Errors when running v3 for styleavatar preprosessing
Closed this issue · 10 comments
Inferencer commented
(styleavatar) C:\Users\Jack\FaceVerse\faceversev3_jittor>python tracking_offline_cuda.py --input C:\\Users\\Jack\\StyleAvatar\\styleavatar\\vids\\render.mp4 --res_folder C:\\Users\\Jack\\FaceVerse\\faceversev3_jittor\\output --save_for_styleavatar --crop_size 1536
[i 0830 00:07:09.335000 00 compiler.py:956] Jittor(1.3.8.5) src: c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor
[i 0830 00:07:09.358000 00 compiler.py:957] cl at C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe(19.29.30133)
[i 0830 00:07:09.358000 00 compiler.py:958] cache_path: C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default
[i 0830 00:07:09.363000 00 install_cuda.py:93] cuda_driver_version: [12, 2, 0]
[i 0830 00:07:09.384000 00 __init__.py:411] Found C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe(11.2.67) at C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe.
[i 0830 00:07:09.426000 00 compiler.py:1011] cuda key:cu11.2.67
[i 0830 00:07:09.428000 00 __init__.py:227] Total mem: 15.94GB, using 5 procs for compiling.
[i 0830 00:07:10.271000 00 jit_compiler.cc:28] Load cc_path: C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe
[i 0830 00:07:10.278000 00 init.cc:62] Found cuda archs: [52,]
[w 0830 00:07:10.364000 00 compile_extern.py:203] CUDA related path found in LD_LIBRARY_PATH or PATH(['', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\lib', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default\\cu11.2.67', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\ucrt\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\um\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\lib', '', 'c', '\\users\\jack\\anaconda3\\envs\\styleavatar\\libs', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\_\\_\\_\\_\\_\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\lib\\site-packages\\cv2\\../../x64/vc14/bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\mingw-w64\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\usr\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Scripts', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\bin', 'C', '\\Users\\Jack\\anaconda3\\condabin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\libnvvp', 'C', '\\Windows\\system32', 'C', '\\Windows', 'C', '\\Windows\\System32\\Wbem', 'C', '\\Windows\\System32\\WindowsPowerShell\\v1.0', 'C', '\\Windows\\System32\\OpenSSH', 'C', '\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn', 'C', '\\Program Files\\Git\\cmd', 'C', '\\Program Files\\dotnet', 'C', '\\Program Files (x86)\\Windows Kits\\10\\Windows Performance Toolkit', 'C', '\\Program Files\\NVIDIA Corporation\\Nsight Compute 2021.1.0', 'C', '\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common', 'C', '\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310\\Scripts', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310', 'C', '\\Users\\Jack\\AppData\\Local\\Microsoft\\WindowsApps']), This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path.
Or you can let jittor install cuda for you: `python3.x -m jittor_utils.install_cuda`
[i 0830 00:07:11.178000 00 cuda_flags.cc:49] CUDA enabled.
[e 0830 00:07:13.399000 00 log.cc:565] cl : Command line warning D9025 : overriding '/EHa' with '/EHs'
__opkey0_index__T_int32__DIM_2__XDIM_2__opkey1_binary__Tx_int32__Ty_int32__Tz_bool__OP_equ___hash_c68448bc674c5f27_op.cc
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(137): error: more than one conversion function from "__half" to a built-in type applies:
function "__half::operator float() const"
function "__half::operator short() const"
function "__half::operator unsigned short() const"
function "__half::operator int() const"
function "__half::operator unsigned int() const"
function "__half::operator long long() const"
function "__half::operator unsigned long long() const"
function "__half::operator __nv_bool() const"
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(137): error: more than one conversion function from "__half" to a built-in type applies:
function "__half::operator float() const"
function "__half::operator short() const"
function "__half::operator unsigned short() const"
function "__half::operator int() const"
function "__half::operator unsigned int() const"
function "__half::operator long long() const"
function "__half::operator unsigned long long() const"
function "__half::operator __nv_bool() const"
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(138): error: no instance of overloaded function "atomicCAS" matches the argument list
argument types are: (unsigned short *, unsigned short, unsigned short)
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(152): error: more than one conversion function from "__half" to a built-in type applies:
function "__half::operator float() const"
function "__half::operator short() const"
function "__half::operator unsigned short() const"
function "__half::operator int() const"
function "__half::operator unsigned int() const"
function "__half::operator long long() const"
function "__half::operator unsigned long long() const"
function "__half::operator __nv_bool() const"
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(152): error: more than one conversion function from "__half" to a built-in type applies:
function "__half::operator float() const"
function "__half::operator short() const"
function "__half::operator unsigned short() const"
function "__half::operator int() const"
function "__half::operator unsigned int() const"
function "__half::operator long long() const"
function "__half::operator unsigned long long() const"
function "__half::operator __nv_bool() const"
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(153): error: no instance of overloaded function "atomicCAS" matches the argument list
argument types are: (unsigned short *, unsigned short, unsigned short)
6 errors detected in the compilation of "C:/Users/Jack/.cache/jittor/jt1.3.8/cl/py3.8.16/Windows-10-10.x93/IntelRCoreTMi7x72/default/cu11.2.67/jit/__opkey0_index__T_int32__DIM_2__XDIM_2__opkey1_binary__Tx_int32__Ty_int32__Tz_bool__OP_equ___hash_c68448bc674c5f27_op.cc".
