search

anuragranj / coma

Convolutional Mesh Autoencoders for Generating 3D Faces
Other
454 stars 100 forks source link

A question about computeError.py #37

Open caozhenxiang-kouji opened 3 years ago

caozhenxiang-kouji commented 3 years ago

Thanks for the great work! When I was running the generateErrors.sh script, the results show that the pca results actually get a lower Error than cnn results, which is shown as below: error

And the plot also shows that the pca has a better Euclidean norm performance. cheeks_in

I 'm wondering whether you can the same results as mine? Or have I mistaken something?

konatasick commented 3 years ago

I got the same results. I can only reproduce the result of "sliced". Have you fixed it?