lzzcd001 / meshdiffusion Goto Github PK

Hellow，when i want to train teh model, i find in shapenet_dmet_dataset.py __getitem__ function, the variable datum is a dict,
'sdf:' tensor([]), 'deform' : tensor([[]]), 'deform_unmasked' : tensor(), but the datum be used like a tensor(eg : datum[:, :1], datum[1:]), can you help sovle my problem

The error info:
sdf_sign = torch.sign(datum[:, :1]) TypeError: unhashable type: 'slice'

Hello~

I'm not sure what does "--config.data.filter_meta_path=$TRAIN_SPLIT_FILE" mean since I saved the path of all 3D_cube_grid.pt to a json file, which represents that there is only one json file in my project here.

Could you please illustrate what does "a json list of indices to be included in the training set" mean?

Thanks.

Hello, I want to learn something through this project, I successfully configured the running environment. My environment is as follows：
CUDA: 11.3
torch: 1.12.0+cu113
touchaudio: 0.12.0+cu113
touchvision: 0.13.0+cu113

When I finished the data set, when I executed the training statement, it could not complete it, and its error message was as follows：

RuntimeError: CUDA error: no kernel image is available for execution on the device
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.

I have searched for many ways, but none of them have been solved, do you know how to solve it?

Thanks in advance.

Hi,

Thanks for your encouraging work on mesh generation and the application of diffusion models!

When I try to train it on ShapeNet dataset following the instructions given in the README, I find that it's really time-consuming to generate the ground truth Tetrahedra representation of all models for each category. It requires about 1500 GPU hours for RTX3090 to generate the Tet ground truth on the Chair category. Will you please provide the generated tet representation of Shapenet?

Thanks in adance.

Thanks for open sourcing the project.

I wonder if you can help with this error: "UnpicklingError: Failed to interpret file './0001.npy' as a pickle" when loading the preprocessed data using numpy. My numpy version is 1.24.3.

Hi, i have downloaded your preprocessed dataset and wish to execute the training process, but i have no idea on how to generate the meta json file, could you give me some hint please?

Hi,

Thanks for your great works.

I have no idea on how to config DMTet and Diffusion. It seems that the default config under configs is not complete for running the code. Will you please provide an example or any doc related?

Thanks in adance.

Hi,
thanks for your detailed introduction. Recently I try to reproduce some conditional generation results stated in Sec.5.3, but all of the generated meshes are greatly different from the ground truths. Thus I want to learn about how to reproduce the visualization results in Sec. 5.3. I've searched for many ways, but all of them don't work. Could you tell me how to reproduce the conditional generation results? The following images are the dmtet after inialization and after diffusion.

Thanks in advanced.

Is there any specific reason why the MeshDiffusion model is not trained on multiple objects? Is the model not generalizable to multiple objects or unseen objects?

Hello,
the code produces only .npy files, but there should be obj meshes as well. There are no errors and the command I use is this:

The current code cannot be trained and the quality of the generated tetrahedral mesh is not good. Am I doing something wrong?

Hi.
You provider npy data do not contains a _ in the filename. Why are you spliting it here?

The file names are just 0000.npy

Hi, thank you for sharing the awesome work! I'm wondering what's the difference between the checkpoints in the google drive and the links?

Where shall I get the metadata of given DMTet dataset?

data.meta_path = "PLACEHOLDER" 
data.filter_meta_path = "PLACEHOLDER" 

Or I should use the given dataset to run tets_to_3dgrid.py and save_meta.py for the metadata? Or worsely, I can only get this by doing all the trainning steps?

The $SAMPLE_PATH should be a meshes? If so, why the U**nconditional Generation ** and Single-view Conditional Generation requires different file type of .npy and .obj?The eval.py is just used for generate a image of one view of the object presented as meshes $SAMPLE_PATH?