__opkey0_index__T_int32__DIM_2__XDIM_2__opkey1_binary__Tx_int32__Ty_int32__Tz_bool__OP_equ___hash_c68448bc674c5f27_op.cc
Traceback (most recent call last):
File "tracking_offline_cuda.py", line 222, in <module>
tracking = Tracking(args)
File "tracking_offline_cuda.py", line 27, in __init__
self.fvm, self.fvd = get_faceverse(batch_size=self.args.batch_size, focal=int(1315 / 512 * self.args.tar_size), img_size=self.args.tar_size)
File "C:\Users\Jack\FaceVerse\faceversev3_jittor\faceverse_cuda\__init__.py", line 9, in get_faceverse
faceverse_model = FaceVerseModel(faceverse_dict, **kargs)
File "C:\Users\Jack\FaceVerse\faceversev3_jittor\faceverse_cuda\FaceVerseModel.py", line 56, in __init__
self.mask_num = int(jt.sum(self.face_mask).numpy()[0])
RuntimeError: Wrong inputs arguments, Please refer to examples(help(jt.numpy)).
Types of your inputs are:
self = Var,
args = (),
The function declarations are:
ArrayArgs fetch_sync()
Failed reason:[f 0830 00:07:13.400000 00 parallel_compiler.cc:331] Error happend during compilation:
[Error] source file location:C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67\jit\__opkey0_index__T_int32__DIM_2__XDIM_2__opkey1_binary__Tx_int32__Ty_int32__Tz_bool__OP_equ___hash_c68448bc674c5f27_op.cc
Compile fused operator(0/8)failed:[Op(11:0:2:2:i0:o2:s0,index->...),Op(14:0:1:1:i2:o1:s0,binary.equal->15),Op(16:0:1:1:i1:o1:s0,unary.cast->17),]
Reason: [f 0830 00:07:13.400000 00 log.cc:608] Check failed ret(1) == 0(0) Run cmd failed: "C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe" "C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67\jit\__opkey0_index__T_int32__DIM_2__XDIM_2__opkey1_binary__Tx_int32__Ty_int32__Tz_bool__OP_equ___hash_c68448bc674c5f27_op.cc" -shared -L"c:\users\jack\anaconda3\envs\styleavatar\libs" -lpython38 -Xcompiler -EHa -Xcompiler -MD -Xcompiler -utf-8 -I"C:\Users\Jack\.cache\jittor\msvc\VC\include" -I"C:\Users\Jack\.cache\jittor\msvc\win10_kits\include\ucrt" -I"C:\Users\Jack\.cache\jittor\msvc\win10_kits\include\shared" -I"C:\Users\Jack\.cache\jittor\msvc\win10_kits\include\um" -DNOMINMAX -L"C:\Users\Jack\.cache\jittor\msvc\VC\lib" -L"C:\Users\Jack\.cache\jittor\msvc\win10_kits\lib\um\x64" -L"C:\Users\Jack\.cache\jittor\msvc\win10_kits\lib\ucrt\x64" -I"c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor\src" -I"c:\users\jack\anaconda3\envs\styleavatar\include" -DHAS_CUDA -DIS_CUDA -I"C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\include" -I"c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor\extern\cuda\inc" -lcudart -L"C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\lib\x64" -L"C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin" -I"C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67" -L"C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67" -L"C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default" -l"jit_utils_core.cp38-win_amd64" -l"jittor_core.cp38-win_amd64" -x cu --cudart=shared -ccbin="C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe" --use_fast_math -w -I"c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor\extern/cuda/inc" -arch=compute_52 -code=sm_52 -o "C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67\jit\__opkey0_index__T_int32__DIM_2__XDIM_2__opkey1_binary__Tx_int32__Ty_int32__Tz_bool__OP_equ___hash_c68448bc674c5f27_op.dll" -Xlinker -EXPORT:"?jit_run@FusedOp@jittor@@QEAAXXZ"
(styleavatar) C:\Users\Jack\FaceVerse\faceversev3_jittor>
904763189cy commented
@Inferencer hi, Have you already resolved it？
LizhenWangT commented
Solved. FaceVerse.py has been updated now. By the way, I don't see this error in Jittor == 1.3.5.19. The updated version of Jittor might be the reason of this bug.
