The error in ‘Application - Part Segmentation’

[robin1chen2]

My environment is ubuntu16.04，cuda9.2，cudnn7.6.4,pytorch1.1.0,faiss and visdom installed.

I used the shapenet dataset in your Google Drive.Its location is '/media/rmv/data1/CPR/shapenetcore_partanno_segmentation_benchmark_v0_normal/',and I changed the 'dataroot' in the opinion of part-seg folder.

Then I compiled customized cuda code.The process is showed below.

Then I began the training,but I found the error''No module named 'util'''.To slove this,I add the 'SO-Net-master' folder path to the python path.

At last it showd the error in the error.txt below,and I cannot figure out how to solve it. error.txt

[robin1chen2]

To avoid the Error,I Commented out these code in ‘train.py' ：

            visualizer.print_current_errors(epoch, epoch_iter, errors, t)
            visualizer.plot_current_errors(epoch, float(epoch_iter) / dataset_size, opt, errors)

and then I ran the 'train.py', it can run, but visdom server couldn't show any information. Instead, I can only see the output in the terminal: I wonder how to get the training and test log to particular object like 'table', 'car' and so on. And how to get the '.txt' or '.npz' files which are the test results?

[qingfeng0830]

Is this problem solved please?