A error about 3DMMExtract/Coarse/util/preprocess.py

[904763189cy]

Hi

t[0] and t[1] are list

so I change the code:
trans_params = np.array([w0, h0, s, t[0], t[1]])
to
trans_params = np.array([w0, h0, s, t[0][0], t[1][0]])

then code executed successfully.
But I’m not sure if this is the correct way to modify the code.

Error：
Traceback (most recent call last):
File “/home/visionx/CIY/OTAvatar_processing_ultimate/3DMMExtract/Coarse/face_recon_videos.py”, line 187, in
main(opt, model)
File “/home/visionx/CIY/OTAvatar_processing_ultimate/3DMMExtract/Coarse/face_recon_videos.py”, line 118, in main
print(dataset[0])
File “/home/visionx/CIY/OTAvatar_processing_ultimate/3DMMExtract/Coarse/face_recon_videos.py”, line 61, in getitem
= self.image_transform(frames[i], lm[i])
File “/home/visionx/CIY/OTAvatar_processing_ultimate/3DMMExtract/Coarse/face_recon_videos.py”, line 97, in image_transform
trans_params, img, lm, _ = align_img(images, lm, self.lm3d_std)
File “/home/visionx/CIY/OTAvatar_processing_ultimate/3DMMExtract/Coarse/util/preprocess.py”, line 98, in align_img
trans_params = np.array([w0, h0, s, t[0], t[1]])
ValueError: setting an array element with a sequence. The requested array has an inhomogeneous shape after 1 dimensions. The detected shape was (5,) + inhomogeneous part.

[TaekyungKi]

Modifying the line trans_params = np.array([w0, h0, s, t[0], t[1]]) to trans_params = np.array([w0, h0, s, t[0], t[1]], dtype=object) may resolve it.