Inferencer commented
Solved. FaceVerse.py has been updated now. By the way, I don't see this error in Jittor == 1.3.5.19. The updated version of Jittor might be the reason of this bug.
Thanks I updated the file. Got another error though.
(styleavatar) C:\Users\Jack\FaceVerse\faceversev3_jittor>python tracking_offline_cuda.py --input C:\\Users\\Jack\\StyleAvatar\\styleavatar\\vids\\render.mp4 --res_folder C:\\Users\\Jack\\FaceVerse\\faceversev3_jittor\\output --save_for_styleavatar --crop_size 1536 --smooth
[i 0904 06:04:18.659000 24 compiler.py:956] Jittor(1.3.8.5) src: c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor
[i 0904 06:04:18.685000 24 compiler.py:957] cl at C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe(19.29.30133)
[i 0904 06:04:18.685000 24 compiler.py:958] cache_path: C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default
[i 0904 06:04:18.689000 24 install_cuda.py:93] cuda_driver_version: [12, 2, 0]
[i 0904 06:04:18.710000 24 __init__.py:411] Found C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe(11.2.67) at C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe.
[i 0904 06:04:18.755000 24 compiler.py:1011] cuda key:cu11.2.67
[i 0904 06:04:18.756000 24 __init__.py:227] Total mem: 15.94GB, using 5 procs for compiling.
[i 0904 06:04:19.804000 24 jit_compiler.cc:28] Load cc_path: C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe
[i 0904 06:04:19.811000 24 init.cc:62] Found cuda archs: [52,]
[w 0904 06:04:19.917000 24 compile_extern.py:203] CUDA related path found in LD_LIBRARY_PATH or PATH(['', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\lib', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default\\cu11.2.67', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\ucrt\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\um\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\lib', '', 'c', '\\users\\jack\\anaconda3\\envs\\styleavatar\\libs', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\_\\_\\_\\_\\_\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\lib\\site-packages\\cv2\\../../x64/vc14/bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\mingw-w64\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\usr\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Scripts', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\bin', 'C', '\\Users\\Jack\\anaconda3\\condabin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\libnvvp', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\libnvvp', 'C', '\\Windows\\system32', 'C', '\\Windows', 'C', '\\Windows\\System32\\Wbem', 'C', '\\Windows\\System32\\WindowsPowerShell\\v1.0', 'C', '\\Windows\\System32\\OpenSSH', 'C', '\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn', 'C', '\\Program Files\\Git\\cmd', 'C', '\\Program Files\\dotnet', 'C', '\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common', 'C', '\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR', 'C', '\\Program Files\\NVIDIA Corporation\\Nsight Compute 2022.2.0', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310\\Scripts', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310', 'C', '\\Users\\Jack\\AppData\\Local\\Microsoft\\WindowsApps']), This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path.
Or you can let jittor install cuda for you: `python3.x -m jittor_utils.install_cuda`
[w 0904 06:04:19.917000 24 compile_extern.py:203] CUDA related path found in LD_LIBRARY_PATH or PATH(['', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\lib', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default\\cu11.2.67', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\ucrt\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\um\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\lib', '', 'c', '\\users\\jack\\anaconda3\\envs\\styleavatar\\libs', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\_\\_\\_\\_\\_\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\lib\\site-packages\\cv2\\../../x64/vc14/bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\mingw-w64\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\usr\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Scripts', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\bin', 'C', '\\Users\\Jack\\anaconda3\\condabin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\libnvvp', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\libnvvp', 'C', '\\Windows\\system32', 'C', '\\Windows', 'C', '\\Windows\\System32\\Wbem', 'C', '\\Windows\\System32\\WindowsPowerShell\\v1.0', 'C', '\\Windows\\System32\\OpenSSH', 'C', '\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn', 'C', '\\Program Files\\Git\\cmd', 'C', '\\Program Files\\dotnet', 'C', '\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common', 'C', '\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR', 'C', '\\Program Files\\NVIDIA Corporation\\Nsight Compute 2022.2.0', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310\\Scripts', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310', 'C', '\\Users\\Jack\\AppData\\Local\\Microsoft\\WindowsApps']), This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path.
Or you can let jittor install cuda for you: `python3.x -m jittor_utils.install_cuda`
[i 0904 06:04:20.766000 24 cuda_flags.cc:49] CUDA enabled.
