search

XChenZ / havatar

[TOG 2023] HAvatar: High-fidelity Head Avatar via Facial Model ConditionedNeural Radiance Field
https://www.liuyebin.com/havatar/
Other
122 stars 9 forks source link

Could be a compilation problem with the fused_bias_act? #8

Closed LeeHanmin closed 6 months ago

LeeHanmin commented 7 months ago

(havatar) ubuntu:~/havatar$ python train_avatar.py --datadir data/demo --logdir logs/demo Credentials not found on disk. Authenticate with:

from fused import NotebookCredentials credentials = NotebookCredentials()

Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off] /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=AlexNet_Weights.IMAGENET1K_V1. You can also use weights=AlexNet_Weights.DEFAULT to get the most up-to-date weights. warnings.warn(msg) Loading model from: /home/lhm/.local/lib/python3.8/site-packages/lpips/weights/v0.1/alex.pth Setting up [LPIPS] perceptual loss: trunk [vgg], v[0.1], spatial [off] /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=VGG16_Weights.IMAGENET1K_V1. You can also use weights=VGG16_Weights.DEFAULT to get the most up-to-date weights. warnings.warn(msg) Loading model from: /home/lhm/.local/lib/python3.8/site-packages/lpips/weights/v0.1/vgg.pth /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3526.) return _VF.meshgrid(tensors, kwargs) # type: ignore[attr-defined] StyleGAN conditon img! StyleGAN conditon img! 0.01730502024292946: 100%|█████████████████████████████████████████████████████████████████████████████████████| 3000/3000 [00:19<00:00, 150.07it/s] Saved mesh as debug/vis_motionWeightVol.obj Traceback (most recent call last): File "train_avatar.py", line 324, in main() File "train_avatar.py", line 121, in main rgbcoarse, , acc_coarse, weights, rgbfine, , acc_fine, latent_code_loss = trainer(inp_data) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, *kwargs) File "/home/lhm/havatar/model/nerf_trainer.py", line 104, in forward rgbcoarse, , acc_coarse, weights, rgbfine, , acc_fine = self.nerf_forward(ray_batch=ray_batch, background_prior=background_prior, File "/home/lhm/havatar/model/nerf_trainer.py", line 41, in nerf_forward self.model_coarse.set_conditional_embedding(front_render_cond=inputs['front_render_cond'], left_render_cond=inputs['left_render_cond'], File "/home/lhm/havatar/model/nerf_model.py", line 82, in set_conditional_embedding conditonXYplaneembedding, = self.XY_gen(inp_latents, front_render_cond) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(args, kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, kwargs) File "/home/lhm/havatar/model/styleUnet.py", line 798, in forward styles = [self.style(s) for s in styles] File "/home/lhm/havatar/model/styleUnet.py", line 798, in styles = [self.style(s) for s in styles] File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/container.py", line 215, in forward input = module(input) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, kwargs) File "/home/lhm/havatar/model/styleUnet.py", line 150, in forward out = fused_leaky_relu(out, self.bias self.lr_mul) File "/home/lhm/havatar/model/op/fused_act.py", line 122, in fused_leaky_relu return FusedLeakyReLUFunction.apply(input.contiguous(), bias, negative_slope, scale) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/autograd/function.py", line 539, in apply return super().apply(args, kwargs) # type: ignore[misc] File "/home/lhm/havatar/model/op/fused_act.py", line 69, in forward out = fused.fused_bias_act(input, bias, empty, 3, 0, negative_slope, scale) AttributeError: module 'fused' has no attribute 'fused_bias_act'

I use CUDA 12.3, torch 2.1.0+cu121. How can I solve this problem？ Looking forward to your reply！

XChenZ commented 7 months ago

Have you complied the ops? https://github.com/XChenZ/havatar/issues/5#issuecomment-1905331006

