dmoham1476
dmoham1476
2to3 didnt do a good job
1. Don't we need to do clip.load_state_dict after clip.load? 2. Are we not doing model.encode_image and model.encode_text and then doing norm before training? 3. Can you please add demo code...
How can I use get3D to generate a 3D object for a 2D image?
Thank you
When will the google colab be updated with this PR?
@Vincentqyw It seems Step 10 (render video) of the colab, If I give n_steps > 2000 (which is the step for the first msgpack), it does not do anything while...
@barney2074 The output_render.mp4 that is generated for my custom example is good, but the mesh .obj is very bad. I can barely tell the object is in the obj file....
@catalin-usurelu When I ran the colab cmake build, it didnt generate a testbed for me.
@catalin-usurelu I initially created a checkpoint after 2000 steps. In step - render a scene, I ran run.py with n_steps > 2000. It never converges, the loss stays the same...
@junxiant The exported .ply mostly is very hard to comprehend. If I zoom in I only see triangles and I cannot make out where the fox is. Are there any...