alievk
CUDA out of memory
Describe the bug
- when running run_windows.bat, loading predictor comes up
- cam window appears
- after pressing 'X', a grey avatarify window pops up , then the program crashes with the following error in miniconda:
C:\Users\raymo\miniconda3\envs\avatarify\lib\site-packages\torch\nn\functional.py:3385: UserWarning: Default grid_sample and affine_grid behavior has changed to align_corners=False since 1.3.0. Please specify align_corners=True if the old behavior is desired. See the documentation of grid_sample for details.
warnings.warn("Default grid_sample and affine_grid behavior has changed "
Traceback (most recent call last):
File "afy/cam_fomm.py", line 316, in <module>
out = predictor.predict(frame)
File "C:\Users\raymo\avatarify\afy\predictor_local.py", line 106, in predict
out = self.generator(self.source, kp_source=self.kp_source, kp_driving=kp_norm)
File "C:\Users\raymo\miniconda3\envs\avatarify\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Users\raymo\avatarify\fomm\modules\generator_optim.py", line 100, in forward
out = self.up_blocks[i](out)
File "C:\Users\raymo\miniconda3\envs\avatarify\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Users\raymo\avatarify\fomm\modules\util.py", line 91, in forward
out = self.conv(out)
File "C:\Users\raymo\miniconda3\envs\avatarify\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "C:\Users\raymo\miniconda3\envs\avatarify\lib\site-packages\torch\nn\modules\conv.py", line 423, in forward
return self._conv_forward(input, self.weight)
File "C:\Users\raymo\miniconda3\envs\avatarify\lib\site-packages\torch\nn\modules\conv.py", line 420, in _conv_forward
self.padding, self.dilation, self.groups)
RuntimeError: CUDA out of memory. Tried to allocate 16.25 GiB (GPU 0; 24.00 GiB total capacity; 658.98 MiB already allocated; 17.02 GiB free; 4.53 GiB reserved in total by PyTorch)
Info (please complete the following information):
-
OS Windows 10 version 20H2, OS Build19042.804
-
GPU model: NVIDIA GeForce RTX 3090
-
Any other relevant information: Conda Info:
active environment : avatarify
active env location : C:\Users\raymo\miniconda3\envs\avatarify
shell level : 2
user config file : C:\Users\raymo\.condarc
populated config files :
conda version : 4.9.2
conda-build version : not installed
python version : 3.8.5.final.0
virtual packages : __cuda=11.2=0
__win=0=0
__archspec=1=x86_64
base environment : C:\Users\raymo\miniconda3 (writable)
channel URLs : https://repo.anaconda.com/pkgs/main/win-64
https://repo.anaconda.com/pkgs/main/noarch
https://repo.anaconda.com/pkgs/r/win-64
https://repo.anaconda.com/pkgs/r/noarch
https://repo.anaconda.com/pkgs/msys2/win-64
https://repo.anaconda.com/pkgs/msys2/noarch
package cache : C:\Users\raymo\miniconda3\pkgs
C:\Users\raymo\.conda\pkgs
C:\Users\raymo\AppData\Local\conda\conda\pkgs
envs directories : C:\Users\raymo\miniconda3\envs
C:\Users\raymo\.conda\envs
C:\Users\raymo\AppData\Local\conda\conda\envs
platform : win-64
user-agent : conda/4.9.2 requests/2.24.0 CPython/3.8.5 Windows/10 Windows/10.0.19041
administrator : True
netrc file : None
offline mode : False
Conda list:
# packages in environment at C:\Users\raymo\miniconda3\envs\avatarify:
#
# Name Version Build Channel
appdirs 1.4.4 pyh9f0ad1d_0 conda-forge
blas 1.0 mkl
blosc 1.21.0 h0e60522_0 conda-forge
brotli 1.0.9 h0e60522_4 conda-forge
brotlipy 0.7.0 py37hcc03f2d_1001 conda-forge
bzip2 1.0.8 h8ffe710_4 conda-forge
ca-certificates 2020.10.14 0 anaconda
certifi 2020.6.20 py37_0 anaconda
cffi 1.14.5 py37hd8e9650_0 conda-forge
chardet 4.0.0 py37h03978a9_1 conda-forge
charls 2.2.0 h39d44d4_0 conda-forge
cloudpickle 1.6.0 py_0 conda-forge
cryptography 3.4.4 py37h65266a2_0 conda-forge
cudatoolkit 11.0.221 h74a9793_0
cycler 0.10.0 py_2 conda-forge
cytoolz 0.11.0 py37hcc03f2d_3 conda-forge
dask-core 2021.2.0 pyhd8ed1ab_0 conda-forge
decorator 4.4.2 py_0 conda-forge
face-alignment 1.3.3 pypi_0 pypi
freetype 2.10.4 h546665d_1 conda-forge
giflib 5.2.1 h8d14728_2 conda-forge
git 2.23.0 h6bb4b03_0 anaconda
idna 2.10 pyh9f0ad1d_0 conda-forge