LeeHanmin commented 6 months ago

Yes, I have finished the operation: cd model/op python setup.py install Feedback is as follows: (havatar) @ubuntu:~/havatar/model/op$ python setup.py install running install running bdist_egg running egg_info writing custom_cuda_extensions.egg-info/PKG-INFO writing dependency_links to custom_cuda_extensions.egg-info/dependency_links.txt writing top-level names to custom_cuda_extensions.egg-info/top_level.txt reading manifest file 'custom_cuda_extensions.egg-info/SOURCES.txt' writing manifest file 'custom_cuda_extensions.egg-info/SOURCES.txt' installing library code to build/bdist.linux-x86_64/egg running install_lib running build_ext /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/utils/cpp_extension.py:414: UserWarning: The detected CUDA version (12.3) has a minor version mismatch with the version that was used to compile PyTorch (12.1). Most likely this shouldn't be a problem. warnings.warn(CUDA_MISMATCH_WARN.format(cuda_str_version, torch.version.cuda)) /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/utils/cpp_extension.py:424: UserWarning: There are no g++ version bounds defined for CUDA version 12.3 warnings.warn(f'There are no {compiler_name} version bounds defined for CUDA version {cuda_str_version}') building 'upfirdn2d' extension Emitting ninja build file /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) ninja: no work to do. g++ -pthread -shared -B /home/ubuntu/miniconda3/envs/lhm-havatar/compiler_compat -L/home/ubuntu/miniconda3/envs/lhm-havatar/lib -Wl,-rpath=/home/ubuntu/miniconda3/envs/lhm-havatar/lib -Wl,--no-as-needed -Wl,--sysroot=/ /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/upfirdn2d.o /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/upfirdn2d_kernel.o -L/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda-12.3/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.8/upfirdn2d.cpython-38-x86_64-linux-gnu.so building 'fused' extension Emitting ninja build file /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) ninja: no work to do. g++ -pthread -shared -B /home/ubuntu/miniconda3/envs/lhm-havatar/compiler_compat -L/home/ubuntu/miniconda3/envs/lhm-havatar/lib -Wl,-rpath=/home/ubuntu/miniconda3/envs/lhm-havatar/lib -Wl,--no-as-needed -Wl,--sysroot=/ /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/fused_bias_act.o /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/fused_bias_act_kernel.o -L/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda-12.3/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.8/fused.cpython-38-x86_64-linux-gnu.so creating build/bdist.linux-x86_64/egg copying build/lib.linux-x86_64-3.8/fused.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg copying build/lib.linux-x86_64-3.8/upfirdn2d.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg creating stub loader for upfirdn2d.cpython-38-x86_64-linux-gnu.so creating stub loader for fused.cpython-38-x86_64-linux-gnu.so byte-compiling build/bdist.linux-x86_64/egg/upfirdn2d.py to upfirdn2d.cpython-38.pyc byte-compiling build/bdist.linux-x86_64/egg/fused.py to fused.cpython-38.pyc creating build/bdist.linux-x86_64/egg/EGG-INFO copying custom_cuda_extensions.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO copying custom_cuda_extensions.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO copying custom_cuda_extensions.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO copying custom_cuda_extensions.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt zip_safe flag not set; analyzing archive contents... pycache.fused.cpython-38: module references file pycache.upfirdn2d.cpython-38: module references file creating 'dist/custom_cuda_extensions-0.0.0-py3.8-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it removing 'build/bdist.linux-x86_64/egg' (and everything under it) Processing custom_cuda_extensions-0.0.0-py3.8-linux-x86_64.egg removing '/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/custom_cuda_extensions-0.0.0-py3.8-linux-x86_64.egg' (and everything under it) creating /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/custom_cuda_extensions-0.0.0-py3.8-linux-x86_64.egg Extracting custom_cuda_extensions-0.0.0-py3.8-linux-x86_64.egg to /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages custom-cuda-extensions 0.0.0 is already the active version in easy-install.pth

Installed /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/custom_cuda_extensions-0.0.0-py3.8-linux-x86_64.egg Processing dependencies for custom-cuda-extensions==0.0.0 Finished processing dependencies for custom-cuda-extensions==0.0.0

But when I tried to train my own data set, I still got the above error.

XChenZ commented 6 months ago

Oh, I think that you may fail to correctly compile the ops. This is because the cuda version (12.3) is different from your pytorch-cuda version(12.1). In my practice, these two versions should be consistent when I try to compile custom cuda extensions.