你好，我在运行命令时：python eval.py --config ./configs/res64.json --out-dir ./output --sample-path ./data/0.npy --deform-scale 3.0 时，会出现以下报错：ImportError: DLL load failed while importing nvdiffrast_plugin_gl: 找不到指定的模块。环境都按照步骤装好了，这个库需要再次install吗？

When I try to run /nvdiffrec/eval.py:
python eval.py --config=configs/res64.json --out-dir=../results --sample-path=../results/0.npy --deform-scale=3.0

I have this complex error:
############################################START#######################################
get cubemap
get light object
light trainable or not: True
build mips
Using /root/.cache/torch_extensions/py38_cu121 as PyTorch extensions root...
Detected CUDA files, patching ldflags
Emitting ninja build file /root/.cache/torch_extensions/py38_cu121/renderutils_plugin/build.ninja...
Building extension module renderutils_plugin...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
ninja: no work to do.
Loading extension module renderutils_plugin...
build mips done
shape of generated data (4, 4, 64, 64, 64)
0%| | 0/4 [00:00<?, ?it/s]
Traceback (most recent call last):
File "eval.py", line 437, in
result_image, _ = validate_itr(glctx, prepare_batch(v_pose, FLAGS.background), geometry, opt_material, lgt, FLAGS)
File "eval.py", line 210, in validate_itr
buffers = geometry.render(glctx, target, lgt, opt_material)
File "/mnt/raid/C1_ML_Analysis/source/blender/famli-ultra-sim/dl/MeshDiffusion/nvdiffrec/lib/geometry/dmtet.py", line 344, in render
return render.render_mesh(glctx, opt_mesh, target['mvp'], target['campos'], lgt, target['resolution'], spp=target['spp'],
File "/mnt/raid/C1_ML_Analysis/source/blender/famli-ultra-sim/dl/MeshDiffusion/nvdiffrec/lib/render/render.py", line 291, in render_mesh
rast, db = peeler.rasterize_next_layer()
File "/mnt/raid/C1_ML_Analysis/source/blender/famli-ultra-sim/dl/MeshDiffusion/nvdiffrec/nvdiffrast/nvdiffrast/torch/ops.py", line 378, in rasterize_next_layer
result = _rasterize_func.apply(self.raster_ctx, self.pos, self.tri, self.resolution, self.ranges, self.grad_db, self.peeling_idx)
File "/usr/local/lib/python3.8/dist-packages/torch/autograd/function.py", line 508, in apply
return super().apply(args, kwargs)
File "/mnt/raid/C1_ML_Analysis/source/blender/famli-ultra-sim/dl/MeshDiffusion/nvdiffrec/nvdiffrast/nvdiffrast/torch/ops.py", line 246, in forward
out, out_db = _get_plugin(gl=True).rasterize_fwd_gl(raster_ctx.cpp_wrapper, pos, tri, resolution, ranges, peeling_idx)
RuntimeError: CUDA mapped array data width mismatch
terminate called after throwing an instance of 'c10::Error'
what(): Cuda error: 208[cudaGraphicsUnregisterResource(s.cudaColorBuffer[i]);]
Exception raised from rasterizeReleaseBuffers at /mnt/raid/C1_ML_Analysis/source/blender/famli-ultra-sim/dl/MeshDiffusion/nvdiffrec/nvdiffrast/nvdiffrast/common/rasterize_gl.cpp:620 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::__cxx11::basic_string<char, std::char_traits, std::allocator >) + 0x6c (0x7fe1baf4f1bc in /usr/local/lib/python3.8/dist-packages/torch/lib/libc10.so)
frame #1: c10::detail::torchCheckFail(char const, char const, unsigned int, std::__cxx11::basic_string<char, std::char_traits, std::allocator > const&) + 0xfa (0x7fe1baf150ea in /usr/local/lib/python3.8/dist-packages/torch/lib/libc10.so)
frame #2: rasterizeReleaseBuffers(int, RasterizeGLState&) + 0x25e (0x7fe181b27764 in /root/.cache/torch_extensions/py38_cu121/nvdiffrast_plugin_gl/nvdiffrast_plugin_gl.so)
frame #3: RasterizeGLStateWrapper::~RasterizeGLStateWrapper() + 0x37 (0x7fe181b404c9 in /root/.cache/torch_extensions/py38_cu121/nvdiffrast_plugin_gl/nvdiffrast_plugin_gl.so)
frame #4: std::default_delete::operator()(RasterizeGLStateWrapper) const + 0x26 (0x7fe181b39080 in /root/.cache/torch_extensions/py38_cu121/nvdiffrast_plugin_gl/nvdiffrast_plugin_gl.so)
frame #5: std::unique_ptr<RasterizeGLStateWrapper, std::default_delete >::~unique_ptr() + 0x56 (0x7fe181b37252 in /root/.cache/torch_extensions/py38_cu121/nvdiffrast_plugin_gl/nvdiffrast_plugin_gl.so)
frame #6: + 0xbaba5 (0x7fe181b35ba5 in /root/.cache/torch_extensions/py38_cu121/nvdiffrast_plugin_gl/nvdiffrast_plugin_gl.so)
frame #7: + 0x3db37b (0x7fe0ff62437b in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_python.so)
frame #8: + 0x3dc323 (0x7fe0ff625323 in /usr/local/lib/python3.8/dist-packages/torch/lib/libtorch_python.so)
frame #9: python() [0x5d1938]
frame #10: python() [0x5a978d]