Traceback (most recent call last):
File "tracking_offline_cuda.py", line 222, in <module>
tracking = Tracking(args)
File "tracking_offline_cuda.py", line 27, in __init__
self.fvm, self.fvd = get_faceverse(batch_size=self.args.batch_size, focal=int(1315 / 512 * self.args.tar_size), img_size=self.args.tar_size)
File "C:\Users\Jack\FaceVerse\faceversev3_jittor\faceverse_cuda\__init__.py", line 9, in get_faceverse
faceverse_model = FaceVerseModel(faceverse_dict, **kargs)
File "C:\Users\Jack\FaceVerse\faceversev3_jittor\faceverse_cuda\FaceVerseModel.py", line 41, in __init__
exBase = model_dict['exBase'].reshape(-1, 3, 171)
KeyError: 'exBase'
(styleavatar) C:\Users\Jack\FaceVerse\faceversev3_jittor>
LizhenWangT commented
Solved. FaceVerse.py has been updated now. By the way, I don't see this error in Jittor == 1.3.5.19. The updated version of Jittor might be the reason of this bug.
Thanks I updated the file. Got another error though.
(styleavatar) C:\Users\Jack\FaceVerse\faceversev3_jittor>python tracking_offline_cuda.py --input C:\\Users\\Jack\\StyleAvatar\\styleavatar\\vids\\render.mp4 --res_folder C:\\Users\\Jack\\FaceVerse\\faceversev3_jittor\\output --save_for_styleavatar --crop_size 1536 --smooth [i 0904 06:04:18.659000 24 compiler.py:956] Jittor(1.3.8.5) src: c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor [i 0904 06:04:18.685000 24 compiler.py:957] cl at C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe(19.29.30133) [i 0904 06:04:18.685000 24 compiler.py:958] cache_path: C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default [i 0904 06:04:18.689000 24 install_cuda.py:93] cuda_driver_version: [12, 2, 0] [i 0904 06:04:18.710000 24 __init__.py:411] Found C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe(11.2.67) at C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe. [i 0904 06:04:18.755000 24 compiler.py:1011] cuda key:cu11.2.67 [i 0904 06:04:18.756000 24 __init__.py:227] Total mem: 15.94GB, using 5 procs for compiling. [i 0904 06:04:19.804000 24 jit_compiler.cc:28] Load cc_path: C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe [i 0904 06:04:19.811000 24 init.cc:62] Found cuda archs: [52,] [w 0904 06:04:19.917000 24 compile_extern.py:203] CUDA related path found in LD_LIBRARY_PATH or PATH(['', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\lib', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default\\cu11.2.67', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\ucrt\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\um\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\lib', '', 'c', '\\users\\jack\\anaconda3\\envs\\styleavatar\\libs', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\_\\_\\_\\_\\_\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\lib\\site-packages\\cv2\\../../x64/vc14/bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\mingw-w64\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\usr\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Scripts', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\bin', 'C', '\\Users\\Jack\\anaconda3\\condabin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\libnvvp', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\libnvvp', 'C', '\\Windows\\system32', 'C', '\\Windows', 'C', '\\Windows\\System32\\Wbem', 'C', '\\Windows\\System32\\WindowsPowerShell\\v1.0', 'C', '\\Windows\\System32\\OpenSSH', 'C', '\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn', 'C', '\\Program Files\\Git\\cmd', 'C', '\\Program Files\\dotnet', 'C', '\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common', 'C', '\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR', 'C', '\\Program Files\\NVIDIA Corporation\\Nsight Compute 2022.2.0', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310\\Scripts', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310', 'C', '\\Users\\Jack\\AppData\\Local\\Microsoft\\WindowsApps']), This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path. Or you can let jittor install cuda for you: `python3.x -m jittor_utils.install_cuda` [w 0904 06:04:19.917000 24 compile_extern.py:203] CUDA related path found in LD_LIBRARY_PATH or PATH(['', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\lib', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default\\cu11.2.67', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\ucrt\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\um\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\lib', '', 'c', '\\users\\jack\\anaconda3\\envs\\styleavatar\\libs', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\_\\_\\_\\_\\_\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\lib\\site-packages\\cv2\\../../x64/vc14/bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\mingw-w64\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\usr\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Scripts', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\bin', 'C', '\\Users\\Jack\\anaconda3\\condabin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\libnvvp', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\libnvvp', 'C', '\\Windows\\system32', 'C', '\\Windows', 'C', '\\Windows\\System32\\Wbem', 'C', '\\Windows\\System32\\WindowsPowerShell\\v1.0', 'C', '\\Windows\\System32\\OpenSSH', 'C', '\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn', 'C', '\\Program Files\\Git\\cmd', 'C', '\\Program Files\\dotnet', 'C', '\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common', 'C', '\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR', 'C', '\\Program Files\\NVIDIA Corporation\\Nsight Compute 2022.2.0', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310\\Scripts', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310', 'C', '\\Users\\Jack\\AppData\\Local\\Microsoft\\WindowsApps']), This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path. Or you can let jittor install cuda for you: `python3.x -m jittor_utils.install_cuda` [i 0904 06:04:20.766000 24 cuda_flags.cc:49] CUDA enabled. Traceback (most recent call last): File "tracking_offline_cuda.py", line 222, in <module> tracking = Tracking(args) File "tracking_offline_cuda.py", line 27, in __init__ self.fvm, self.fvd = get_faceverse(batch_size=self.args.batch_size, focal=int(1315 / 512 * self.args.tar_size), img_size=self.args.tar_size) File "C:\Users\Jack\FaceVerse\faceversev3_jittor\faceverse_cuda\__init__.py", line 9, in get_faceverse faceverse_model = FaceVerseModel(faceverse_dict, **kargs) File "C:\Users\Jack\FaceVerse\faceversev3_jittor\faceverse_cuda\FaceVerseModel.py", line 41, in __init__ exBase = model_dict['exBase'].reshape(-1, 3, 171) KeyError: 'exBase' (styleavatar) C:\Users\Jack\FaceVerse\faceversev3_jittor>
Fixed now.
