M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

If training is failing to start, and you are not receiving an error message telling you what to do, tell us about it here


Forum rules

Read the FAQs and search the forum before posting a new topic.

This forum is for reporting errors with the Training process. If you want to get tips, or better understand the Training process, then you should look in the Training Discussion forum.

Please mark any answers that fixed your problems so others can find the solutions.

Post Reply
User avatar
giz1978
Posts: 1
Joined: Thu Jan 12, 2023 6:42 pm

M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by giz1978 »

Hi all,

this is a great job you doing regarding making FS work on M1-Macs.
Due to this is my first experience with FS I got to install it properly on my M1 Mac and the GUI starts also.

I extracted the images already and now tried to "train".
But none of the models will work. Everytime the process is exited because of this error:

Code: Select all

01/12/2023 19:45:47 INFO     ===================================================
01/12/2023 19:45:47 INFO       Starting
01/12/2023 19:45:47 INFO     ===================================================
01/12/2023 19:45:47 INFO     Loading data, this may take a while...
01/12/2023 19:45:47 INFO     Loading Model from Original plugin...
01/12/2023 19:45:47 INFO     No existing state file found. Generating.
WARNING:tensorflow:Mixed precision compatibility check (mixed_float16): WARNING01/12/2023 19:45:47 INFO     Storing Mixed Precision compatible layers. Please ignore any following warnings about using mixed precision.

Your GPU may run slowly with dtype policy mixed_float16 because it does not have compute capability of at least 7.0. Your GPU:01/12/2023 19:45:47 WARNING  Mixed precision compatibility check (mixed_float16): WARNING

METAL, no compute capability (probably not an Nvidia GPU)Your GPU may run slowly with dtype policy mixed_float16 because it does not have compute capability of at least 7.0. Your GPU:

See https://developer.nvidia.com/cuda-gpus for a list of GPUs and their compute capabilities.  METAL, no compute capability (probably not an Nvidia GPU)

If you will use compatible GPU(s) not attached to this host, e.g. by running a multi-worker model, you can ignore this warning. This message will only be logged onceSee https://developer.nvidia.com/cuda-gpus for a list of GPUs and their compute capabilities.

If you will use compatible GPU(s) not attached to this host, e.g. by running a multi-worker model, you can ignore this warning. This message will only be logged once
Process exited.

I have no idea what to do now... I read that there is a CPU training possible but how do I activate this?

Thank you in advance for any hint.

BR

by torzdf » Wed Jan 18, 2023 1:05 pm

Ok, I think I know the issue, but don't have a Mac to test with.

I think the version of tensorflow-metal (Mac backend) is not compatible with your installed Tensorflow. If you could confirm if the following does or does not fix the issue, I can look to fix the problem permanently. Can you please do the following.

Open up a terminal emulator and enter each of the following commands one by one:

Code: Select all

conda activate faceswap
pip install tensorflow-metal==0.6.0
Go to full post
User avatar
torzdf
Posts: 2202
Joined: Fri Jul 12, 2019 12:53 am
Answers: 141
Has thanked: 108 times
Been thanked: 502 times

Re: M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by torzdf »

Ok, I'm not sure the error message and the exit are related.

The message is actually just a warning saying that mixed precision may run slower as you do not have an Nvidia GPU. This is true, you do not have an Nvidia GPU. How well Apple Silicon runs mixed precision, I do not know, but I would not worry about it too much.

The exit though? Of course that is more problematic.

In the first instance can you post the output of this:
app.php/rules#rule-4b

Could you also fill out the training tab and hit 'Generate' rather than 'train' and post the output here.

My word is final

User avatar
callumfowler101
Posts: 3
Joined: Tue Jan 17, 2023 5:21 pm

Re: M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by callumfowler101 »

Hi,

I had a similar issue. I ran generate and got the following log:

Code: Select all

/Users/username/miniforge3/envs/faceswap/bin/python /Users/username/Documents/Work/ML/faceswap/faceswap.py train -A /Users/username/Documents/Work/ML/environment/a -B /Users/username/Documents/Work/ML/environment/b -m /Users/username/Documents/Work/ML/environment/model -t original -bs 16 -it 1000000 -D default -s 250 -ss 25000 -tia /Users/username/Documents/Work/ML/environment/a -tib /Users/username/Documents/Work/ML/environment/b -to /Users/username/Documents/Work/ML/environment/timelapse -L INFO

Below is the system information.
Thanks for your help in advance.