frame #12: python() [0x6aa83a]
frame #13: python() [0x4effff]
frame #19: __libc_start_main + 0xf3 (0x7fe1c13ea083 in /usr/lib/x86_64-linux-gnu/libc.so.6)

Aborted (core dumped)
############################################END#########################################

I did check to have everything install well (rasterize, pytorch3d, tinycudann)

CUDA: Cuda compilation tools, release 12.1, V12.1.66. Build cuda_12.1.r12.1/compiler.32415258_0

GPU:
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 515.105.01 Driver Version: 515.105.01 CUDA Version: 12.1 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA A100-SXM... On | 00000000:81:00.0 Off | 0 |
| N/A 64C P0 301W / 500W | 63643MiB / 81920MiB | 100% Default |
| | | Disabled |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
+-----------------------------------------------------------------------------+

Thanks to anyone who may read this issue.

Hi. Thank you for releasing the code.
When I run
python main_diffusion.py --mode=train --config=./configs/res64.py --config.data.meta_path=./meta_file.json --config.data.filter_meta_path=./metadata/train_split/chair_train.json --config.data.extension=npy i get the following error:

W0222 02:11:24.233449 140201066399616 utils.py:10] No checkpoint found at PLACEHOLDER/checkpoints-meta/checkpoint.pth. Returned the same state as input
----- Assigning mask -----
I0222 02:11:24.233782 140201066399616 trainer.py:56] ./meta_file.json, ./metadata/train_split/chair_train.json
----- Assigning mask -----
work dir: PLACEHOLDER
sdf normalized or not:  True
dataset  with sdf normalized: True
Traceback (most recent call last):
  File "main_diffusion.py", line 28, in <module>
    app.run(main)
  File "/miniconda3x86/envs/get3d/lib/python3.8/site-packages/absl/app.py", line 308, in run
    _run_main(main, args)
  File "//miniconda3x86/envs/get3d/lib/python3.8/site-packages/absl/app.py", line 254, in _run_main
    sys.exit(main(argv))
  File "main_diffusion.py", line 21, in main
    trainer.train(FLAGS.config)
  File "/MeshDiffusion/lib/diffusion/trainer.py", line 68, in train
    train_dataset = ShapeNetDMTetDataset(json_path, deform_scale=config.model.deform_scale, aug=True, grid_mask=mask, 
  File "MeshDiffusion/lib/dataset/shapenet_dmtet_dataset.py", line 25, in __init__
    full_id_list = [int(x.rstrip().split('_')[-1][:-len(self.extension)-1]) for i, x in enumerate(self.fpath_list)]
  File "/MeshDiffusion/lib/dataset/shapenet_dmtet_dataset.py", line 25, in <listcomp>
    full_id_list = [int(x.rstrip().split('_')[-1][:-len(self.extension)-1]) for i, x in enumerate(self.fpath_list)]
ValueError: invalid literal for int() with base 10: '../res64/chair/0000'