Inferencer commented
Let me know at any point if the issues are on my end, I'm planning to set up a Google Collab anyways, I just wanted to use StyleAvatar and figured I would need this not only for future StyleAvatar use but also to create the files required to test the pre-trained model.
(styleavatar) C:\Users\Jack\FaceVerse\faceversev3_jittor>python tracking_offline_cuda.py --input C:\Users\Jack\Downloads\lizhen.mp4 --res_folder C:\\Users\\Jack\\FaceVerse\\faceversev3_jittor\\output --save_for_styleavatar --crop_size 1536 --smooth
[i 0904 06:27:24.218000 76 compiler.py:956] Jittor(1.3.8.5) src: c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor
[i 0904 06:27:24.240000 76 compiler.py:957] cl at C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe(19.29.30133)
[i 0904 06:27:24.240000 76 compiler.py:958] cache_path: C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default
[i 0904 06:27:24.244000 76 install_cuda.py:93] cuda_driver_version: [12, 2, 0]
[i 0904 06:27:24.265000 76 __init__.py:411] Found C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe(11.2.67) at C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe.
[i 0904 06:27:24.308000 76 compiler.py:1011] cuda key:cu11.2.67
[i 0904 06:27:24.310000 76 __init__.py:227] Total mem: 15.94GB, using 5 procs for compiling.
[i 0904 06:27:25.355000 76 jit_compiler.cc:28] Load cc_path: C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe
[i 0904 06:27:25.362000 76 init.cc:62] Found cuda archs: [52,]
[w 0904 06:27:25.462000 76 compile_extern.py:203] CUDA related path found in LD_LIBRARY_PATH or PATH(['', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\lib', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default\\cu11.2.67', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\ucrt\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\um\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\lib', '', 'c', '\\users\\jack\\anaconda3\\envs\\styleavatar\\libs', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\_\\_\\_\\_\\_\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\lib\\site-packages\\cv2\\../../x64/vc14/bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\mingw-w64\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\usr\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Scripts', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\bin', 'C', '\\Users\\Jack\\anaconda3\\condabin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\libnvvp', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\libnvvp', 'C', '\\Windows\\system32', 'C', '\\Windows', 'C', '\\Windows\\System32\\Wbem', 'C', '\\Windows\\System32\\WindowsPowerShell\\v1.0', 'C', '\\Windows\\System32\\OpenSSH', 'C', '\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn', 'C', '\\Program Files\\Git\\cmd', 'C', '\\Program Files\\dotnet', 'C', '\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common', 'C', '\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR', 'C', '\\Program Files\\NVIDIA Corporation\\Nsight Compute 2022.2.0', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310\\Scripts', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310', 'C', '\\Users\\Jack\\AppData\\Local\\Microsoft\\WindowsApps']), This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path.