imagecodecs 2021.1.28 py37hb664a41_0 conda-forge
imageio 2.9.0 py_0 conda-forge
intel-openmp 2020.3 h57928b3_311 conda-forge
jpeg 9d h8ffe710_0 conda-forge
jxrlib 1.1 h8ffe710_2 conda-forge
kiwisolver 1.3.1 py37h8c56517_1 conda-forge
lcms2 2.12 h2a16943_0 conda-forge
lerc 2.2.1 h0e60522_0 conda-forge
libaec 1.0.4 h39d44d4_1 conda-forge
libblas 3.9.0 8_mkl conda-forge
libcblas 3.9.0 8_mkl conda-forge
libdeflate 1.7 h8ffe710_5 conda-forge
liblapack 3.9.0 8_mkl conda-forge
libpng 1.6.37 h1d00b33_2 conda-forge
libtiff 4.2.0 hc10be44_0 conda-forge
libuv 1.40.0 he774522_0
libwebp-base 1.2.0 h8ffe710_0 conda-forge
libzopfli 1.0.3 h0e60522_0 conda-forge
llvmlite 0.35.0 pypi_0 pypi
lz4-c 1.9.3 h8ffe710_0 conda-forge
m2w64-gcc-libgfortran 5.3.0 6 conda-forge
m2w64-gcc-libs 5.3.0 7 conda-forge
m2w64-gcc-libs-core 5.3.0 7 conda-forge
m2w64-gmp 6.1.0 2 conda-forge
m2w64-libwinpthread-git 5.0.0.4634.697f757 2 conda-forge
matplotlib-base 3.3.4 py37h3379fd5_0 conda-forge
mkl 2020.4 hb70f87d_311 conda-forge
msgpack 1.0.2 pypi_0 pypi
msgpack-numpy 0.4.7.1 pypi_0 pypi
msys2-conda-epoch 20160418 1 conda-forge
networkx 2.5 py_0 conda-forge
ninja 1.10.2 py37h6d14046_0
numba 0.52.0 pypi_0 pypi
numpy 1.19.0 py37hae9e721_0 conda-forge
olefile 0.46 pyh9f0ad1d_1 conda-forge
opencv-python 4.2.0.34 pypi_0 pypi
openjpeg 2.4.0 h48faf41_0 conda-forge
openssl 1.1.1j h2bbff1b_0
packaging 20.9 pyh44b312d_0 conda-forge
pillow 8.1.0 py37h96663a1_2 conda-forge
pip 21.0.1 py37haa95532_0
pooch 1.3.0 pyhd8ed1ab_0 conda-forge
pycparser 2.20 pyh9f0ad1d_2 conda-forge
pyfakewebcam 0.1.0 pypi_0 pypi
pyopenssl 20.0.1 pyhd8ed1ab_0 conda-forge
pyparsing 2.4.7 pyh9f0ad1d_0 conda-forge
pysocks 1.7.1 py37h03978a9_3 conda-forge
python 3.7.10 h6244533_0
python-blosc 1.7.0 py37h6538335_1001 conda-forge
python-dateutil 2.8.1 py_0 conda-forge
python_abi 3.7 1_cp37m conda-forge
pytorch 1.7.1 py3.7_cuda110_cudnn8_0 pytorch
pywavelets 1.1.1 py37hda49f71_3 conda-forge
pyyaml 5.3.1 pypi_0 pypi
pyzmq 20.0.0 pypi_0 pypi
requests 2.25.1 pyhd3deb0d_0 conda-forge
scikit-image 0.18.1 py37h08fd248_0 conda-forge
scipy 1.6.0 py37h6db1a17_0 conda-forge
setuptools 52.0.0 py37haa95532_0
six 1.15.0 pyh9f0ad1d_0 conda-forge
snappy 1.1.8 ha925a31_3 conda-forge
sqlite 3.33.0 h2a8f88b_0
tifffile 2021.2.26 pyhd8ed1ab_0 conda-forge
tk 8.6.10 h8ffe710_1 conda-forge
toolz 0.11.1 py_0 conda-forge
torchvision 0.2.2 py_3 pytorch
tornado 6.1 py37hcc03f2d_1 conda-forge
tqdm 4.58.0 pypi_0 pypi
typing_extensions 3.7.4.3 pyha847dfd_0
urllib3 1.26.3 pyhd8ed1ab_0 conda-forge
vc 14.2 h21ff451_1
vs2015_runtime 14.27.29016 h5e58377_2
wheel 0.36.2 pyhd3eb1b0_0
win_inet_pton 1.1.0 py37h03978a9_2 conda-forge
wincertstore 0.2 py37_0
xz 5.2.5 h62dcd97_1 conda-forge
yaml 0.2.5 he774522_0 conda-forge
zfp 0.5.5 h0e60522_4 conda-forge
zlib 1.2.11 h62dcd97_4
zstd 1.4.8 h4e2f164_1 conda-forge
:: Environment info
CONDA_DEFAULT_ENV=avatarify
CONDA_ENV_NAME=avatarify
CONDA_EXE=C:\Users\raymo\miniconda3\condabin\..\Scripts\conda.exe
CONDA_PREFIX=C:\Users\raymo\miniconda3\envs\avatarify
CONDA_PREFIX_1=C:\Users\raymo\miniconda3
CONDA_PROMPT_MODIFIER=(avatarify)
CONDA_PYTHON_EXE=C:\Users\raymo\miniconda3\python.exe
CONDA_SHLVL=2
PYTHONPATH=;C:\Users\raymo\avatarify;C:\Users\raymo\avatarify/fomm;C:\Users\raymo\avatarify;C:\Users\raymo\avatarify/fomm;C:\Users\raymo\avatarify;C:\Users\raymo\avatarify/fomm;C:\Users\raymo\avatarify;C:\Users\raymo\avatarify/fomm
I have the same issue on Ubuntu 20.04 64 bits with a CUDA GTX 1030
(base) carlos@desktop:/media/DATA/avatarify$ time bash run.sh
[1617211270.691124] Loading Predictor
Traceback (most recent call last):
File "afy/cam_fomm.py", line 218, in <module>
**predictor_args
File "/media/DATA/avatarify/afy/predictor_local.py", line 48, in __init__
self.generator, self.kp_detector = self.load_checkpoints()
File "/media/DATA/avatarify/afy/predictor_local.py", line 66, in load_checkpoints
checkpoint = torch.load(self.checkpoint_path, map_location=self.device)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/serialization.py", line 593, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/serialization.py", line 772, in _legacy_load