Code: Select all

============ System Information ============
backend:             apple_silicon
encoding:            UTF-8
git_branch:          master
git_commits:         798e591 unit test updates   - Add XVFB (virtual display)   - Re-activate viewer gui test. 110f53d bugfix - skip tkinter unit tests. 34b5584 bugfix:     - preview tool - Prevent tkinter variables from exiting main thread refactor:     - preview tool - Split module to smaller sub-modules + docs, locales Typing:     - tools.preview.cli Unit test:     - tools.preview.viewer. 80f6328 Bugfixes   - plugin.train.unbalanced - decoder b   - gui.stats - crash when log folder deleted   - setup.py - install gcc=12.1.0 on linux (scipy dep)   - setup.py - don't test ROCm unless valid   - typofix - cli_args extract singleprocess help typing   - lib.gui.analysis.event_reader   - lib.gpu_stats.directml - make platform specific unit tests   - lib.gui.analysis.event_reader. 28cb2fc Unhide options for ROCm
gpu_cuda:            No global version found. Check Conda packages for Conda Cuda
gpu_cudnn:           No global version found. Check Conda packages for Conda cuDNN
gpu_devices:         GPU_0: /physical_device:GPU:0
gpu_devices_active:  GPU_0
gpu_driver:          Not Applicable
gpu_vram:            GPU_0: 16384MB (6540MB free)
os_machine:          arm64
os_platform:         macOS-12.1-arm64-arm-64bit
os_release:          21.2.0
py_command:          faceswap.py gui
py_conda_version:    conda 22.9.0
py_implementation:   CPython
py_version:          3.9.15
py_virtual_env:      True
sys_cores:           10
sys_processor:       arm
sys_ram:             Total: 16384MB, Available: 6530MB, Used: 7715MB, Free: 443MB
User avatar
torzdf
Posts: 2202
Joined: Fri Jul 12, 2019 12:53 am
Answers: 141
Has thanked: 108 times
Been thanked: 502 times

Re: M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by torzdf »

Is the error displayed the same as the above user's?

Also I need the full output from "Help -> Output system information" as it gives me relevant information about the packages installed and config settings.

My word is final

User avatar
callumfowler101
Posts: 3
Joined: Tue Jan 17, 2023 5:21 pm

Re: M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by callumfowler101 »

Yep I get the same error message as OP.

Full System Info below

Code: Select all

============ System Information ============
backend:             apple_silicon
encoding:            UTF-8
git_branch:          master
git_commits:         798e591 unit test updates   - Add XVFB (virtual display)   - Re-activate viewer gui test. 110f53d bugfix - skip tkinter unit tests. 34b5584 bugfix:     - preview tool - Prevent tkinter variables from exiting main thread refactor:     - preview tool - Split module to smaller sub-modules + docs, locales Typing:     - tools.preview.cli Unit test:     - tools.preview.viewer. 80f6328 Bugfixes   - plugin.train.unbalanced - decoder b   - gui.stats - crash when log folder deleted   - setup.py - install gcc=12.1.0 on linux (scipy dep)   - setup.py - don't test ROCm unless valid   - typofix - cli_args extract singleprocess help typing   - lib.gui.analysis.event_reader   - lib.gpu_stats.directml - make platform specific unit tests   - lib.gui.analysis.event_reader. 28cb2fc Unhide options for ROCm
gpu_cuda:            No global version found. Check Conda packages for Conda Cuda
gpu_cudnn:           No global version found. Check Conda packages for Conda cuDNN
gpu_devices:         GPU_0: /physical_device:GPU:0
gpu_devices_active:  GPU_0
gpu_driver:          Not Applicable
gpu_vram:            GPU_0: 16384MB (4750MB free)
os_machine:          arm64
os_platform:         macOS-12.1-arm64-arm-64bit
os_release:          21.2.0
py_command:          faceswap.py gui
py_conda_version:    conda 22.9.0
py_implementation:   CPython
py_version:          3.9.15
py_virtual_env:      True
sys_cores:           10
sys_processor:       arm
sys_ram:             Total: 16384MB, Available: 4725MB, Used: 6786MB, Free: 209MB