Or you can let jittor install cuda for you: `python3.x -m jittor_utils.install_cuda`
[w 0904 06:27:25.463000 76 compile_extern.py:203] CUDA related path found in LD_LIBRARY_PATH or PATH(['', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\mkl\\dnnl_win_2.2.0_cpu_vcomp\\lib', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jt1.3.8\\cl\\py3.8.16\\Windows-10-10.x93\\IntelRCoreTMi7x72\\default\\cu11.2.67', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\bin', '', 'C', '\\Users\\Jack\\.cache\\jittor\\jtcuda\\cuda11.2_cudnn8_win\\lib\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\ucrt\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\win10_kits\\lib\\um\\x64', '', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\lib', '', 'c', '\\users\\jack\\anaconda3\\envs\\styleavatar\\libs', 'C', '\\Users\\Jack\\.cache\\jittor\\msvc\\VC\\_\\_\\_\\_\\_\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\lib\\site-packages\\cv2\\../../x64/vc14/bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\mingw-w64\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\usr\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Library\\bin', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\Scripts', 'C', '\\Users\\Jack\\anaconda3\\envs\\styleavatar\\bin', 'C', '\\Users\\Jack\\anaconda3\\condabin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.7\\libnvvp', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\bin', 'C', '\\Program Files\\NVIDIA GPU Computing Toolkit\\CUDA\\v11.3\\libnvvp', 'C', '\\Windows\\system32', 'C', '\\Windows', 'C', '\\Windows\\System32\\Wbem', 'C', '\\Windows\\System32\\WindowsPowerShell\\v1.0', 'C', '\\Windows\\System32\\OpenSSH', 'C', '\\Program Files\\Microsoft SQL Server\\150\\Tools\\Binn', 'C', '\\Program Files\\Git\\cmd', 'C', '\\Program Files\\dotnet', 'C', '\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common', 'C', '\\Program Files\\NVIDIA Corporation\\NVIDIA NvDLISR', 'C', '\\Program Files\\NVIDIA Corporation\\Nsight Compute 2022.2.0', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310\\Scripts', 'C', '\\Users\\Jack\\AppData\\Local\\Programs\\Python\\Python310', 'C', '\\Users\\Jack\\AppData\\Local\\Microsoft\\WindowsApps']), This path may cause jittor found the wrong libs, please unset LD_LIBRARY_PATH and remove cuda lib path in Path.
Or you can let jittor install cuda for you: `python3.x -m jittor_utils.install_cuda`
[i 0904 06:27:26.317000 76 cuda_flags.cc:49] CUDA enabled.
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
OpenCV: FFMPEG: tag 0x5634504d/'MP4V' is not supported with codec id 12 and format 'mp4 / MP4 (MPEG-4 Part 14)'
OpenCV: FFMPEG: fallback to use tag 0x7634706d/'mp4v'
First frame: 1493 [1507 2372]
[e 0904 06:27:29.053000 84 log.cc:565] cl : Command line warning D9025 : overriding '/EHa' with '/EHs'
__opkey0_unary__Tx_int32__Ty_float32__OP_cast__JIT_1__JIT_cuda_1__graph_010000___var_info____hash_686e29d98f884693_op.cc
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(137): error: more than one conversion function from "__half" to a built-in type applies:
function "__half::operator float() const"
function "__half::operator short() const"
function "__half::operator unsigned short() const"
function "__half::operator int() const"
function "__half::operator unsigned int() const"
function "__half::operator long long() const"
function "__half::operator unsigned long long() const"
function "__half::operator __nv_bool() const"
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(137): error: more than one conversion function from "__half" to a built-in type applies:
function "__half::operator float() const"
function "__half::operator short() const"
function "__half::operator unsigned short() const"
function "__half::operator int() const"
function "__half::operator unsigned int() const"
function "__half::operator long long() const"
function "__half::operator unsigned long long() const"
function "__half::operator __nv_bool() const"
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(138): error: no instance of overloaded function "atomicCAS" matches the argument list
argument types are: (unsigned short *, unsigned short, unsigned short)
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(152): error: more than one conversion function from "__half" to a built-in type applies:
function "__half::operator float() const"
function "__half::operator short() const"
function "__half::operator unsigned short() const"
function "__half::operator int() const"
function "__half::operator unsigned int() const"
function "__half::operator long long() const"
function "__half::operator unsigned long long() const"
function "__half::operator __nv_bool() const"
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(152): error: more than one conversion function from "__half" to a built-in type applies:
function "__half::operator float() const"
function "__half::operator short() const"
function "__half::operator unsigned short() const"
function "__half::operator int() const"
function "__half::operator unsigned int() const"
function "__half::operator long long() const"
function "__half::operator unsigned long long() const"
function "__half::operator __nv_bool() const"
c:/users/jack/anaconda3/envs/styleavatar/lib/site-packages/jittor/src\misc/cuda_atomic.h(153): error: no instance of overloaded function "atomicCAS" matches the argument list
argument types are: (unsigned short *, unsigned short, unsigned short)
6 errors detected in the compilation of "C:/Users/Jack/.cache/jittor/jt1.3.8/cl/py3.8.16/Windows-10-10.x93/IntelRCoreTMi7x72/default/cu11.2.67/jit/__opkey0_unary__Tx_int32__Ty_float32__OP_cast__JIT_1__JIT_cuda_1__graph_010000___var_info____hash_686e29d98f884693_op.cc".