result = unpickler.load()
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/serialization.py", line 728, in persistent_load
deserialized_objects[root_key] = restore_location(obj, location)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/serialization.py", line 809, in restore_location
return default_restore_location(storage, map_location)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/serialization.py", line 175, in default_restore_location
result = fn(storage, location)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/serialization.py", line 155, in _cuda_deserialize
return storage_type(obj.size())
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/cuda/__init__.py", line 484, in _lazy_new
return super(_CudaBase, cls).__new__(cls, *args, **kwargs)
RuntimeError: CUDA out of memory. Tried to allocate 18.00 MiB (GPU 0; 1.95 GiB total capacity; 935.53 MiB already allocated; 31.94 MiB free; 946.00 MiB reserved in total by PyTorch)
real 0m9.609s
user 0m6.202s
sys 0m2.198s
It looks like a memory leak; trying to allocate GPU memory in some loop? I can see from the nvidia tools that the GPU memory is getting eaten up and after that run.sh stops; and GPU memory goes back down to what it was before.
OK I did nothing whatsoever since posting the previous comment and right now just for fun I tried the same command again and it did not crash .
Damned. Restarted the computer to try fresh and now I got the same crash once more.
Yep so the problem persists even though I am able to get a little bit further. After having configured my face in the red square and pressing "X" the memory leak happens again. By the way I have no other processes using GPU atm
[1617215736.869267] 101
/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/functional.py:3829: UserWarning: Default grid_sample and affine_grid behavior has changed to align_corners=False since 1.3.0. Please specify align_corners=True if the old behavior is desired. See the documentation of grid_sample for details.
"Default grid_sample and affine_grid behavior has changed "
Traceback (most recent call last):
File "afy/cam_fomm.py", line 316, in <module>
out = predictor.predict(frame)
File "/media/DATA/avatarify/afy/predictor_local.py", line 106, in predict
out = self.generator(self.source, kp_source=self.kp_source, kp_driving=kp_norm)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/media/DATA/avatarify/fomm/modules/generator_optim.py", line 77, in forward
kp_source=kp_source)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/media/DATA/avatarify/fomm/modules/dense_motion.py", line 96, in forward
prediction = self.hourglass(input)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/media/DATA/avatarify/fomm/modules/util.py", line 196, in forward
return self.decoder(self.encoder(x))
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/media/DATA/avatarify/fomm/modules/util.py", line 178, in forward
out = up_block(out)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/media/DATA/avatarify/fomm/modules/util.py", line 91, in forward
out = self.conv(out)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 399, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/media/DATA/miniconda3/envs/avatarify/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 396, in _conv_forward
self.padding, self.dilation, self.groups)
RuntimeError: CUDA out of memory. Tried to allocate 278.00 MiB (GPU 0; 1.95 GiB total capacity; 632.81 MiB already allocated; 285.50 MiB free; 734.00 MiB reserved in total by PyTorch)
FATAL: exception not rethrown
./run.sh: line 151: 8374 Aborted (core dumped) python afy/cam_fomm.py --config $FOMM_CONFIG --checkpoint $FOMM_CKPT --virt-cam $CAMID_VIRT --relative --adapt_scale $@
It looks like a memory leak; trying to allocate GPU memory in some loop? I can see from the nvidia tools that the GPU memory is getting eaten up and after that run.sh stops; and GPU memory goes back down to what it was before.
