Chen Hou

Hi! Thanks for this marvellous work. I have questions about how to do temperature scaling, like Fig. 6 in the paper does. I use pretrained ODE model to generate 256x256...

How can I use pretrained model offered (like ffhq.pkl) and do inference using the structures mentioned in the paper?

Are code of discriminator used for selecting avaliable? Seems that description of this part in article is not clarified enough for reinplementation, most importantly, loss function of this part is...

ValueError: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 0 is different from 3)

1

Hi! When I run run_particlesfm.py on 16 256x256 images, the error goes up: Elapsed time: 0.376 [minutes] {'num_reg_images': 16, 'num_sparse_points': 1141, 'num_observations': 10630, 'mean_track_length': 9.316389, 'num_observations_per_image': 664.375, 'mean_reproj_error': 0.401069} WARNING:root:This...