limhoyeon / ToothGroupNetwork

3D Dental surface segmentation with Tooth Group Network
173 stars 41 forks source link

Train tgnet_fps and find the error #32

Open Frq-F opened 7 months ago

Frq-F commented 7 months ago

Hello, when I train the tgnet_fps model, I got following error Traceback (most recent call last): File "start_train.py", line 51, in runner(config, model) File "/workspace/ToothGroupNetwork-main/ToothGroupNetwork-main/runner.py", line 53, in runner gen_set = [get_generator_set(config["generator"], False)] File "/workspace/ToothGroupNetwork-main/ToothGroupNetwork-main/runner.py", line 28, in get_generator_set point_loader = DataLoader( File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 268, in init sampler = RandomSampler(dataset, generator=generator) File "/opt/conda/lib/python3.8/site-packages/torch/utils/data/sampler.py", line 102, in init raise ValueError("num_samples should be a positive integer " ValueError: num_samples should be a positive integer value, but got num_samples=0

How to solve this issue? By the way , I use the challange dataset.

Frq-F commented 7 months ago

My base_name_train_fold.txt belike 00OMSZGW_lower_lower_sampled_points.npy 00OMSZGW_upper_upper_sampled_points.npy 01328DDN_lower_lower_sampled_points.npy...... Is that right? or it should contain input_data_dir_path

Frq-F commented 7 months ago

I modify the code ,change the parameter of shuffle from true to false,solve this issue。 point_loader = DataLoader( DentalModelGenerator( config["input_data_dir_path"], aug_obj_str=config["aug_obj_str"], split_with_txt_path=config["train_data_split_txt_path"] ), shuffle=False, batch_size=config["train_batch_size"], collate_fn=collate_fn ) But my data path is not set right, the train_set=0, validation_set=0. My input_data_dir_path is set to the folder where data is stored,and txt file belike 00OMSZGW_lower_lower_sampled_points.npy 00OMSZGW_upper_upper_sampled_points.npy 01328DDN_lower_lower_sampled_points.npy......

Frq-F commented 7 months ago

I solve the problem ,txt file should be like 01328DDN

ericnlt commented 7 months ago

I solve the problem ,txt file should be like 01328DDN

What's your video card? How long did it take to train tgnet_fps?