LeeHanmin commented 6 months ago

I've now switched CUDA version to 12.1 and rerun setup.py, and here's the feedback: python setup.py install running install running bdist_egg running egg_info writing upfirdn2d.egg-info/PKG-INFO writing dependency_links to upfirdn2d.egg-info/dependency_links.txt writing top-level names to upfirdn2d.egg-info/top_level.txt reading manifest file 'upfirdn2d.egg-info/SOURCES.txt' writing manifest file 'upfirdn2d.egg-info/SOURCES.txt' installing library code to build/bdist.linux-x86_64/egg running install_lib running build_ext /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/utils/cpp_extension.py:424: UserWarning: There are no g++ version bounds defined for CUDA version 12.1 warnings.warn(f'There are no {compiler_name} version bounds defined for CUDA version {cuda_str_version}') building 'upfirdn2d' extension creating /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8 Emitting ninja build file /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) [1/2] /usr/local/cuda-12.1/bin/nvcc -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/TH -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-12.1/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/include/python3.8 -c -c /home/lhm/havatar/model/op/upfirdn2d_kernel.cu -o /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/upfirdn2d_kernel.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_BFLOAT16_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=upfirdn2d -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 -std=c++17 [2/2] c++ -MMD -MF /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/upfirdn2d.o.d -pthread -B /home/ubuntu/miniconda3/envs/lhm-havatar/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/TH -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-12.1/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/include/python3.8 -c -c /home/lhm/havatar/model/op/upfirdn2d.cpp -o /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/upfirdn2d.o -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=upfirdn2d -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++17 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/Generator.h:11, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/CPUGeneratorImpl.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/Context.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7, from /home/lhm/havatar/model/op/upfirdn2d.cpp:1: /home/lhm/havatar/model/op/upfirdn2d.cpp: In function ‘at::Tensor upfirdn2d(const at::Tensor&, const at::Tensor&, int, int, int, int, int, int, int, int)’: /home/lhm/havatar/model/op/upfirdn2d.cpp:10:22: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations] 10 | TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor") | ^ /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:207:64: note: in definition of macro ‘C10_UNLIKELY’ 207 | #define C10_UNLIKELY(expr) (__builtin_expect(static_cast(expr), 0)) | ^~~~ /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:503:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’ 503 | if (C10_UNLIKELY_OR_CONST(!(cond))) { \ | ^~~~~ /home/lhm/havatar/model/op/upfirdn2d.cpp:10:3: note: in expansion of macro ‘TORCH_CHECK’ 10 | TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor") | ^~~ /home/lhm/havatar/model/op/upfirdn2d.cpp:14:3: note: in expansion of macro ‘CHECK_CUDA’ 14 | CHECK_CUDA(x); \ | ^~~~~~ /home/lhm/havatar/model/op/upfirdn2d.cpp:20:3: note: in expansion of macro ‘CHECK_INPUT’ 20 | CHECK_INPUT(input); | ^~~ In file included from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/ivalue.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/List_inl.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/List.h:490, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/IListRef_inl.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/IListRef.h:632, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9, from /home/lhm/havatar/model/op/upfirdn2d.cpp:1: /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:225:30: note: declared here 225 | DeprecatedTypeProperties & type() const { | ^~~~ In file included from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/Generator.h:11, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/CPUGeneratorImpl.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/Context.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7, from /home/lhm/havatar/model/op/upfirdn2d.cpp:1: /home/lhm/havatar/model/op/upfirdn2d.cpp:10:22: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations] 10 | TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor") | ^ /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:207:64: note: in definition of macro ‘C10_UNLIKELY’ 207 | #define C10_UNLIKELY(expr) (builtin_expect(static_cast(expr), 0)) | ^~~~ /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:503:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’ 503 | if (C10_UNLIKELY_OR_CONST(!(cond))) { \ | ^~~~~ /home/lhm/havatar/model/op/upfirdn2d.cpp:10:3: note: in expansion of macro ‘TORCH_CHECK’ 10 | TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor") | ^~~ /home/lhm/havatar/model/op/upfirdn2d.cpp:14:3: note: in expansion of macro ‘CHECK_CUDA’ 14 | CHECK_CUDA(x); \ | ^~~~~~ /home/lhm/havatar/model/op/upfirdn2d.cpp:21:3: note: in expansion of macro ‘CHECK_INPUT’ 21 | CHECK_INPUT(kernel); | ^~~ In file included from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/ivalue.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/List_inl.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/List.h:490, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/IListRef_inl.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/IListRef.h:632, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9, from /home/lhm/havatar/model/op/upfirdn2d.cpp:1: /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:225:30: note: declared here 225 | DeprecatedTypeProperties & type() const { | ^~~~ g++ -pthread -shared -B /home/ubuntu/miniconda3/envs/lhm-havatar/compiler_compat -L/home/ubuntu/miniconda3/envs/lhm-havatar/lib -Wl,-rpath=/home/ubuntu/miniconda3/envs/lhm-havatar/lib -Wl,--no-as-needed -Wl,--sysroot=/ /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/upfirdn2d.o /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/upfirdn2d_kernel.o -L/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda-12.1/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.8/upfirdn2d.cpython-38-x86_64-linux-gnu.so creating build/bdist.linux-x86_64/egg copying build/lib.linux-x86_64-3.8/fused.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg copying build/lib.linux-x86_64-3.8/upfirdn2d.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg creating stub loader for upfirdn2d.cpython-38-x86_64-linux-gnu.so byte-compiling build/bdist.linux-x86_64/egg/upfirdn2d.py to upfirdn2d.cpython-38.pyc creating build/bdist.linux-x86_64/egg/EGG-INFO copying upfirdn2d.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO copying upfirdn2d.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO copying upfirdn2d.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO copying upfirdn2d.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt zip_safe flag not set; analyzing archive contents... pycache.upfirdn2d.cpython-38: module references file__ creating 'dist/upfirdn2d-0.0.0-py3.8-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it removing 'build/bdist.linux-x86_64/egg' (and everything under it) Processing upfirdn2d-0.0.0-py3.8-linux-x86_64.egg removing '/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/upfirdn2d-0.0.0-py3.8-linux-x86_64.egg' (and everything under it) creating /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/upfirdn2d-0.0.0-py3.8-linux-x86_64.egg Extracting upfirdn2d-0.0.0-py3.8-linux-x86_64.egg to /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages upfirdn2d 0.0.0 is already the active version in easy-install.pth

