Time-Travel-Rephotography.github.io
Time-Travel-Rephotography.github.io copied to clipboard
Cannot run example cuda load errore
Hello, I installed all necessary lib following instruction but cannot proceed having this error
++ path='dataset/Abraham Lincoln_01.png'
++ blur_radius=0.75
+++ dirname 'dataset/Abraham Lincoln_01.png'
++ list=dataset
+++ basename dataset
++ list=dataset
++ '[' b == b ']'
++ FLAGS=(--spectral_sensitivity b --encoder_ckpt checkpoint/encoder/checkpoint_b.pt)
++ name='dataset/Abraham Lincoln_01'
++ name='Abraham Lincoln_01'
++ echo 'Abraham Lincoln_01'
Abraham Lincoln_01
++ python projector.py 'dataset/Abraham Lincoln_01.png' --gaussian 0.75 --log_dir log/ --results_dir results/ --spectral_sensitivity b --encoder_ckpt checkpoint/encoder/checkpoint_b.pt
2023-09-06 22:04:48.282080: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2023-09-06 22:04:48.885676: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used.
2023-09-06 22:04:48.888682: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2023-09-06 22:04:50.881629: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
/home/vboxuser/miniconda3/envs/rephotography/lib/python3.8/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: '/home/vboxuser/miniconda3/envs/rephotography/lib/python3.8/site-packages/torchvision/image.so: undefined symbol: _ZN5torch3jit17parseSchemaOrNameERKSs'If you don't plan on using image functionality from `torchvision.io`, you can ignore this warning. Otherwise, there might be something wrong with your environment. Did you have `libjpeg` or `libpng` installed before building `torchvision` from source?
warn(
No CUDA runtime is found, using CUDA_HOME='/home/miniconda3/envs/rephotography'
Traceback (most recent call last):
File "projector.py", line 25, in <module>
from model import Generator
File "/home/vboxuser/Documents/Time-Travel-Rephotography.github.io/model.py", line 12, in <module>
from op import FusedLeakyReLU, fused_leaky_relu, upfirdn2d
File "/home/vboxuser/Documents/Time-Travel-Rephotography.github.io/op/__init__.py", line 1, in <module>
from .fused_act import FusedLeakyReLU, fused_leaky_relu
File "/home/vboxuser/Documents/Time-Travel-Rephotography.github.io/op/fused_act.py", line 10, in <module>
fused = load(
File "/home/vboxuser/miniconda3/envs/rephotography/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1284, in load
return _jit_compile(
File "/home/vboxuser/miniconda3/envs/rephotography/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1509, in _jit_compile
_write_ninja_file_and_build_library(
File "/home/vboxuser/miniconda3/envs/rephotography/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1611, in _write_ninja_file_and_build_library
_write_ninja_file_to_build_library(
File "/home/vboxuser/miniconda3/envs/rephotography/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 2007, in _write_ninja_file_to_build_library
cuda_flags = common_cflags + COMMON_NVCC_FLAGS + _get_cuda_arch_flags()
File "/home/vboxuser/miniconda3/envs/rephotography/lib/python3.8/site-packages/torch/utils/cpp_extension.py", line 1773, in _get_cuda_arch_flags
arch_list[-1] += '+PTX'
IndexError: list index out of range
Where conda install CUDA? Wich is the correct CUDA_HOME?