dongkwonjin / semantic-line-mwcs Goto Github PK

great work,Does it support using own data for training?thanks

Hello!
When starting training S-Net, the following error occurs：
in load_model_for_train
checkpoint = torch.load(cfg.dir['weight'] + 'checkpoint_final')
FileNotFoundError: [Errno 2] No such file or directory: '/MWCS/Modeling/S_Net/output_snet_SEL/train/weight/checkpoint_final'

Where can I get this weight file？
thanks！

1. The instructions stated in readme are not clear wheather they are for testing, training or evaluation. Please infrom the correct guidelines for xtesting training and evaluation of the data.
2. Provide instructions to use test_paper option.

下载了原始数据和处理过的数据，Preprocessing S_Net H-Net三个改了数据配置什么的都没法直接运行

Hi, could you provide basic instruction to test the code ? I'd like to try inference on my images. It is my understanding that I have to preprocess my images using Preprocessing/main.py but is not clear to me how to edit the option/config.py file.

Hi, thanks for the repo.
I'm trying to reproduce the results on the SEL dataset from scratch.
I downloaded the raw dataset. When I run the script to generate the preprocessed data,

cd Semantic-Line-MWCS/Preprocessing/code/
python main.py

I run into an error train.pickle is not available. This file indeed is not part of the raw dataset.

Traceback (most recent call last):
  File "main.py", line 29, in <module>
    main()
  File "main.py", line 23, in main
    dict_DB = prepare_dataloader(cfg, dict_DB)
  File "/home/testuser/Semantic-Line-MWCS/Preprocessing/code/libs/prepare.py", line 7, in prepare_dataloader
    dataset = Dataset_train(cfg=cfg, datalist=cfg.datalist_mode)
  File "/home/testuser/Semantic-Line-MWCS/Preprocessing/code/datasets/dataset.py", line 16, in __init__
    self.datalist = load_pickle(os.path.join(self.cfg.dir['dataset'][self.cfg.dataset_name], 'data/', datalist))
  File "/home/azureuser/Semantic-Line-MWCS/Preprocessing/code/libs/utils.py", line 68, in load_pickle
    with open(file_path + '.pickle', 'rb') as f:
FileNotFoundError: [Errno 2] No such file or directory: '/datadrive/datasets/SEL/data/train.pickle'

The file, train.pickle file is part of preprocessed data.
However, I would like to generate all the preprocessing data using the scripts from the repository.
Could you please share if we can generate the preprocessing data using just the raw dataset and preprocessing scripts? Thank you!

thanks for your great work.

Thank you for your great work! It seems that the preprocessed data downloaded from the provided link does not contain images?