__opkey0_unary__Tx_int32__Ty_float32__OP_cast__JIT_1__JIT_cuda_1__graph_010000___var_info____hash_686e29d98f884693_op.cc
Exception in thread Thread-6:
Traceback (most recent call last):
File "C:\Users\Jack\anaconda3\envs\styleavatar\lib\threading.py", line 932, in _bootstrap_inner
self.run()
File "tracking_offline_cuda.py", line 90, in run
rigid_optimizer.backward(loss)
File "C:\Users\Jack\anaconda3\envs\styleavatar\lib\site-packages\jittor\optim.py", line 170, in backward
jt.sync(params_has_grad)
RuntimeError: Wrong inputs arguments, Please refer to examples(help(jt.sync)).
Types of your inputs are:
self = module,
args = (list, ),
The function declarations are:
void sync(const vector<VarHolder*>& vh=vector<VarHolder*>(), bool device_sync=false, bool weak_sync=true)
Failed reason:[f 0904 06:27:29.054000 84 parallel_compiler.cc:331] Error happend during compilation:
[Error] source file location:C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67\jit\__opkey0_unary__Tx_int32__Ty_float32__OP_cast__JIT_1__JIT_cuda_1__graph_010000___var_info____hash_686e29d98f884693_op.cc
Compile fused operator(2/4)failed:[Op(103:0:1:1:i1:o1:s0,unary.cast->104),]
Reason: [f 0904 06:27:29.054000 84 log.cc:608] Check failed ret(1) == 0(0) Run cmd failed: "C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe" "C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67\jit\__opkey0_unary__Tx_int32__Ty_float32__OP_cast__JIT_1__JIT_cuda_1__graph_010000___var_info____hash_686e29d98f884693_op.cc" -shared -L"c:\users\jack\anaconda3\envs\styleavatar\libs" -lpython38 -Xcompiler -EHa -Xcompiler -MD -Xcompiler -utf-8 -I"C:\Users\Jack\.cache\jittor\msvc\VC\include" -I"C:\Users\Jack\.cache\jittor\msvc\win10_kits\include\ucrt" -I"C:\Users\Jack\.cache\jittor\msvc\win10_kits\include\shared" -I"C:\Users\Jack\.cache\jittor\msvc\win10_kits\include\um" -DNOMINMAX -L"C:\Users\Jack\.cache\jittor\msvc\VC\lib" -L"C:\Users\Jack\.cache\jittor\msvc\win10_kits\lib\um\x64" -L"C:\Users\Jack\.cache\jittor\msvc\win10_kits\lib\ucrt\x64" -I"c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor\src" -I"c:\users\jack\anaconda3\envs\styleavatar\include" -DHAS_CUDA -DIS_CUDA -I"C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\include" -I"c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor\extern\cuda\inc" -lcudart -L"C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\lib\x64" -L"C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin" -I"C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67" -L"C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67" -L"C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default" -l"jit_utils_core.cp38-win_amd64" -l"jittor_core.cp38-win_amd64" -x cu --cudart=shared -ccbin="C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe" --use_fast_math -w -I"c:\users\jack\anaconda3\envs\styleavatar\lib\site-packages\jittor\extern/cuda/inc" -arch=compute_52 -code=sm_52 -o "C:\Users\Jack\.cache\jittor\jt1.3.8\cl\py3.8.16\Windows-10-10.x93\IntelRCoreTMi7x72\default\cu11.2.67\jit\__opkey0_unary__Tx_int32__Ty_float32__OP_cast__JIT_1__JIT_cuda_1__graph_010000___var_info____hash_686e29d98f884693_op.dll" -Xlinker -EXPORT:"?jit_run@FusedOp@jittor@@QEAAXXZ"
LizhenWangT commented
Maybe you can try to reinstall Jittor by pip install jittor==1.3.5.19. The version compatibility of jittor is not that good.
Inferencer commented
Maybe you can try to reinstall Jittor by
pip install jittor==1.3.5.19. The version compatibility of jittor is not that good.