Installed /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/upfirdn2d-0.0.0-py3.8-linux-x86_64.egg Processing dependencies for upfirdn2d==0.0.0 Finished processing dependencies for upfirdn2d==0.0.0 running install running bdist_egg running egg_info writing fused.egg-info/PKG-INFO writing dependency_links to fused.egg-info/dependency_links.txt writing top-level names to fused.egg-info/top_level.txt reading manifest file 'fused.egg-info/SOURCES.txt' writing manifest file 'fused.egg-info/SOURCES.txt' installing library code to build/bdist.linux-x86_64/egg running install_lib running build_ext /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/utils/cpp_extension.py:424: UserWarning: There are no g++ version bounds defined for CUDA version 12.1 warnings.warn(f'There are no {compiler_name} version bounds defined for CUDA version {cuda_str_version}') building 'fused' extension Emitting ninja build file /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) [1/2] /usr/local/cuda-12.1/bin/nvcc -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/TH -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-12.1/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/include/python3.8 -c -c /home/lhm/havatar/model/op/fused_bias_act_kernel.cu -o /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/fused_bias_act_kernel.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_BFLOAT16_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=fused -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_89,code=compute_89 -gencode=arch=compute_89,code=sm_89 -std=c++17 [2/2] c++ -MMD -MF /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/fused_bias_act.o.d -pthread -B /home/ubuntu/miniconda3/envs/lhm-havatar/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/torch/csrc/api/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/TH -I/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/THC -I/usr/local/cuda-12.1/include -I/home/ubuntu/miniconda3/envs/lhm-havatar/include/python3.8 -c -c /home/lhm/havatar/model/op/fused_bias_act.cpp -o /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/fused_bias_act.o -DTORCH_API_INCLUDE_EXTENSION_H '-DPYBIND11_COMPILER_TYPE="_gcc"' '-DPYBIND11_STDLIB="_libstdcpp"' '-DPYBIND11_BUILD_ABI="_cxxabi1011"' -DTORCH_EXTENSION_NAME=fused -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++17 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/Generator.h:11, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/CPUGeneratorImpl.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/Context.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7, from /home/lhm/havatar/model/op/fused_bias_act.cpp:2: /home/lhm/havatar/model/op/fused_bias_act.cpp: In function ‘at::Tensor fused_bias_act(const at::Tensor&, const at::Tensor&, const at::Tensor&, int, int, float, float)’: /home/lhm/havatar/model/op/fused_bias_act.cpp:11:22: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations] 11 | TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor") | ^ /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:207:64: note: in definition of macro ‘C10_UNLIKELY’ 207 | #define C10_UNLIKELY(expr) (__builtin_expect(static_cast(expr), 0)) | ^~~~ /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:503:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’ 503 | if (C10_UNLIKELY_OR_CONST(!(cond))) { \ | ^~~~~ /home/lhm/havatar/model/op/fused_bias_act.cpp:11:3: note: in expansion of macro ‘TORCH_CHECK’ 11 | TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor") | ^~~ /home/lhm/havatar/model/op/fused_bias_act.cpp:15:3: note: in expansion of macro ‘CHECK_CUDA’ 15 | CHECK_CUDA(x); \ | ^~~~~~ /home/lhm/havatar/model/op/fused_bias_act.cpp:22:3: note: in expansion of macro ‘CHECK_INPUT’ 22 | CHECK_INPUT(input); | ^~~ In file included from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/ivalue.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/List_inl.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/List.h:490, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/IListRef_inl.