=============== Pip Packages ===============
absl-py @ file:///home/conda/feedstock_root/build_artifacts/absl-py_1673535674859/work
aiohttp @ file:///Users/runner/miniforge3/conda-bld/aiohttp_1666878726950/work
aiosignal @ file:///home/conda/feedstock_root/build_artifacts/aiosignal_1667935791922/work
appdirs @ file:///home/conda/feedstock_root/build_artifacts/appdirs_1603108395799/work
astunparse @ file:///home/conda/feedstock_root/build_artifacts/astunparse_1610696312422/work
async-timeout @ file:///home/conda/feedstock_root/build_artifacts/async-timeout_1640026696943/work
attrs @ file:///home/conda/feedstock_root/build_artifacts/attrs_1671632566681/work
blinker @ file:///home/conda/feedstock_root/build_artifacts/blinker_1664823096650/work
brotlipy @ file:///Users/runner/miniforge3/conda-bld/brotlipy_1666764778428/work
cached-property @ file:///home/conda/feedstock_root/build_artifacts/cached_property_1615209429212/work
cachetools @ file:///home/conda/feedstock_root/build_artifacts/cachetools_1673784451927/work
certifi==2022.12.7
cffi @ file:///Users/runner/miniforge3/conda-bld/cffi_1671179432479/work
charset-normalizer @ file:///home/conda/feedstock_root/build_artifacts/charset-normalizer_1661170624537/work
click @ file:///home/conda/feedstock_root/build_artifacts/click_1666798198223/work
cloudpickle @ file:///home/conda/feedstock_root/build_artifacts/cloudpickle_1662587369221/work
colorama @ file:///home/conda/feedstock_root/build_artifacts/colorama_1666700638685/work
cryptography @ file:///Users/runner/miniforge3/conda-bld/cryptography-split_1672673493910/work
cycler @ file:///home/conda/feedstock_root/build_artifacts/cycler_1635519461629/work
decorator @ file:///home/conda/feedstock_root/build_artifacts/decorator_1641555617451/work
dm-tree @ file:///Users/runner/miniforge3/conda-bld/dm-tree_1649681384944/work
fastcluster==1.2.6
ffmpy @ file:///home/conda/feedstock_root/build_artifacts/ffmpy_1659474992694/work
flatbuffers @ file:///home/conda/feedstock_root/build_artifacts/python-flatbuffers_1672960389335/work
fonttools @ file:///Users/runner/miniforge3/conda-bld/fonttools_1666827107313/work
frozenlist @ file:///Users/runner/miniforge3/conda-bld/frozenlist_1667935560987/work
gast @ file:///home/conda/feedstock_root/build_artifacts/gast_1596839682936/work
google-auth @ file:///home/conda/feedstock_root/build_artifacts/google-auth_1669953359096/work
google-auth-oauthlib @ file:///home/conda/feedstock_root/build_artifacts/google-auth-oauthlib_1630497468950/work
google-pasta==0.2.0
grpcio @ file:///Users/runner/miniforge3/conda-bld/grpcio_1653138941901/work
h5py @ file:///Users/runner/miniforge3/conda-bld/h5py_1637964045648/work
idna @ file:///home/conda/feedstock_root/build_artifacts/idna_1663625384323/work
imageio @ file:///home/conda/feedstock_root/build_artifacts/imageio_1673265813438/work
imageio-ffmpeg @ file:///home/conda/feedstock_root/build_artifacts/imageio-ffmpeg_1673483481485/work
importlib-metadata @ file:///home/conda/feedstock_root/build_artifacts/importlib-metadata_1672612343532/work
joblib @ file:///home/conda/feedstock_root/build_artifacts/joblib_1663332044897/work
keras==2.10.0
Keras-Preprocessing @ file:///home/conda/feedstock_root/build_artifacts/keras-preprocessing_1610713559828/work
kiwisolver @ file:///Users/runner/miniforge3/conda-bld/kiwisolver_1666805901953/work
libclang==15.0.6.1
Markdown @ file:///home/conda/feedstock_root/build_artifacts/markdown_1657921053229/work
MarkupSafe @ file:///Users/runner/miniforge3/conda-bld/markupsafe_1666770330366/work
matplotlib @ file:///Users/runner/miniforge3/conda-bld/matplotlib-suite_1661439904837/work
multidict @ file:///Users/runner/miniforge3/conda-bld/multidict_1672339583149/work
munkres==1.1.4
numexpr @ file:///Users/runner/miniforge3/conda-bld/numexpr_1666816696240/work
numpy @ file:///Users/runner/miniforge3/conda-bld/numpy_1660672958449/work
nvidia-ml-py @ file:///home/conda/feedstock_root/build_artifacts/nvidia-ml-py_1673472441120/work
oauthlib @ file:///home/conda/feedstock_root/build_artifacts/oauthlib_1666056362788/work
opencv-python==4.7.0.68
opt-einsum @ file:///home/conda/feedstock_root/build_artifacts/opt_einsum_1617859230218/work
packaging @ file:///home/conda/feedstock_root/build_artifacts/packaging_1673482170163/work
pexpect @ file:///home/conda/feedstock_root/build_artifacts/pexpect_1667297516076/work
Pillow @ file:///Users/runner/miniforge3/conda-bld/pillow_1672675372759/work
pooch @ file:///home/conda/feedstock_root/build_artifacts/pooch_1643032624649/work
protobuf==3.19.4
psutil @ file:///Users/runner/miniforge3/conda-bld/psutil_1667885951924/work
ptyprocess @ file:///home/conda/feedstock_root/build_artifacts/ptyprocess_1609419310487/work/dist/ptyprocess-0.7.0-py2.py3-none-any.whl
pyasn1==0.4.8
pyasn1-modules==0.2.7
pycparser @ file:///home/conda/feedstock_root/build_artifacts/pycparser_1636257122734/work
PyJWT @ file:///home/conda/feedstock_root/build_artifacts/pyjwt_1666240235902/work
pyOpenSSL @ file:///home/conda/feedstock_root/build_artifacts/pyopenssl_1672659226110/work
pyparsing @ file:///home/conda/feedstock_root/build_artifacts/pyparsing_1652235407899/work
PySocks @ file:///home/conda/feedstock_root/build_artifacts/pysocks_1661604839144/work
python-dateutil @ file:///home/conda/feedstock_root/build_artifacts/python-dateutil_1626286286081/work
pyu2f @ file:///home/conda/feedstock_root/build_artifacts/pyu2f_1604248910016/work
requests @ file:///home/conda/feedstock_root/build_artifacts/requests_1673863902341/work
requests-oauthlib @ file:///home/conda/feedstock_root/build_artifacts/requests-oauthlib_1643557462909/work
rsa @ file:///home/conda/feedstock_root/build_artifacts/rsa_1658328885051/work
scikit-learn @ file:///Users/runner/miniforge3/conda-bld/scikit-learn_1670537015787/work
scipy==1.10.0
six @ file:///home/conda/feedstock_root/build_artifacts/six_1620240208055/work
tensorboard==2.10.1
tensorboard-data-server @ file:///Users/runner/miniforge3/conda-bld/tensorboard-data-server_1670043859733/work/tensorboard_data_server-0.6.1-py3-none-macosx_11_0_arm64.whl
tensorboard-plugin-wit @ file:///home/conda/feedstock_root/build_artifacts/tensorboard-plugin-wit_1641458951060/work/tensorboard_plugin_wit-1.8.1-py3-none-any.whl
tensorflow-estimator==2.10.0
tensorflow-macos==2.10.0
tensorflow-metal==0.5.1
tensorflow-probability==0.7.0
termcolor @ file:///home/conda/feedstock_root/build_artifacts/termcolor_1672833821273/work
threadpoolctl @ file:///home/conda/feedstock_root/build_artifacts/threadpoolctl_1643647933166/work
tornado @ file:///Users/runner/miniforge3/conda-bld/tornado_1666788824966/work
tqdm @ file:///home/conda/feedstock_root/build_artifacts/tqdm_1662214488106/work
typing_extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1665144421445/work
unicodedata2 @ file:///Users/runner/miniforge3/conda-bld/unicodedata2_1667239959992/work
urllib3 @ file:///home/conda/feedstock_root/build_artifacts/urllib3_1673452138552/work
Werkzeug @ file:///home/conda/feedstock_root/build_artifacts/werkzeug_1660053523487/work
wrapt @ file:///Users/runner/miniforge3/conda-bld/wrapt_1666806126518/work
yarl @ file:///Users/runner/miniforge3/conda-bld/yarl_1672341025811/work
zipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1669453021653/work