I can see from the backtrace you posted that this happens really early during startup, and there are no loops involved there. The function that fails is when we tell PyTorch to load the checkpoint file, which for some reason thinks that you don't have enough GPU memory.
Regarding other processes, you don't even have a web browser open? It sounds like it's saying 632MB GPU RAM is allocated by someone else
Yep it happens very early but on the third occasion it happened much later, after I had pressed "X" to setup my red square. It consumes from 632MB of ram all the way up to 2GB,,, eating 1.4GB of RAM in a matter of few seconds. I saw it comes from Pytorch but at first I was wondering if my checkpoint file could be corrupted or something? Can I get this file from different sources ? The one I have was from a dropbox link.
On Wed, 31 Mar 2021 at 14:39, Johan Aires Rastén @.***> wrote:
It looks like a memory leak; trying to allocate GPU memory in some loop? I can see from the nvidia tools that the GPU memory is getting eaten up and after that run.sh stops; and GPU memory goes back down to what it was before.
I can see from the backtrace you posted that this happens really early during startup, and there are no loops involved there. The function that fails is us telling PyTorch to load the checkpoint file, which for some reason thinks that you don't have enough GPU memory.
Regarding other processes, you don't even have a web browser open? It sounds like it's saying 632MB GPU RAM is allocated by someone else
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/alievk/avatarify-python/issues/385#issuecomment-811328756, or unsubscribe https://github.com/notifications/unsubscribe-auth/AAI3WRYMDTOZWD5FSBCWCA3TGNT6JANCNFSM4YPBVTDQ .
-- Joao Machado @.***
There are 3 alternative download sources in the install instructions, though first run md5sum on the file to verify its contents
It was quite a long time since I installed avatarify-python, but I have two files 2DFAN4-11f355bf06.pth.tar and s3fd-619a316812.pth that I think have been created when running it (because they're not in the repo and you don't download them during installation).. But if you clone avatarify-python to a new folder, and follow the instructions from the beginning you should definitely end up with a clean install
(base) C:\Users\hp>cd avatarify-python
(base) C:\Users\hp\avatarify-python>scripts\install_windows.bat conda found Channels:
- defaults Platform: win-64 Collecting package metadata (repodata.json): done Solving environment: done
Package Plan
environment location: C:\Users\hp\miniconda3\envs\avatarify
added / updated specs: - python=3.7
The following NEW packages will be INSTALLED:
ca-certificates pkgs/main/win-64::ca-certificates-2023.08.22-haa95532_0 certifi pkgs/main/win-64::certifi-2022.12.7-py37haa95532_0 openssl pkgs/main/win-64::openssl-1.1.1w-h2bbff1b_0 pip pkgs/main/win-64::pip-22.3.1-py37haa95532_0 python pkgs/main/win-64::python-3.7.16-h6244533_0 setuptools pkgs/main/win-64::setuptools-65.6.3-py37haa95532_0 sqlite pkgs/main/win-64::sqlite-3.41.2-h2bbff1b_0 vc pkgs/main/win-64::vc-14.2-h21ff451_1 vs2015_runtime pkgs/main/win-64::vs2015_runtime-14.27.29016-h5e58377_2 wheel pkgs/main/win-64::wheel-0.38.4-py37haa95532_0 wincertstore pkgs/main/win-64::wincertstore-0.2-py37haa95532_2
Downloading and Extracting Packages:
Preparing transaction: done Verifying transaction: done Executing transaction: done
To activate this environment, use
$ conda activate avatarify
To deactivate an active environment, use
$ conda deactivate
Channels:
- conda-forge
- defaults Platform: win-64 Collecting package metadata (repodata.json): done Solving environment: done
Package Plan
environment location: C:\Users\hp\miniconda3\envs\avatarify
