OpenShape_code
OpenShape_code copied to clipboard
official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”
Hi, Thanks for open-sourcing such a wonderful work. Regarding the preprocessing of pretraining data, did you apply this [template prompts in ULIP](https://github.com/salesforce/ULIP/blob/main/data/templates.json) to both the raw texts, blip and msft...
Hi, how do you sample 10,000 points from mesh surface, is it fps?
I have encountered an issue when using your project, where some points in the point cloud are being lost during processing. Specifically, in the config file, the transform configuration is...
Could you please provide the specific settings of these parameters and the corresponding point cloud input data? - `prompt`, - `noise_level`, - `width`, - `height`, - `cfg_scale`, - `num_steps`, -...
The result of training for 200 epochs using 8 A800 GPUs on the ModelNet40 dataset is only 80.06% accuracy. All other parameters are the same as those in the train.yaml...
Could the author provide th test scripts of the models, thx
Hello, I am really interested in your work and have been exploring the OpenShape dataset. I have a question regarding the OpenShape/openshape-training-data/rendered_images folder. Could you provide some details about how...
The huggingface live demo shows the following error. ``` OSError: libcudart.so.11.0: cannot open shared object file: No such file or directory Traceback: File "/home/user/.pyenv/versions/3.10.14/lib/python3.10/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 565, in _run_script exec(code, module.__dict__)...
Thank you for proposing such an inspiring method. However, my performance on the ScanObjectNN dataset is quite poor. I suspect it might be related to the number of points (2048...