Traceback (most recent call last):
  File "/home/koya/git/GanHand/test.py", line 443, in <module>
    Test()
  File "/home/koya/git/GanHand/test.py", line 257, in __init__
    self._display_visualizer_test(20, self._total_steps)
  File "/home/koya/git/GanHand/test.py", line 321, in _display_visualizer_test
    self._model.forward(keep_data_for_visuals=True)
  File "/home/koya/git/GanHand/models/ganhand.py", line 222, in forward
    handfullpose_list, touching_indexs, loss_distance, loss_angle, loss_angle_2ndjoint, loss_angle_3rdjoint = fk.optimize_hand(handfullpose[i].unsqueeze(0), R[i].unsqueeze(0), T[i].unsqueeze(0), self._input_obj_resampled_verts[i][self._input_object_id[i]])
  File "/home/koya/git/GanHand/utils/forward_kinematics_3dof.py", line 491, in optimize_hand
    meshes, _ = get_hand(handfullpose_repeated, R.repeat(num_samples, 1), T.repeat(num_samples, 1))
  File "/home/koya/git/GanHand/utils/forward_kinematics_3dof.py", line 297, in get_hand
    MANO.th_posedirs, th_pose_map.transpose(0, 1)).permute(2, 0, 1)
RuntimeError: size mismatch, m1: [2334 x 135], m2: [144 x 51] at /tmp/pip-req-build-ocx5vxk7/aten/src/THC/generic/THCTensorMathBlas.cu:290

I saw around code, however, I have no idea.
Do you know the cause?

Where the error occurred

    # NOTE: GET HAND MESH VERTICES: 778 vertices in 3D
    # th_v_posed -> [batchsize, 778, 3]
    th_v_posed = th_v_shaped + torch.matmul(
        MANO.th_posedirs, th_pose_map.transpose(0, 1)).permute(2, 0, 1)

[tan5o]

I solved it.
Use manopth at this commit

hassony2/manopth@246a4e3