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/IListRef.h:632, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9, from /home/lhm/havatar/model/op/fused_bias_act.cpp:2: /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:225:30: note: declared here 225 | DeprecatedTypeProperties & type() const { | ^~~~ In file included from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/Generator.h:11, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/CPUGeneratorImpl.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/Context.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/ATen.h:7, from /home/lhm/havatar/model/op/fused_bias_act.cpp:2: /home/lhm/havatar/model/op/fused_bias_act.cpp:11:22: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations] 11 | TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor") | ^ /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/macros/Macros.h:207:64: note: in definition of macro ‘C10_UNLIKELY’ 207 | #define C10_UNLIKELY(expr) (builtin_expect(static_cast(expr), 0)) | ^~~~ /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/c10/util/Exception.h:503:7: note: in expansion of macro ‘C10_UNLIKELY_OR_CONST’ 503 | if (C10_UNLIKELY_OR_CONST(!(cond))) { \ | ^~~~~ /home/lhm/havatar/model/op/fused_bias_act.cpp:11:3: note: in expansion of macro ‘TORCH_CHECK’ 11 | TORCH_CHECK(x.type().is_cuda(), #x " must be a CUDA tensor") | ^~~ /home/lhm/havatar/model/op/fused_bias_act.cpp:15:3: note: in expansion of macro ‘CHECK_CUDA’ 15 | CHECK_CUDA(x); \ | ^~~~~~ /home/lhm/havatar/model/op/fused_bias_act.cpp:23:3: note: in expansion of macro ‘CHECK_INPUT’ 23 | CHECK_INPUT(bias); | ^~~ In file included from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/ivalue.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/List_inl.h:4, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/List.h:490, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/IListRef_inl.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/IListRef.h:632, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/DeviceGuard.h:3, from /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/ATen.h:9, from /home/lhm/havatar/model/op/fused_bias_act.cpp:2: /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/include/ATen/core/TensorBody.h:225:30: note: declared here 225 | DeprecatedTypeProperties & type() const { | ^~~~ g++ -pthread -shared -B /home/ubuntu/miniconda3/envs/lhm-havatar/compiler_compat -L/home/ubuntu/miniconda3/envs/lhm-havatar/lib -Wl,-rpath=/home/ubuntu/miniconda3/envs/lhm-havatar/lib -Wl,--no-as-needed -Wl,--sysroot=/ /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/fused_bias_act.o /home/lhm/havatar/model/op/build/temp.linux-x86_64-3.8/fused_bias_act_kernel.o -L/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/lib -L/usr/local/cuda-12.1/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.8/fused.cpython-38-x86_64-linux-gnu.so creating build/bdist.linux-x86_64/egg copying build/lib.linux-x86_64-3.8/fused.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg copying build/lib.linux-x86_64-3.8/upfirdn2d.cpython-38-x86_64-linux-gnu.so -> build/bdist.linux-x86_64/egg creating stub loader for fused.cpython-38-x86_64-linux-gnu.so byte-compiling build/bdist.linux-x86_64/egg/fused.py to fused.cpython-38.pyc creating build/bdist.linux-x86_64/egg/EGG-INFO copying fused.egg-info/PKG-INFO -> build/bdist.linux-x86_64/egg/EGG-INFO copying fused.egg-info/SOURCES.txt -> build/bdist.linux-x86_64/egg/EGG-INFO copying fused.egg-info/dependency_links.txt -> build/bdist.linux-x86_64/egg/EGG-INFO copying fused.egg-info/top_level.txt -> build/bdist.linux-x86_64/egg/EGG-INFO writing build/bdist.linux-x86_64/egg/EGG-INFO/native_libs.txt zip_safe flag not set; analyzing archive contents... pycache.fused.cpython-38: module references file__ creating 'dist/fused-0.0.0-py3.8-linux-x86_64.egg' and adding 'build/bdist.linux-x86_64/egg' to it removing 'build/bdist.linux-x86_64/egg' (and everything under it) Processing fused-0.0.0-py3.8-linux-x86_64.egg removing '/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/fused-0.0.0-py3.8-linux-x86_64.egg' (and everything under it) creating /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/fused-0.0.0-py3.8-linux-x86_64.egg Extracting fused-0.0.0-py3.8-linux-x86_64.egg to /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages fused 0.0.0 is already the active version in easy-install.pth

