AlphaPav

Hi author, thanks for the amazing work. On your released pre-trained model, I can get 0.7082 F-score, 2.722 CD. However, when I train from scratch, I had some problems listed...

your [processed ShapeNet dataset ](https://gateway.infinitescript.com/?fileName=ShapeNetCompletion) has 28974 training data samples while [the PCN dataset](https://drive.google.com/drive/folders/1P_W1tz5Q4ZLapUifuOE4rFAZp6L1XTJz) has 231792 training data samples is it because your provided dataset is not completed?

> @AlphaPav > Sorry for the late reply. I don't have time to check this issue these days. > But I'm sure that there is nothing wrong with the released...

Thanks for reporting this issue! During testing, actually loss is not required. You can delete the lines related to the loss and run again. Note that we trained a model...

You can use tensorboard to see the results. `tensorboard —logdir=/path/to/log/directory` Or you can load the trained model and test. `python test.py --gpu 0 --work_dir /path/to/logfiles --model sparenet --weights /path/to/cheakpoint --test_mode...

I have the same question here. Is this problem solved?

Thanks for reporting the issue! I upload the dataset to the google drive and please try this link: https://drive.google.com/drive/folders/1m4lXUo_dxHmhb-Uhr6xSXqrQuyebJcFz?usp=sharing Let me know if there are any questions!

Thanks @HazardFY and @ehsan886 for reporting the issue. The pretrained model aims to provide a good initialization and feel free to try different learning rates to get a good pretrained...

I solved the problem by changing `dll=np.ctypeslib.load_library('render_balls_so','.')` into `dll = np.ctypeslib.load_library('render_balls_so.so', '.')`

Hi @HengerLi Sorry for the late reply. I just saw your issue. Please add the "poison_label_swap" key in the 'params.yaml' file. Thanks for reporting the issue and I will update...