This line throws an error full_id_list = [int(x.rstrip().split('_')[-1][:-len(self.extension)-1]) for i, x in enumerate(self.fpath_list)].

Why are you trying to split

meta_file.json
{
"../res64/chair/0000.npy"
"../res64/chair/0001.npy"
...
}

shapenet_json
{
"chair/c97b5b80a24030ae70e99aac955544a0/model.obj"
"chair/fbca73a2c226a86a593a4d04856c4691/model.obj"
"chair/de3e082195346ca419fb4103277a6b93/model.obj"
...
}

What am I missing here?

Thank you.

Hello~It is really an impressive work.

Could you please instruct me that how to create a list of paths of all ground-truth meshes and store them as a json file under shapenet_json. For example, I've downloaded ShapeNetCore.

Thanks.

Hi.
I'm facing few issues. one solution leads to another problem.

1. I installed pytorch3d v 0.7.4 using conda install pytorch3d -c pytorch3d. This lead to this error

 python -c "import pytorch3d.ops"
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "~miniconda3x86/envs/mesh/lib/python3.8/site-packages/pytorch3d/ops/__init__.py", line 7, in <module>
    from .ball_query import ball_query
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/pytorch3d/ops/ball_query.py", line 10, in <module>
    from pytorch3d import _C
ImportError: /lib64/libstdc++.so.6: version `GLIBCXX_3.4.26' not found (required by ~/envs/mesh/lib/python3.8/site-packages/pytorch3d/_C.cpython-38-x86_64-linux-gnu.so)

I solved the GLIBCXX_3.4.26 not found error by exporting a recent version of lib64/libstdc++.so.6 (export LD_LIBRARY_PATH=~/miniconda3x86/lib see.
python -c "import pytorch3d.ops" now works.

2. I then install pymeshlab v 2022.2.post3, I chose version 2022.2.post3 because other versions lead to this issue #27.
   After the installation of pymeshlab, I get this error

python -c "import pymeshlab as p; ms = p.MeshSet(); ms.meshing_isotropic_explicit_remeshing()"
Traceback (most recent call last):
  File "<string>", line 1, in <module>
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/pymeshlab/__init__.py", line 11, in <module>
    from .pmeshlab import *
ImportError: /lib64/libc.so.6: version `GLIBC_2.25' not found (required by ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/pymeshlab/lib/libpython3.8.so.1.0)

I solved this by exporting export LD_LIBRARY_PATH=/lib64, (i.e., the old libstdc++.so.6).

I can combine the two LD_LIBRARY_PATH paths, but one libstdc++.so.6 will simply override the previous one.

Can someone point me to the right versions of pymeshlab and pytorch3d to use?
Thanks.

Thank you for your excellent work!
I have an obj file with vertex colors, how to render it with textures?

Hi , I am trying to learn this paper and project. But I am a beginner so I have met too many challenges.Could I know if this project running on windows or linux?I have met the following error:

ImportError: cannot import name '_rref_context_get_debug_info' from 'torch.distributed.rpc'

I try to study it on windows.And I don't know if there is something wrong with the environment configuration.
Sorry for taking up your valuable time.

Hi, thanks for the great work. Could you please share the models trained on rifle and table classes? It would be much appreciated.

I want to get a depth map from Mesh. Please send me a sample code using nvdiffrast!