added / updated specs: - numpy==1.19.0 - python-blosc==1.7.0 - scikit-image
The following NEW packages will be INSTALLED:
blosc conda-forge/win-64::blosc-1.21.5-hdccc3a2_0 brotli conda-forge/win-64::brotli-1.0.9-hcfcfb64_9 brotli-bin conda-forge/win-64::brotli-bin-1.0.9-hcfcfb64_9 bzip2 conda-forge/win-64::bzip2-1.0.8-hcfcfb64_5 cfitsio conda-forge/win-64::cfitsio-3.470-h0af3d06_7 charls conda-forge/win-64::charls-2.2.0-h39d44d4_0 cloudpickle conda-forge/noarch::cloudpickle-2.2.1-pyhd8ed1ab_0 cycler conda-forge/noarch::cycler-0.11.0-pyhd8ed1ab_0 cytoolz conda-forge/win-64::cytoolz-0.12.0-py37hcc03f2d_0 dask-core conda-forge/noarch::dask-core-2022.2.0-pyhd8ed1ab_0 fonttools conda-forge/win-64::fonttools-4.38.0-py37h51bd9d9_0 freetype conda-forge/win-64::freetype-2.12.1-hdaf720e_2 fsspec conda-forge/noarch::fsspec-2023.1.0-pyhd8ed1ab_0 giflib conda-forge/win-64::giflib-5.2.1-h64bf75a_3 imagecodecs pkgs/main/win-64::imagecodecs-2021.8.26-py37hc0a7faf_1 imageio conda-forge/noarch::imageio-2.31.5-pyh8c1a49c_0 intel-openmp conda-forge/win-64::intel-openmp-2023.2.0-h57928b3_50497 jpeg conda-forge/win-64::jpeg-9e-hcfcfb64_3 kiwisolver conda-forge/win-64::kiwisolver-1.4.4-py37h8c56517_0 lcms2 conda-forge/win-64::lcms2-2.14-h90d422f_0 lerc conda-forge/win-64::lerc-3.0-h0e60522_0 libaec conda-forge/win-64::libaec-1.1.2-h63175ca_1 libblas conda-forge/win-64::libblas-3.9.0-20_win64_mkl libbrotlicommon conda-forge/win-64::libbrotlicommon-1.0.9-hcfcfb64_9 libbrotlidec conda-forge/win-64::libbrotlidec-1.0.9-hcfcfb64_9 libbrotlienc conda-forge/win-64::libbrotlienc-1.0.9-hcfcfb64_9 libcblas conda-forge/win-64::libcblas-3.9.0-20_win64_mkl libdeflate conda-forge/win-64::libdeflate-1.8-h8ffe710_0 libhwloc conda-forge/win-64::libhwloc-2.9.3-default_haede6df_1009 libiconv conda-forge/win-64::libiconv-1.17-h8ffe710_0 liblapack conda-forge/win-64::liblapack-3.9.0-20_win64_mkl libpng conda-forge/win-64::libpng-1.6.39-h19919ed_0 libtiff pkgs/main/win-64::libtiff-4.4.0-h8a3f274_2 libwebp-base conda-forge/win-64::libwebp-base-1.3.2-hcfcfb64_0 libxcb conda-forge/win-64::libxcb-1.13-hcd874cb_1004 libxml2 conda-forge/win-64::libxml2-2.11.6-hc3477c8_0 libzlib conda-forge/win-64::libzlib-1.2.13-hcfcfb64_5 libzopfli conda-forge/win-64::libzopfli-1.0.3-h0e60522_0 locket conda-forge/noarch::locket-1.0.0-pyhd8ed1ab_0 lz4-c conda-forge/win-64::lz4-c-1.9.4-hcfcfb64_0 m2w64-gcc-libgfor~ conda-forge/win-64::m2w64-gcc-libgfortran-5.3.0-6 m2w64-gcc-libs conda-forge/win-64::m2w64-gcc-libs-5.3.0-7 m2w64-gcc-libs-co~ conda-forge/win-64::m2w64-gcc-libs-core-5.3.0-7 m2w64-gmp conda-forge/win-64::m2w64-gmp-6.1.0-2 m2w64-libwinpthre~ conda-forge/win-64::m2w64-libwinpthread-git-5.0.0.4634.697f757-2 matplotlib-base conda-forge/win-64::matplotlib-base-3.5.1-py37h4a79c79_0 mkl conda-forge/win-64::mkl-2023.2.0-h6a75c08_50497 msys2-conda-epoch conda-forge/win-64::msys2-conda-epoch-20160418-1 munkres conda-forge/noarch::munkres-1.1.4-pyh9f0ad1d_0 networkx conda-forge/noarch::networkx-2.7-pyhd8ed1ab_0 numpy conda-forge/win-64::numpy-1.19.0-py37hae9e721_0 openjpeg conda-forge/win-64::openjpeg-2.5.0-hc9384bd_1 packaging conda-forge/noarch::packaging-23.2-pyhd8ed1ab_0 pandas pkgs/main/win-64::pandas-1.2.4-py37hf11a4ad_0 partd conda-forge/noarch::partd-1.4.1-pyhd8ed1ab_0 pillow conda-forge/win-64::pillow-9.2.0-py37h42a8222_2 pthread-stubs conda-forge/win-64::pthread-stubs-0.4-hcd874cb_1001 pthreads-win32 conda-forge/win-64::pthreads-win32-2.9.1-hfa6e2cd_3 pyparsing conda-forge/noarch::pyparsing-3.1.1-pyhd8ed1ab_0 python-blosc conda-forge/win-64::python-blosc-1.7.0-py37h6538335_1001 python-dateutil conda-forge/noarch::python-dateutil-2.8.2-pyhd8ed1ab_0 python_abi conda-forge/win-64::python_abi-3.7-4_cp37m