[CVPR 2023 Highlight] GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts.
Home Page: https://pku-epic.github.io/GAPartNet/
Thank you for such an excellent work !!!
Would the author be willing to release the dataset through Baidu Cloud Disk? In many scenarios, Peking University Cloud Disk often interrupts downloading, we have no idea about the reason why in three devices.
Additionally, we noticed that the training code seems to have not been fully completed yet, and we hope the author can supplement this part.
Dear haoran,
Firstly, I want to express my appreciation for open-sourcing the URDF files in your GAPartNet.
I am interested in reproducing your work and would like to replicate the results you have achieved. In order to do so, I would need access to the code or any instructions necessary to generate the training data from the URDF files. Therefore, I kindly request your assistance in providing the code or guidelines to generate the training data from the URDF files.
Thank you for your attention, and I look forward to your response.
Best regards
Thanks for your remarkable work!
I looked up the project, but couldn't find the code to calculate QRB_adv_loss. If it's my negligence, please tell me where the code is.
Looking forward to your reply.
Regards
Hello, I'm trying to run Inference and Visualization command
CUDA_VISIBLE_DEVICES=0 \
python train.py test -c gapartnet.yaml \
--model.init_args.ckpt ckpt/release.ckpt
It's suggested to install pytorch-lightning, but that doesn't match the import statements in the files which uses lightning. I believe it's referring to this package instead - lightning.
However, when I try to run train.py using the above I get the following error:
usage: train.py [options] test [-h] [-c CONFIG] [--print_config[=flags]] [--seed_everything SEED_EVERYTHING] [--trainer CONFIG]
[--trainer.accelerator.help CLASS_PATH_OR_NAME] [--trainer.accelerator ACCELERATOR]
[--trainer.strategy.help CLASS_PATH_OR_NAME] [--trainer.strategy STRATEGY] [--trainer.devices DEVICES]
[--trainer.num_nodes NUM_NODES] [--trainer.precision PRECISION] [--trainer.logger.help CLASS_PATH_OR_NAME]
[--trainer.logger LOGGER] [--trainer.callbacks.help CLASS_PATH_OR_NAME] [--trainer.callbacks CALLBACKS]
[--trainer.fast_dev_run FAST_DEV_RUN] [--trainer.max_epochs MAX_EPOCHS] [--trainer.min_epochs MIN_EPOCHS]
[--trainer.max_steps MAX_STEPS] [--trainer.min_steps MIN_STEPS] [--trainer.max_time MAX_TIME]
[--trainer.limit_train_batches LIMIT_TRAIN_BATCHES] [--trainer.limit_val_batches LIMIT_VAL_BATCHES]
[--trainer.limit_test_batches LIMIT_TEST_BATCHES] [--trainer.limit_predict_batches LIMIT_PREDICT_BATCHES]
[--trainer.overfit_batches OVERFIT_BATCHES] [--trainer.val_check_interval VAL_CHECK_INTERVAL]
[--trainer.check_val_every_n_epoch CHECK_VAL_EVERY_N_EPOCH]
[--trainer.num_sanity_val_steps NUM_SANITY_VAL_STEPS] [--trainer.log_every_n_steps LOG_EVERY_N_STEPS]
[--trainer.enable_checkpointing {true,false,null}] [--trainer.enable_progress_bar {true,false,null}]
[--trainer.enable_model_summary {true,false,null}] [--trainer.accumulate_grad_batches ACCUMULATE_GRAD_BATCHES]
[--trainer.gradient_clip_val GRADIENT_CLIP_VAL] [--trainer.gradient_clip_algorithm GRADIENT_CLIP_ALGORITHM]
[--trainer.deterministic DETERMINISTIC] [--trainer.benchmark {true,false,null}]
[--trainer.inference_mode {true,false}] [--trainer.use_distributed_sampler {true,false}]
[--trainer.profiler.help CLASS_PATH_OR_NAME] [--trainer.profiler PROFILER]
[--trainer.detect_anomaly {true,false}] [--trainer.barebones {true,false}]
[--trainer.plugins.help CLASS_PATH_OR_NAME] [--trainer.plugins PLUGINS] [--trainer.sync_batchnorm {true,false}]
[--trainer.reload_dataloaders_every_n_epochs RELOAD_DATALOADERS_EVERY_N_EPOCHS]
[--trainer.default_root_dir DEFAULT_ROOT_DIR] [--model.help CLASS_PATH_OR_NAME]
--model CONFIG | CLASS_PATH_OR_NAME | .INIT_ARG_NAME VALUE [--data.help CLASS_PATH_OR_NAME]
--data CONFIG | CLASS_PATH_OR_NAME | .INIT_ARG_NAME VALUE [--optimizer.help CLASS_PATH_OR_NAME]
[--optimizer CONFIG | CLASS_PATH_OR_NAME | .INIT_ARG_NAME VALUE] [--lr_scheduler.help CLASS_PATH_OR_NAME]
[--lr_scheduler CONFIG | CLASS_PATH_OR_NAME | .INIT_ARG_NAME VALUE] [--ckpt_path CKPT_PATH]
[--verbose {true,false}]
error: Parser key "model":
sequence item 0: expected str instance, int found
I was wondering what version of lightning or pytorch-lightning is required for this project? Or if you have any insight as to what is causing this bug please let me know. Thank you.
Hello, I'm interested in your work. I attempted to convert the point cloud to object coordinates using the quaternions stored in the 'meta' folder, but it didn't work. I'd like to know how to convert the point cloud in the .pth format to object coordinates and how to utilize the quaternions. Thank you.
Hi, Thanks for your awesome work.
Since GAPartNet dataset is built on SAPIEN, I would like to ask about how to synthesize data (e.g. image format) of articulation objects using of various states using the original urdf file. (i.e., Before rotation and after rotation)
However, I have not found any clue from the documentation of SAPEIN.
Can you provide several tips or pseudo codes to insight me?
That will be very helpful to me! Thanks in advance.
This is excellent work. After downloading the data and extracting it, I found that inside, there is only the PartNet dataset, and there is no corresponding data for AKB-48.
Thanks for your remarkable work!! I want to obtain your dataset,but failed.How to solve it?
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.