No luck, I tried creating a new env with Jittor repo and tested that with similar results, seems to be an issues others are facing but unsolved, perhaps you can take a look at this collab and see if we can get something working
https://colab.research.google.com/drive/1A7wsQbewvdv3jsORfv6XNMuN66wdTAdA?usp=sharing
LizhenWangT commented
Maybe you can try to reinstall Jittor by
pip install jittor==1.3.5.19. The version compatibility of jittor is not that good.No luck, I tried creating a new env with Jittor repo and tested that with similar results, seems to be an issues others are facing but unsolved, perhaps you can take a look at this collab and see if we can get something working https://colab.research.google.com/drive/1A7wsQbewvdv3jsORfv6XNMuN66wdTAdA?usp=sharing
Jittor will download a CUDA 11.2 to C:/Users/xxx/.cache/jittor/jtcuda and use this CUDA to compile the opearators on Windows but I saw your were using a nvcc with version 11.8. I don't know if this version will work for jittor. Try this to check if your Jittor works well:
sudo apt install python3.7-dev libomp-dev
python3.7 -m pip install jittor
python3.7 -m jittor.test.test_example
python3.7 -m jittor.test.test_cudnn_op
python3.7 -m jittor.test.test_cuda
Inferencer commented
Looks like collab needs me to remove some stuff as it's missing a GUI and there is a few ima.show commands in the offline script so i'll look at that a bit later
Those are linux commands above so I tried
python -m pip install jittor
python -m jittor.test.test_example
python -m jittor.test.test_cudnn_op
python -m jittor.test.test_cuda
and they were all sucsessfull
regardless I went to a new env and setx the cuda path Jittor installed
(base) C:\Users\Jack>conda activate facev
(facev) C:\Users\Jack>cd C:\Users\Jack\FaceVerse\faceversev3_jittor
(facev) C:\Users\Jack\FaceVerse\faceversev3_jittor>nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2020 NVIDIA Corporation
Built on Mon_Nov_30_19:15:10_Pacific_Standard_Time_2020
Cuda compilation tools, release 11.2, V11.2.67
Build cuda_11.2.r11.2/compiler.29373293_0
(facev) C:\Users\Jack\FaceVerse\faceversev3_jittor>python --version
Python 3.8.17
(facev) C:\Users\Jack\FaceVerse\faceversev3_jittor>python tracking_offline_cuda.py --input C:\\Users\\Jack\\StyleAvatar\\styleavatar\\vids\\render.mp4 --res_folder C:\\Users\\Jack\\FaceVerse\\faceversev3_jittor\\output --save_for_styleavatar --crop_size 1536 --smooth
[i 0904 10:58:04.342000 48 compiler.py:955] Jittor(1.3.5.19) src: c:\users\jack\anaconda3\envs\facev\lib\site-packages\jittor
[i 0904 10:58:04.365000 48 compiler.py:956] cl at C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe(19.29.30133)
[i 0904 10:58:04.366000 48 compiler.py:957] cache_path: C:\Users\Jack\.cache\jittor\jt1.3.5\cl\py3.8.17\Windows-10-10.x93\IntelRCoreTMi7x72\default
[i 0904 10:58:04.369000 48 install_cuda.py:91] cuda_driver_version: [12, 2, 0]
[i 0904 10:58:04.389000 48 __init__.py:411] Found C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe(11.2.67) at C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin\nvcc.exe.
[i 0904 10:58:04.429000 48 compiler.py:1010] cuda key:cu11.2.67
[i 0904 10:58:04.430000 48 __init__.py:227] Total mem: 15.94GB, using 5 procs for compiling.
[i 0904 10:58:05.591000 48 jit_compiler.cc:28] Load cc_path: C:\Users\Jack\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe
[i 0904 10:58:05.592000 48 init.cc:62] Found cuda archs: [52,]
[i 0904 10:58:05.621000 48 compile_extern.py:517] mpicc not found, distribution disabled.
[i 0904 10:58:06.622000 48 cuda_flags.cc:32] CUDA enabled.
[i 0904 10:58:06.626000 48 cuda_flags.cc:32] CUDA enabled.
[i 0904 10:58:06.629000 48 cuda_flags.cc:32] CUDA enabled.
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
OpenCV: FFMPEG: tag 0x5634504d/'MP4V' is not supported with codec id 12 and format 'mp4 / MP4 (MPEG-4 Part 14)'
OpenCV: FFMPEG: fallback to use tag 0x7634706d/'mp4v'
First frame: 1493 [1507 2372]
Exception in thread Thread-4:
Traceback (most recent call last):
File "C:\Users\Jack\anaconda3\envs\facev\lib\threading.py", line 932, in _bootstrap_inner
self.run()
File "tracking_offline_cuda.py", line 46, in run
detected, align, lms_detect, outimg, frame_num = self.offreader.get_data()
File "C:\Users\Jack\FaceVerse\faceversev3_jittor\data_reader.py", line 160, in get_data
outimg = np.asarray(frame_b.resize((self.crop_size, self.crop_size), Image.ANTIALIAS))
AttributeError: module 'PIL.Image' has no attribute 'ANTIALIAS'
this appears to be an issue with Pillow10.0 so am installing Pillow==9.5.0 which removed that error
still too early to confirm everything is fixed
Inferencer commented
confirmed working now, thanks for the help!
@904763189cy
setx PATH "%PATH%;C:\Users\Jack\.cache\jittor\jtcuda\cuda11.2_cudnn8_win\bin"
and
pip install Pillow==9.5.0
seems to fix, was mostly Jittor installing the correct Cuda version (11.2) but not using it and defaulting to my pc's Cuda version