pytz conda-forge/noarch::pytz-2023.3.post1-pyhd8ed1ab_0 pywavelets conda-forge/win-64::pywavelets-1.3.0-py37hec80d1f_0 pyyaml conda-forge/win-64::pyyaml-6.0-py37hcc03f2d_4 scikit-image conda-forge/win-64::scikit-image-0.19.2-py37h9386db6_0 scipy conda-forge/win-64::scipy-1.7.3-py37hb6553fb_0 six conda-forge/noarch::six-1.16.0-pyh6c4a22f_0 snappy conda-forge/win-64::snappy-1.1.10-hfb803bf_0 tbb conda-forge/win-64::tbb-2021.10.0-h91493d7_2 tifffile conda-forge/noarch::tifffile-2021.11.2-pyhd8ed1ab_0 tk conda-forge/win-64::tk-8.6.13-h5226925_1 toolz conda-forge/noarch::toolz-0.12.0-pyhd8ed1ab_0 typing-extensions conda-forge/noarch::typing-extensions-4.7.1-hd8ed1ab_0 typing_extensions conda-forge/noarch::typing_extensions-4.7.1-pyha770c72_0 ucrt conda-forge/win-64::ucrt-10.0.22621.0-h57928b3_0 unicodedata2 conda-forge/win-64::unicodedata2-14.0.0-py37hcc03f2d_1 vc14_runtime conda-forge/win-64::vc14_runtime-14.36.32532-hdcecf7f_17 xorg-libxau conda-forge/win-64::xorg-libxau-1.0.11-hcd874cb_0 xorg-libxdmcp conda-forge/win-64::xorg-libxdmcp-1.1.3-hcd874cb_0 xz conda-forge/win-64::xz-5.2.6-h8d14728_0 yaml conda-forge/win-64::yaml-0.2.5-h8ffe710_2 zfp conda-forge/win-64::zfp-0.5.5-h0e60522_8 zlib conda-forge/win-64::zlib-1.2.13-hcfcfb64_5 zstd conda-forge/win-64::zstd-1.5.5-h12be248_0
The following packages will be UPDATED:
ca-certificates pkgs/main::ca-certificates-2023.08.22~ --> conda-forge::ca-certificates-2023.11.17-h56e8100_0 certifi pkgs/main/win-64::certifi-2022.12.7-p~ --> conda-forge/noarch::certifi-2023.11.17-pyhd8ed1ab_0 openssl pkgs/main::openssl-1.1.1w-h2bbff1b_0 --> conda-forge::openssl-3.2.0-hcfcfb64_1 vs2015_runtime pkgs/main::vs2015_runtime-14.27.29016~ --> conda-forge::vs2015_runtime-14.36.32532-h05e6639_17
The following packages will be SUPERSEDED by a higher-priority channel:
python pkgs/main::python-3.7.16-h6244533_0 --> conda-forge::python-3.7.12-h900ac77_100_cpython
Downloading and Extracting Packages:
Preparing transaction: done Verifying transaction: done Executing transaction: done Channels:
- pytorch
- defaults
- conda-forge Platform: win-64 Collecting package metadata (repodata.json): done Solving environment: done
Package Plan
environment location: C:\Users\hp\miniconda3\envs\avatarify
added / updated specs: - cudatoolkit=11.0 - pytorch==1.7.1 - torchvision
The following NEW packages will be INSTALLED:
blas pkgs/main/win-64::blas-1.0-mkl cudatoolkit pkgs/main/win-64::cudatoolkit-11.0.221-h74a9793_0 libuv pkgs/main/win-64::libuv-1.44.2-h2bbff1b_0 libwebp conda-forge/win-64::libwebp-1.3.2-hcfcfb64_1 ninja pkgs/main/win-64::ninja-1.10.2-haa95532_5 ninja-base pkgs/main/win-64::ninja-base-1.10.2-h6d14046_5 pytorch pytorch/win-64::pytorch-1.7.1-py3.7_cuda110_cudnn8_0 torchvision pytorch/win-64::torchvision-0.8.2-py37_cu110
The following packages will be UPDATED:
pillow conda-forge::pillow-9.2.0-py37h42a822~ --> pkgs/main::pillow-9.3.0-py37hdc2b20a_1
The following packages will be SUPERSEDED by a higher-priority channel:
jpeg conda-forge::jpeg-9e-hcfcfb64_3 --> pkgs/main::jpeg-9b-hb83a4c4_2 lcms2 conda-forge::lcms2-2.14-h90d422f_0 --> pkgs/main::lcms2-2.12-h83e58a3_0
Downloading and Extracting Packages:
Preparing transaction: done Verifying transaction: done Executing transaction: done Channels:
- anaconda
- defaults
- conda-forge
- pytorch Platform: win-64 Collecting package metadata (repodata.json): done Solving environment: done
Package Plan
environment location: C:\Users\hp\miniconda3\envs\avatarify
added / updated specs: - git
The following NEW packages will be INSTALLED:
git anaconda/win-64::git-2.40.1-haa95532_1
Downloading and Extracting Packages:
