Dratlan
Dratlan
I just came across the same problem, would you please tell me how to figure it?
I just got a question, how did you figure that question of "sfm_data.bin cannot be read." ? I just came acrosss the same problem
> performance killer, I have fix for the fixed shape situation: > > * [nonezero](https://github.com/IDEA-Research/GroundingDINO/blob/main/groundingdino/models/GroundingDINO/bertwarper.py#L240) > * [arange](https://github.com/IDEA-Research/GroundingDINO/blob/main/groundingdino/models/GroundingDINO/bertwarper.py#L256) Can you share your exported onnx model
> i try to use torch.onnx.export to transfer grounding-dino to onnx, it seems like some problem , such as several logical operators are not supported by onnx. for example: torch.onnx.symbolic_registry.UnsupportedOperatorError:...
If there is no output for grounding dino, this error occurs.
> ``` > from argparse import Namespace > from models.psp import pSp > import torch.nn as nn > import torch > import onnx > > #Function to Convert to ONNX...
> we can not use dynamic shapes when convert to ONNX, all right, while in yolovx(x is the vertion number), it can use dynamic shapes when convert to onnx. maybe...
In here [https://github.com/TMElyralab/MusePose/issues/19](url), there are pose align discussions. Now I'm stucking in SMPL pose align.
> you can increase the smoothing factor in the blender file . I guess it's in champ/scripts/data_processors/smpl/smooth_smpls.py? or the installed blender file?