G-force78
G-force78
RuntimeError: Error(s) in loading state_dict for Generator: size mismatch for pixelwise_flow_predictor.hourglass.encoder.down_blocks.0.conv.weight: copying a param with shape torch.Size([128, 44, 3, 3]) from checkpoint, the shape in current model is torch.Size([128, 84,...
https://github.com/snap-research/articulated-animation/assets/114336644/0b300e99-d13b-4033-a481-52cd49f20e89 Was there some post processing to make the disentanglement look better than it was? All examples I have done come out with significant warping and shadows. https://snap-research.github.io/articulated-animation/
Before generating I would like to see the segmentation map the code in the collab does not work
2023-10-17 10:57:05,909 [nnabla][INFO]: Initializing CPU extension... usage: animate.py [-h] [--config CONFIG] [--params PARAMS] [--source SOURCE] [--driving DRIVING] [--out-dir OUT_DIR] [--context {cudnn,cpu}] [--output-png] [--fps FPS] [--only-generated] [--detailed] [--full] [--adapt-movement-scale] [--unuse-relative-movement] [--unuse-relative-jacobian]...
Eg: on kaggle where for some reason it holds onto high RAM so model merges arent possible as it runs out of memory.
/src/utils/pose_util.py", line 38, in project_points transformed_points = points_3d_homogeneous @ (transformation_matrix @ euler_and_translation_to_matrix(pose_vectors[i][:3], pose_vectors[i][3:])).T @ P IndexError: index 60 is out of bounds for axis 0 with size 60 Edit: this...
Thanks for the colab, I'm wondering if there is a way to keep the audio, maybe by not converting to avi and back to mp4?
**Describe the bug** A clear and concise description of what the bug is. UI crashes nothing is produced despite not getting close to maxing out memory **To Reproduce** Steps to...