diegovalsesia / graphcnn-gan Goto Github PK

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.

Hello Diego,
Thanks for sharing your code. It's really an excellent idea to use GAN in point cloud.
This repo is kind of large, which could easily lead to download failure. I tried three times and still failed. I think you can set up another repo without results.

Hello.
I want no upsampling.
but, I have issues.

config.py

self.upsampling = [False] + [False]*4 + [False]

bash launch_gconv_train.sh

chair
6778 pclouds were loaded. They belong in 1 shape-classes.

Traceback (most recent call last):
File "/home/sohee/anaconda3/envs/python3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1659, in _create_c_op
c_op = c_api.TF_FinishOperation(op_desc)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Dimensions must be equal, but are 2048 and 128 for 'add_33' (op: 'Add') with input shapes: [?,2048,3], [?,128,3].

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "gconv_code/main.py", line 55, in
model = GAN(config)
File "/home/sohee/coding/PointCloud/GraphCNN-GAN/gconv_code/gan.py", line 161, in init
self.__make_compute_graph()
File "/home/sohee/coding/PointCloud/GraphCNN-GAN/gconv_code/gan.py", line 582, in __make_compute_graph
self.x_int = epsilon * self.x + (1 - epsilon) * self.x_hat
File "/home/sohee/anaconda3/envs/python3/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py", line 812, in binary_op_wrapper
return func(x, y, name=name)
File "/home/sohee/anaconda3/envs/python3/lib/python3.6/site-packages/tensorflow/python/ops/gen_math_ops.py", line 365, in add
"Add", x=x, y=y, name=name)
File "/home/sohee/anaconda3/envs/python3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 788, in _apply_op_helper
op_def=op_def)
File "/home/sohee/anaconda3/envs/python3/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py", line 507, in new_func
return func(*args, **kwargs)
File "/home/sohee/anaconda3/envs/python3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 3300, in create_op
op_def=op_def)
File "/home/sohee/anaconda3/envs/python3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1823, in init
control_input_ops)
File "/home/sohee/anaconda3/envs/python3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1662, in _create_c_op
raise ValueError(str(e))
ValueError: Dimensions must be equal, but are 2048 and 128 for 'add_33' (op: 'Add') with input shapes: [?,2048,3], [?,128,3].

Hi Diego Valsesia,

Could you double-check the checkpoint you provide for generating chairs? I can only get weird outputs like below:

I can successfully generate point clouds for the other 3 classes. So, I believe the problem may be in the checkpoint for chair class.

Also, there is no training/test split information provided in this repo. Did you exactly follow r-GAN's data split or you have your own splitting?

A quick answer will be highly appreciated.

Best,
He