Thank you very much!

Hi, thanks for your great work. I want to know how to render the mesh with shadow. (e.g., Fig.1 in your ICLR paper).
Could you please provide the code or method to render files in *.obj format to get those results.

Nice work! I am planning to train the network on my own data, so I followed the instructions in ReadMe to process the data, and I also obtained the pt file generated by DMTet. But when I wanted to load data for training, I found that the data loader did not properly handle pt file. The data format in the preprocessed shapenet you provided is npy. So I want to know if I missed any steps? Thank you!

The $META_FILE (provided by you) contains 6775 dmtet 3D cubic:

{
"/res64/chair/0000.npy",
"/res64/chair/0001.npy",
...
"/res64/chair/6774.npy"
}

The Train Split file ./metadata/train_split/chair_train.json contains 4744 items {0, 1, 10, 22, ... 6776}
This is a subset of the shapenet chair dataset.

While the Shapenet dataset contains 6777 items:

{
"/ShapeNetCore.v1/03001627/c97b5b80a24030ae70e99aac955544a0/model.obj",
....
"/ShapeNetCore.v1/03001627/8a455c7acaef577824f0493013a8318f/model.obj"
}

I can understand that thedmet 3D cubic index 0000.npy refers to the index in train_split/chair_train.json. But is there a way, to know which model.obj generated the dmtet 3D cubic?

There is also 2dmtet missing (6777 - 6775)?

I run the main_diffusion.py file for unconditional generation, but the tensorflow is required for installation. Is the project not pytorch only? which version for tensorflow installed?

Hi, when I try to load your npy data using np.load, it throws this error.
Even after passing allow_pickle=True to np.load(...), I still face the same problem

How did you load your npy files?
Thanks

Traceback (most recent call last):
  File "main_diffusion.py", line 28, in <module>
    app.run(main)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/absl/app.py", line 308, in run
    _run_main(main, args)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/absl/app.py", line 254, in _run_main
    sys.exit(main(argv))
  File "main_diffusion.py", line 21, in main
    trainer.train(FLAGS.config)
  File "~/MeshDiffusion/lib/diffusion/trainer.py", line 100, in train
    batch = next(data_iter)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in __next__
    data = self._next_data()
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
    return self._process_data(data)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
    data.reraise()
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/_utils.py", line 434, in reraise
    raise exception
ValueError: Caught ValueError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
    data = fetcher.fetch(index)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/gpfs/u/scratch/QCML/shared/mesh/MeshDiffusion/lib/dataset/shapenet_dmtet_dataset.py", line 39, in __getitem__
    datum = torch.tensor(np.load(self.fpath_list[idx]))
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/numpy/lib/npyio.py", line 438, in load
    raise ValueError("Cannot load file containing pickled data "
ValueError: Cannot load file containing pickled data when allow_pickle=False

when passing allow_pickle=True, This is the error

dataset  with sdf normalized: True
data loader set
I0222 11:28:01.073143 140650419656576 trainer.py:92] Starting training loop at step 0.
Traceback (most recent call last):
  File "main_diffusion.py", line 28, in <module>
    app.run(main)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/absl/app.py", line 308, in run
    _run_main(main, args)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/absl/app.py", line 254, in _run_main
    sys.exit(main(argv))
  File "main_diffusion.py", line 21, in main
    trainer.train(FLAGS.config)
  File "/gpfs/u/scratch/QCML/shared/mesh/MeshDiffusion/lib/diffusion/trainer.py", line 100, in train
    batch = next(data_iter)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 521, in __next__
    data = self._next_data()
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1203, in _next_data
    return self._process_data(data)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/dataloader.py", line 1229, in _process_data
    data.reraise()
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/_utils.py", line 434, in reraise
    raise exception
_pickle.UnpicklingError: Caught UnpicklingError in DataLoader worker process 0.
Original Traceback (most recent call last):
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/numpy/lib/npyio.py", line 441, in load
    return pickle.load(fid, **pickle_kwargs)
_pickle.UnpicklingError: invalid load key, 'v'.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/_utils/worker.py", line 287, in _worker_loop
    data = fetcher.fetch(index)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in fetch
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py", line 49, in <listcomp>
    data = [self.dataset[idx] for idx in possibly_batched_index]
  File "/gpfs/u/scratch/QCML/shared/mesh/MeshDiffusion/lib/dataset/shapenet_dmtet_dataset.py", line 39, in __getitem__
    datum = torch.tensor(np.load(self.fpath_list[idx], allow_pickle=True))
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/numpy/lib/npyio.py", line 443, in load
    raise pickle.UnpicklingError(
_pickle.UnpicklingError: Failed to interpret file '~/MeshDiffusion/dmtet_npy_folder/res64/chair/4618.npy' as a pickle

