xuchen-ethz / snarf Goto Github PK

The SMPL models url is no longer accessible.

Hi, thanks for releasing the code!

I just have a simple question -- how did you guys generate data for the 2D stick toy experiment [Figure 4]? Could you share a piece of code/pointer for doing this?

Appreciate your help!

Hello,
I am trying to compile the project but I am running into an error for the meshing.py runtime compilation:
ImportError: cannot import name 'mise' from 'lib.libmise' (unknown location)
This might be a cython error but I have it installed and also the mise.pyx is in the libmise folder.
Pls let me know if this is an isolated issue or if its reproducible.
regards
SK

Hi, first of all, thank you for sharing this amazing work!
I had a question with regards to how you derived equation(13), and (14) on your paper.
(Part about implicit differentiation when calculating the gradients).

Please correct me if I'm wrong, but I think the sign of the second term in (13) should be negative.

Could you explain in details how you derived (13) from (12)?

Thank you.

在执行 sh ./download_data.sh 出现如下问题：
: not foundta.sh: 2: download_data.sh:
Downloading motion sequences...
: not foundta.sh: 4: download_data.sh:
--2021-11-03 01:26:23-- https://scanimate.is.tue.mpg.de/media/upload/demo_data/aist_demo_seq.zip%0D
Resolving scanimate.is.tue.mpg.de (scanimate.is.tue.mpg.de)... 192.124.27.142
Connecting to scanimate.is.tue.mpg.de (scanimate.is.tue.mpg.de)|192.124.27.142|:443... connected.
HTTP request sent, awaiting response... 404 Not Found
2021-11-03 01:26:24 ERROR 404: Not Found.

unzip: cannot find or open aist_demo_seq.zip, aist_demo_seq.zip.zip or aist_demo_seq.zip.ZIP.
rm: cannot remove 'aist_demo_seq.zip'$'\r': No such file or directory
mv: cannot stat './data/gLO_sBM_cAll_d14_mLO1_ch05': No such file or directory
: not foundta.sh: 9: download_data.sh:
Done!
: not foundta.sh: 11: download_data.sh:
: not foundta.sh: 12: download_data.sh:
mkdir: cannot create directory ‘outputs\r’: File exists
: not foundta.sh: 14: download_data.sh:
Downloading pretrained models ...
--2021-11-03 01:26:24-- https://dataset.ait.ethz.ch/downloads/fOUiBuCXJy/pretrained_models.zip%0D
Resolving dataset.ait.ethz.ch (dataset.ait.ethz.ch)... 129.132.114.75
Connecting to dataset.ait.ethz.ch (dataset.ait.ethz.ch)|129.132.114.75|:443... connected.
HTTP request sent, awaiting response... 404 Not Found
2021-11-03 01:26:25 ERROR 404: Not Found.

unzip: cannot find or open pretrained_models.zip, pretrained_models.zip.zip or pretrained_models.zip.ZIP.
mv: cannot stat 'outputs/pretrained_models/*': No such file or directory
'm: invalid option -- '
Try 'rm --help' for more information.
rm: cannot remove 'pretrained_models.zip'$'\r': No such file or directory

Hi
I would like to train CAPE dataset by myself.
By following the guidance, I put CAPE dataset under the data directory as shown below.

data/CAPE/03375
data/CAPE/cape_release

And I run the command for training.

python train.py datamodule=cape subject=3375 datamodule.clothing='blazerlong' +experiments=cape

Then the error was shown below.

ValueError: Dataloader returned 0 length. Please make sure that it returns at least 1 batch

Do you have any idea to solve it?
Thanks

May I ask what the code here means and why you can do this?

    # trick for implicit diff with autodiff:
    # xc = xc_opt + 0 and xc' = correction'
    xc = xc_opt + correction`

I am very confused about the AMASS results on subject 50002 trained on different versions of pytorch.

According to your environments, it suggests to install pytorch==1.7.0. However the results trained on pytorch1.7 is less than the results I train on pytorch==1.6.0 significantly. I am very confused about it.

the training loss, and evaluation IoU is shown as(blue is trained on torch==1.6.0, and red is trained on 1.7.0):

Looking forward to your reply.

Great work and thanks for releasing the code!

I'm going through the code and it seems like there is a tiny bug that exists in the broyden function. It may or may not affect the results but I feel it's good to report it:

The code here should be x_opt = x.clone(). Otherwise the following code x[ids_val] += delta_x[ids_val] will also modify the values in the x_opt.

Hi, first of all , thanks for your team's great work.

I am having trouble running CAPE training code provided by readme.md

  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 180, in instantiate
    return instantiate_node(config, *args, recursive=_recursive_, convert=_convert_)
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 266, in instantiate_node
    cfg[key] = instantiate_node(
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 245, in instantiate_node
    value = instantiate_node(
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 249, in instantiate_node
    return _call_target(_target_, *args, **kwargs)
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 64, in _call_target
    raise type(e)(
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 62, in _call_target
    return _target_(*args, **kwargs)
TypeError: Error instantiating 'lib.dataset.cape.CAPEDataProcessor' : __init__() missing 2 required positional arguments: 'opt' and 'meta_info'

and this msg is produced when I run

 python train.py datamodule=cape subject=3375 +datamodule.clothing='blazerlong' +experiments=cape  

I put + right before datamodule.clothing argument on purpose, which is different from the guide on readme.md; otherwise, it gave different error like:

omegaconf.errors.ConfigAttributeError: Key 'clothing' is not in struct
    full_key: datamodule.clothing
    object_type=dict

I think datamodule = hydra.utils.instantiate(opt.datamodule, opt.datamodule) in train.py part gave this error.

If I train on AMASS it also produces similar error

python train.py subject=50002

then

Traceback (most recent call last):
  File "D:\python_proj\snarf\train.py", line 64, in <module>
    main()
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\main.py", line 48, in decorated_main
    _run_hydra(
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\utils.py", line 377, in _run_hydra
    run_and_report(
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\utils.py", line 214, in run_and_report
    raise ex
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\utils.py", line 211, in run_and_report
    return func()
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\utils.py", line 378, in <lambda>
    lambda: hydra.run(
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\hydra.py", line 111, in run
    _ = ret.return_value
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\core\utils.py", line 233, in return_value
    raise self._return_value
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\core\utils.py", line 160, in run_job
    ret.return_value = task_function(task_cfg)
  File "D:\python_proj\snarf\train.py", line 22, in main
    datamodule = hydra.utils.instantiate(opt.datamodule, opt.datamodule) #problem starts here.
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 180, in instantiate
    return instantiate_node(config, *args, recursive=_recursive_, convert=_convert_)
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 266, in instantiate_node
    cfg[key] = instantiate_node(
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 249, in instantiate_node
    return _call_target(_target_, *args, **kwargs)
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 64, in _call_target
    raise type(e)(
  File "C:\Users\mms312\anaconda3\envs\snarf_env\lib\site-packages\hydra\_internal\instantiate\_instantiate2.py", line 62, in _call_target
    return _target_(*args, **kwargs)
TypeError: Error instantiating 'lib.dataset.dfaust.DFaustDataModule' : __init__() missing 1 required positional argument: 'opt'

Any thought or idea on this?
Thanks,