Preparing transaction: done Verifying transaction: done Executing transaction: done Cloning into 'fomm'... remote: Enumerating objects: 211, done. remote: Total 211 (delta 0), reused 0 (delta 0), pack-reused 211Receiving objects: 87% (184/211), 57.88 MiB | 4.20 MiB/s Receiving objects: 100% (211/211), 58.16 MiB | 4.21 MiB/s, done. Resolving deltas: 100% (108/108), done. Collecting opencv-python>=4.2.0.34 Using cached opencv_python-4.8.1.78-cp37-abi3-win_amd64.whl (38.1 MB) Collecting face-alignment==1.3.3 Using cached face_alignment-1.3.3-py2.py3-none-any.whl Collecting pyzmq==20.0.0 Using cached pyzmq-20.0.0-cp37-cp37m-win_amd64.whl (1.0 MB) Collecting msgpack-numpy==0.4.7.1 Using cached msgpack_numpy-0.4.7.1-py2.py3-none-any.whl (6.7 kB) Collecting pyyaml==5.4 Using cached PyYAML-5.4-cp37-cp37m-win_amd64.whl (209 kB) Collecting requests==2.31.0 Using cached requests-2.31.0-py3-none-any.whl (62 kB) Collecting pyfakewebcam==0.1.0 Using cached pyfakewebcam-0.1.0-py3-none-any.whl Requirement already satisfied: torch in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from face-alignment==1.3.3->-r requirements.txt (line 2)) (1.7.1) Collecting numba Using cached numba-0.56.4-cp37-cp37m-win_amd64.whl (2.5 MB) Requirement already satisfied: scipy>=0.17 in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from face-alignment==1.3.3->-r requirements.txt (line 2)) (1.7.3) Collecting tqdm Using cached tqdm-4.66.1-py3-none-any.whl (78 kB) Requirement already satisfied: numpy in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from face-alignment==1.3.3->-r requirements.txt (line 2)) (1.19.0) Requirement already satisfied: scikit-image in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from face-alignment==1.3.3->-r requirements.txt (line 2)) (0.19.2) Collecting msgpack>=0.5.2 Using cached msgpack-1.0.5-cp37-cp37m-win_amd64.whl (62 kB) Requirement already satisfied: certifi>=2017.4.17 in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from requests==2.31.0->-r requirements.txt (line 6)) (2023.11.17) Collecting idna<4,>=2.5 Using cached idna-3.6-py3-none-any.whl (61 kB) Collecting charset-normalizer<4,>=2 Using cached charset_normalizer-3.3.2-cp37-cp37m-win_amd64.whl (98 kB) Collecting urllib3<3,>=1.21.1 Using cached urllib3-2.0.7-py3-none-any.whl (124 kB) Collecting importlib-metadata Using cached importlib_metadata-6.7.0-py3-none-any.whl (22 kB) Requirement already satisfied: setuptools in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from numba->face-alignment==1.3.3->-r requirements.txt (line 2)) (65.6.3) Collecting llvmlite<0.40,>=0.39.0dev0 Using cached llvmlite-0.39.1-cp37-cp37m-win_amd64.whl (23.2 MB) Requirement already satisfied: tifffile>=2019.7.26 in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from scikit-image->face-alignment==1.3.3->-r requirements.txt (line 2)) (2021.11.2) Requirement already satisfied: PyWavelets>=1.1.1 in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from scikit-image->face-alignment==1.3.3->-r requirements.txt (line 2)) (1.3.0) Requirement already satisfied: packaging>=20.0 in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from scikit-image->face-alignment==1.3.3->-r requirements.txt (line 2)) (23.2) Requirement already satisfied: pillow!=7.1.0,!=7.1.1,!