Hi,

Congrats for the great work!! Additionaly, I've been trying to run the Single-view Conditional Generation (over file : fit_singleview.py) but I receive the error message: NameError: name 'global_index' is not defined.

In other files such as data/tets_to_3dgrid.py and nvdiffrec/fit_dmtets.py, the variable global_index is predefined regarding two input variables named: FLAGS.index and FLAGS.split_size. As those are not solicitated as inputs on fit_singleview.py, could you clarify how should I define it? Tks!!

Hi. II have this error when running
python fit_dmtets.py --config ./configs/res64.json --meta-path ../meta_path/shapenet_json/chair.json --out-dir ../dmtet_data_path --index 0 --split-size 100000
I already installed conda install -c conda-forge mesa-libegl-devel-cos6-x86_64 mesa-libgl-devel-cos6-x86_64 (#21 ) but the error persist.

ulti_gpu False
tet_path ./data/tets/64_tets_cropped.npz
first_stage_deform 2.0
second_stage_deform 3.0
---------
Using dmt grid of resolution 64
Traceback (most recent call last):
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1717, in _run_ninja_build
    subprocess.run(
  File "~/miniconda3x86/envs/mesh/lib/python3.8/subprocess.py", line 516, in run
    raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "fit_dmtets.py", line 636, in <module>
    glctx = dr.RasterizeGLContext()
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/torch/ops.py", line 221, in __init__
    self.cpp_wrapper = _get_plugin(gl=True).RasterizeGLStateWrapper(output_db, mode == 'automatic', cuda_device_idx)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/torch/ops.py", line 118, in _get_plugin
    torch.utils.cpp_extension.load(name=plugin_name, sources=source_paths, extra_cflags=opts, extra_cuda_cflags=opts+['-lineinfo'], extra_ldflags=ldflags, with_cuda=True, verbose=False)
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1124, in load
    return _jit_compile(
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1337, in _jit_compile
    _write_ninja_file_and_build_library(
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1449, in _write_ninja_file_and_build_library
    _run_ninja_build(
  File "~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1733, in _run_ninja_build
    raise RuntimeError(message) from e
RuntimeError: Error building extension 'nvdiffrast_plugin_gl': [1/4] c++ -MMD -MF glutil.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/TH -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem ~/miniconda3x86/envs/mesh/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -DNVDR_TORCH -c ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/glutil.cpp -o glutil.o 
FAILED: glutil.o 
c++ -MMD -MF glutil.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/TH -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem ~/miniconda3x86/envs/mesh/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -DNVDR_TORCH -c ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/glutil.cpp -o glutil.o 
In file included from ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/glutil.cpp:14:
~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/glutil.h:36:10: fatal error: EGL/egl.h: No such file or directory
   36 | #include <EGL/egl.h>
      |          ^~~~~~~~~~~
compilation terminated.
[2/4] c++ -MMD -MF rasterize_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/TH -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem ~/miniconda3x86/envs/mesh/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -DNVDR_TORCH -c ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/rasterize_gl.cpp -o rasterize_gl.o 
FAILED: rasterize_gl.o 
c++ -MMD -MF rasterize_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/TH -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem ~/miniconda3x86/envs/mesh/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -DNVDR_TORCH -c ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/rasterize_gl.cpp -o rasterize_gl.o 
In file included from ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/rasterize_gl.h:16,
                 from ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/rasterize_gl.cpp:9:
~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/common/glutil.h:36:10: fatal error: EGL/egl.h: No such file or directory
   36 | #include <EGL/egl.h>
      |          ^~~~~~~~~~~
compilation terminated.
[3/4] c++ -MMD -MF torch_rasterize_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/TH -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem ~/miniconda3x86/envs/mesh/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -DNVDR_TORCH -c ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/torch/torch_rasterize_gl.cpp -o torch_rasterize_gl.o 
FAILED: torch_rasterize_gl.o 
c++ -MMD -MF torch_rasterize_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/TH -isystem ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem ~/miniconda3x86/envs/mesh/include/python3.8 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++14 -DNVDR_TORCH -c ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/torch/torch_rasterize_gl.cpp -o torch_rasterize_gl.o 
In file included from ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/torch/../common/rasterize_gl.h:16,
                 from ~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/torch/torch_rasterize_gl.cpp:12:
~/miniconda3x86/envs/mesh/lib/python3.8/site-packages/nvdiffrast/torch/../common/glutil.h:36:10: fatal error: EGL/egl.h: No such file or directory
   36 | #include <EGL/egl.h>
      |          ^~~~~~~~~~~
compilation terminated.
ninja: build stopped: subcommand failed.

