zhaofang0627/hpbtt

HPBTT-Pytorch

hpbtt's Issues

Original masks of Deepfashion model dataset ?

Thanks for your great work!

I am trying to train the fashion model and there needs a seg folder here:
self.mask_ori_dir = osp.join(self.data_dir, 'seg')

I think it should be the ground truth mask? How can I get these? Would you share the method that you used?

GPU Memory requirement

Hi @zhaofang0627,
I am trying to train the framework on a Nvidia 1080Ti GPU (11 GB memory) with batch size 16 (which is set as default). I am getting out of memory errors. It would be very helpful if you state the memory that you required for training.

Thanking You,
Rahul Mitra

What is the scale net?

I notice that there is a scale net in the code. However, I cannot find the corresponding descriptions in the paper. Could you please provide more explanations about this scale net?

Besides, I find that the scale net is not trained in the training code. I am also confused about this.

Thanks!

Where can i find meshzoo 0.3.1?

seems now it only support Python 3.8

batch_hmr.pkl is missing

Hello, I am trying to run your demo code, however it had an issue where a pickle file is missing

Traceback (most recent call last):
  File "/usr/lib/python3.6/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.6/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/home/rustickey/projects/HPBTT/demo_fashion.py", line 173, in <module>
    app.run(main)
  File "/home/rustickey/.local/share/virtualenvs/HPBTT-6OKk-9qG/lib/python3.6/site-packages/absl/app.py", line 274, in run
    _run_main(main, argv)
  File "/home/rustickey/.local/share/virtualenvs/HPBTT-6OKk-9qG/lib/python3.6/site-packages/absl/app.py", line 238, in _run_main
    sys.exit(main(argv))
  File "/home/rustickey/projects/HPBTT/demo_fashion.py", line 158, in main
    batch = pickle.load(open('./HPBTT/batch_hmr.pkl', 'rb'))
FileNotFoundError: [Errno 2] No such file or directory: './HPBTT/batch_hmr.pkl'

Is there a file that I missed? Thanks.

requirements.txt and Data organization

Hi Fang,
Thanks for your impressive work, however, when I download the released code, and want to have a try about HPBTT. There are lots of library errors such as:

• chainer
• cupy
• etc.
  So, would you could be please to list the CUDA version, and all other version used in your codebase? And also if I want to train a model of the proposed HPBTT, how should I organization the dataset of DeepFashion and Market-1501?

I think it would be a great help for people like me who are interested in your wonderful work.

Looking forward to your reply.

Best wishes.