search

diegovalsesia / GraphCNN-GAN

Graph-convolutional GAN for point cloud generation. Code from ICLR 2019 paper Learning Localized Generative Models for 3D Point Clouds via Graph Convolution
57 stars 9 forks source link

IndexError: list index out of range #3

Open Timaces opened 4 years ago

Timaces commented 4 years ago

hi,thank you for your work. when I run the code : python main.py, there is a problem: Give me the class name (e.g. "chair"): chair Traceback (most recent call last): File "main.py", line 39, in all_pc_data = load_all_point_clouds_under_folder(class_dir, n_threads=8, file_ending='.ply', verbose=True) File "/home/omnisky/Desktop/GraphCNN-GAN-master/gconv_up_aggr_code/in_out.py", line 115, in load_all_point_clouds_under_folder pclouds, model_ids, syn_ids = load_point_clouds_from_filenames(file_names, n_threads, loader=pc_loader, verbose=verbose) File "/home/omnisky/Desktop/GraphCNN-GAN-master/gconv_up_aggr_code/in_out.py", line 120, in load_point_clouds_from_filenames pc = loader(file_names[0])[0] IndexError: list index out of range

Could you help me ? thank you very much.

diegovalsesia commented 4 years ago

Make sure you have downloaded the training data. They are the same used in https://github.com/optas/latent_3d_points and need to be placed under a data/ subdirectory

Timaces commented 4 years ago

Make sure you have downloaded the training data. They are the same used in https://github.com/optas/latent_3d_points and need to be placed under a data/ subdirectory

Hello, I have solved the problem. Can you tell me how you run this code? I run Python main.py directly and always report an error. I may not be as knowledgeable as you think.

diegovalsesia commented 4 years ago

Use the launcher scripts, they will provide all the input parameters. ./launcher_test.sh to test the model and ./launcher_train.sh to train it. You may need to create an empty directory for the output point clouds. Create it under Results/gconv_up_aggr/table/renders

Timaces commented 4 years ago

Use the launcher scripts, they will provide all the input parameters. ./launcher_test.sh to test the model and ./launcher_train.sh to train it. You may need to create an empty directory for the output point clouds. Create it under Results/gconv_up_aggr/table/renders

If the code is under gconv_up_grcode in the file, the error indexerror: list index out of range will be reported, that is, the name of the data set cannot be read. I put the code on the same level directory of gconv_up_grcode, and the error will be gone, but it will appear:

File "main.py", line 61, in

shutil.rmtree(config.render_dir)

File "/usr/lib/python2.7/shutil.py", line 239, in rmtree

onerror(os.listdir, path, sys.exc_info())

File "/usr/lib/python2.7/shutil.py", line 237, in rmtree

names = os.listdir(path)

OSError: [Errno 2] No such file or directory: ''