Hi
I used pymeshlab 1.21.2 and 0.1.7 but have this error.

Traceback (most recent call last):
  File "eval.py", line 451, in <module>
    ms.meshing_isotropic_explicit_remeshing()
AttributeError: 'pymeshlab.pmeshlab.MeshSet' object has no attribute 'meshing_isotropic_explicit_remeshing'

Describe
Runing Unconditional Generation on ubuntu. Finished first step successfully, and show the error below in second step. Seems like somthing wrong with the ninjia, can you help me?

Reproduce

python eval.py --config configs/res64.json -o outdir -sp '../outputs/0.npy' -ds 3.0 --angle-ind 25 -ns 1

Error

Warning:
Unable to load the following plugins:

    libio_e57.so: libio_e57.so does not seem to be a Qt Plugin.

Cannot load library /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/pymeshlab/lib/plugins/libio_e57.so: (/usr/lib/x86_64-linux-gnu/libp11-kit.so.0: undefined symbol: ffi_type_pointer, version LIBFFI_BASE_7.0)

Traceback (most recent call last):
File "/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1893, in _run_ninja_build
subprocess.run(
File "/root/miniconda3/envs/meshdiffusion/lib/python3.9/subprocess.py", line 528, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "/root/code/MeshDiffusion/nvdiffrec/eval.py", line 367, in
glctx = dr.RasterizeGLContext()
File "/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/torch/ops.py", line 221, in init
self.cpp_wrapper = _get_plugin(gl=True).RasterizeGLStateWrapper(output_db, mode == 'automatic', cuda_device_idx)
File "/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/torch/ops.py", line 118, in _get_plugin
torch.utils.cpp_extension.load(name=plugin_name, sources=source_paths, extra_cflags=opts, extra_cuda_cflags=opts+['-lineinfo'], extra_ldflags=ldflags, with_cuda=True, verbose=False)
File "/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1284, in load
return _jit_compile(
File "/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1509, in _jit_compile
_write_ninja_file_and_build_library(
File "/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1624, in _write_ninja_file_and_build_library
_run_ninja_build(
File "/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/utils/cpp_extension.py", line 1909, in _run_ninja_build
raise RuntimeError(message) from e
RuntimeError: Error building extension 'nvdiffrast_plugin_gl': [1/6] c++ -MMD -MF common.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/TH -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /root/miniconda3/envs/meshdiffusion/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DNVDR_TORCH -c /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/common.cpp -o common.o
[2/6] c++ -MMD -MF rasterize_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/TH -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /root/miniconda3/envs/meshdiffusion/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DNVDR_TORCH -c /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/rasterize_gl.cpp -o rasterize_gl.o
FAILED: rasterize_gl.o
c++ -MMD -MF rasterize_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/TH -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /root/miniconda3/envs/meshdiffusion/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DNVDR_TORCH -c /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/rasterize_gl.cpp -o rasterize_gl.o
In file included from /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/rasterize_gl.h:16,
from /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/rasterize_gl.cpp:9:
/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/glutil.h:36:10: fatal error: EGL/egl.h: No such file or directory