=8.3.0,>=6.1.0 in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from scikit-image->face-alignment==1.3.3->-r requirements.txt (line 2)) (9.3.0) Requirement already satisfied: networkx>=2.2 in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from scikit-image->face-alignment==1.3.3->-r requirements.txt (line 2)) (2.7) Requirement already satisfied: imageio>=2.4.1 in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from scikit-image->face-alignment==1.3.3->-r requirements.txt (line 2)) (2.31.5) Requirement already satisfied: typing_extensions in c:\users\hp\miniconda3\envs\avatarify\lib\site-packages (from torch->face-alignment==1.3.3->-r requirements.txt (line 2)) (4.7.1) Collecting colorama Using cached colorama-0.4.6-py2.py3-none-any.whl (25 kB) Collecting zipp>=0.5 Using cached zipp-3.15.0-py3-none-any.whl (6.8 kB) Installing collected packages: msgpack, zipp, urllib3, pyzmq, pyyaml, pyfakewebcam, opencv-python, msgpack-numpy, llvmlite, idna, colorama, charset-normalizer, tqdm, requests, importlib-metadata, numba, face-alignment Attempting uninstall: pyyaml Found existing installation: PyYAML 6.0 Uninstalling PyYAML-6.0: Successfully uninstalled PyYAML-6.0 Successfully installed charset-normalizer-3.3.2 colorama-0.4.6 face-alignment-1.3.3 idna-3.6 importlib-metadata-6.7.0 llvmlite-0.39.1 msgpack-1.0.5 msgpack-numpy-0.4.7.1 numba-0.56.4 opencv-python-4.8.1.78 pyfakewebcam-0.1.0 pyyaml-5.4 pyzmq-20.0.0 requests-2.31.0 tqdm-4.66.1 urllib3-2.0.7 zipp-3.15.0
(avatarify) C:\Users\hp\avatarify-python>run_windows.bat [1701910038.089195] Loading Predictor C:\Users\hp\miniconda3\envs\avatarify\lib\site-packages\torch\nn\functional.py:3103: UserWarning: The default behavior for interpolate/upsample with float scale_factor changed in 1.6.0 to align with other frameworks/libraries, and now uses scale_factor directly, instead of relying on the computed output size. If you wish to restore the old behavior, please set recompute_scale_factor=True. See the documentation of nn.Upsample for details. warnings.warn("The default behavior for interpolate/upsample with float scale_factor changed "
=== Control keys === 1-9: Change avatar 1: avatars\einstein.jpg 2: avatars\eminem.jpg 3: avatars\jobs.jpg 4: avatars\mona.jpg 5: avatars\obama.jpg 6: avatars\potter.jpg 7: avatars\ronaldo.png 8: avatars\schwarzenegger.png W: Zoom camera in S: Zoom camera out A: Previous avatar in folder D: Next avatar in folder Q: Get random avatar X: Calibrate face pose I: Show FPS ESC: Quit
Full key list: https://github.com/alievk/avatarify#controls
Traceback (most recent call last):
File "afy/cam_fomm.py", line 316, in cusparseCreate(handle)
(avatarify) C:\Users\hp\avatarify-python>
(avatarify) C:\Users\hp\avatarify-python>nvidia-smi Thu Dec 7 04:50:58 2023 +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 546.12 Driver Version: 546.12 CUDA Version: 12.3 | |-----------------------------------------+----------------------+----------------------+ | GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+======================+======================| | 0 NVIDIA GeForce RTX 4060 ... WDDM | 00000000:01:00.0 Off | N/A | | N/A 48C P0 13W / 87W | 0MiB / 8188MiB | 0% Default | | | | N/A | +-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | No running processes found | +---------------------------------------------------------------------------------------+
(avatarify) C:\Users\hp\avatarify-python>
Here is it Download anydesk drop the address to my WhatsApp +234 811 513 3627
Or check my video on YouTube Avatarify easy installation https://youtu.be/nW5_-zPVmec
I'm on NVIDIA GeForce RTX 4060, the cam windows opens everything is operational until i pre X to begin and the it close by it self giving this warning.
Traceback (most recent call last): File "afy/cam_fomm.py", line 316, in out = predictor.predict(frame) File "C:\Users\hp\avatarify-python\afy\predictor_local.py", line 104, in predict use_relative_jacobian=self.relative, adapt_movement_scale=self.adapt_movement_scale) File "C:\Users\hp\avatarify-python\afy\predictor_local.py", line 28, in normalize_kp jacobian_diff = torch.matmul(kp_driving['jacobian'], torch.inverse(kp_driving_initial['jacobian'])) RuntimeError: CUDA error: operation not supported when calling cusparseCreate(handle)