Installed /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/fused-0.0.0-py3.8-linux-x86_64.egg Processing dependencies for fused==0.0.0 Finished processing dependencies for fused==0.0.0

However, when the training began, the following errors still appeared： Credentials not found on disk. Authenticate with:

from fused import NotebookCredentials credentials = NotebookCredentials()

Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off] /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. warnings.warn( /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=AlexNet_Weights.IMAGENET1K_V1. You can also use weights=AlexNet_Weights.DEFAULT to get the most up-to-date weights. warnings.warn(msg) Loading model from: /home/lhm/.local/lib/python3.8/site-packages/lpips/weights/v0.1/alex.pth Setting up [LPIPS] perceptual loss: trunk [vgg], v[0.1], spatial [off] /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing weights=VGG16_Weights.IMAGENET1K_V1. You can also use weights=VGG16_Weights.DEFAULT to get the most up-to-date weights. warnings.warn(msg) Loading model from: /home/lhm/.local/lib/python3.8/site-packages/lpips/weights/v0.1/vgg.pth /home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3526.) return _VF.meshgrid(tensors, kwargs) # type: ignore[attr-defined] StyleGAN conditon img! StyleGAN conditon img! 0.017313696444034576: 100%|████████████████████████████████████████████████████████████████████████████████████| 3000/3000 [00:19<00:00, 155.96it/s] Saved mesh as debug/vis_motionWeightVol.obj Traceback (most recent call last): File "train_avatar.py", line 324, in main() File "train_avatar.py", line 121, in main rgbcoarse, , acc_coarse, weights, rgbfine, , acc_fine, latent_code_loss = trainer(inp_data) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, *kwargs) File "/home/lhm/havatar/model/nerf_trainer.py", line 104, in forward rgbcoarse, , acc_coarse, weights, rgbfine, , acc_fine = self.nerf_forward(ray_batch=ray_batch, background_prior=background_prior, File "/home/lhm/havatar/model/nerf_trainer.py", line 41, in nerf_forward self.model_coarse.set_conditional_embedding(front_render_cond=inputs['front_render_cond'], left_render_cond=inputs['left_render_cond'], File "/home/lhm/havatar/model/nerf_model.py", line 82, in set_conditional_embedding conditonXYplaneembedding, = self.XY_gen(inp_latents, front_render_cond) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(args, kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(*args, kwargs) File "/home/lhm/havatar/model/styleUnet.py", line 798, in forward styles = [self.style(s) for s in styles] File "/home/lhm/havatar/model/styleUnet.py", line 798, in styles = [self.style(s) for s in styles] File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/container.py", line 215, in forward input = module(input) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, kwargs) File "/home/lhm/havatar/model/styleUnet.py", line 150, in forward out = fused_leaky_relu(out, self.bias self.lr_mul) File "/home/lhm/havatar/model/op/fused_act.py", line 122, in fused_leaky_relu return FusedLeakyReLUFunction.apply(input.contiguous(), bias, negative_slope, scale) File "/home/ubuntu/miniconda3/envs/lhm-havatar/lib/python3.8/site-packages/torch/autograd/function.py", line 539, in apply return super().apply(args, kwargs) # type: ignore[misc] File "/home/lhm/havatar/model/op/fused_act.py", line 69, in forward out = fused.fused_bias_act(input, bias, empty, 3, 0, negative_slope, scale) AttributeError: module 'fused' has no attribute 'fused_bias_act'

I have no idea about it.

XChenZ commented 6 months ago

The most confusing part of the bug log is: Credentials not found on disk. Authenticate with: from fused import NotebookCredentials credentials = NotebookCredentials()

I have not seen such log before, and I cannot search the keyword "NotebookCredentials" in my codes. I search in the github and only find one result(https://github.com/fusedio/notebooks/blob/447991c28f87f26275d8347e785112bb7f098099/public/noaa.ipynb#L62). Are you sure that there is no another installed library called 'fused"?

LeeHanmin commented 6 months ago

Oh, when I looked at issue #4,, I thought I needed to install fused==0.1.0, which is what caused the problem above. Thank you for your help and look forward to more of your work!