36 | #include <EGL/egl.h>
| ^~~~~~~~~~~
compilation terminated.
[3/6] c++ -MMD -MF glutil.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/TH -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /root/miniconda3/envs/meshdiffusion/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DNVDR_TORCH -c /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/glutil.cpp -o glutil.o
FAILED: glutil.o
c++ -MMD -MF glutil.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/TH -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /root/miniconda3/envs/meshdiffusion/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DNVDR_TORCH -c /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/glutil.cpp -o glutil.o
In file included from /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/glutil.cpp:14:
/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/common/glutil.h:36:10: fatal error: EGL/egl.h: No such file or directory
36 | #include <EGL/egl.h>
| ^~~~~~~~~~~
compilation terminated.
[4/6] c++ -MMD -MF torch_rasterize_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/TH -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /root/miniconda3/envs/meshdiffusion/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DNVDR_TORCH -c /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/torch/torch_rasterize_gl.cpp -o torch_rasterize_gl.o
FAILED: torch_rasterize_gl.o
c++ -MMD -MF torch_rasterize_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/TH -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /root/miniconda3/envs/meshdiffusion/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DNVDR_TORCH -c /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/torch/torch_rasterize_gl.cpp -o torch_rasterize_gl.o
In file included from /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/torch/../common/rasterize_gl.h:16,
from /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/torch/torch_rasterize_gl.cpp:12:
/root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/torch/../common/glutil.h:36:10: fatal error: EGL/egl.h: No such file or directory
36 | #include <EGL/egl.h>
| ^~~~~~~~~~~
compilation terminated.
[5/6] c++ -MMD -MF torch_bindings_gl.o.d -DTORCH_EXTENSION_NAME=nvdiffrast_plugin_gl -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE="_gcc" -DPYBIND11_STDLIB="_libstdcpp" -DPYBIND11_BUILD_ABI="_cxxabi1011" -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/torch/csrc/api/include -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/TH -isystem /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/torch/include/THC -isystem /usr/local/cuda/include -isystem /root/miniconda3/envs/meshdiffusion/include/python3.9 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -DNVDR_TORCH -c /root/miniconda3/envs/meshdiffusion/lib/python3.9/site-packages/nvdiffrast/torch/torch_bindings_gl.cpp -o torch_bindings_gl.o
ninja: build stopped: subcommand failed.

Hello, I am a beginner，I installed pytorch3d and tinycudann when running, but install one of them first and then install the other, the first installed could not be found, it seems that there is a conflict between these two, I would like to ask if there is a problem with my version configuration？
windows11
python：3.8
cuda：11.6
pytorch：1.12.0
pytorch3d：0.7.1
tinycudann：1.7
I can see these packages in conda list, but when i import this packages shows ‘no module name pytorch3d（or tinycudann）’

I run it on linux and got the error while running the cmd

python main_diffusion.py --config=$DIFFUSION_CONFIG --mode=uncond_gen --config.eval.eval_dir=$OUTPUT_PATH --config.eval.ckpt_path=$CKPT_PATH