============== Conda Packages ==============
# packages in environment at /Users/callumfowler/miniforge3/envs/faceswap:
#
# Name                    Version                   Build  Channel
absl-py                   1.4.0              pyhd8ed1ab_0    conda-forge
aiohttp                   3.8.3            py39h02fc5c5_1    conda-forge
aiosignal                 1.3.1              pyhd8ed1ab_0    conda-forge
aom                       3.5.0                h7ea286d_0    conda-forge
appdirs                   1.4.4              pyh9f0ad1d_0    conda-forge
astunparse                1.6.3              pyhd8ed1ab_0    conda-forge
async-timeout             4.0.2              pyhd8ed1ab_0    conda-forge
attrs                     22.2.0             pyh71513ae_0    conda-forge
blinker                   1.5                pyhd8ed1ab_0    conda-forge
brotli                    1.0.9                h1a8c8d9_8    conda-forge
brotli-bin                1.0.9                h1a8c8d9_8    conda-forge
brotlipy                  0.7.0           py39h02fc5c5_1005    conda-forge
bzip2                     1.0.8                h3422bc3_4    conda-forge
c-ares                    1.18.1               h3422bc3_0    conda-forge
ca-certificates           2022.12.7            h4653dfc_0    conda-forge
cached-property           1.5.2                hd8ed1ab_1    conda-forge
cached_property           1.5.2              pyha770c72_1    conda-forge
cachetools                5.2.1              pyhd8ed1ab_0    conda-forge
certifi                   2022.12.7          pyhd8ed1ab_0    conda-forge
cffi                      1.15.1           py39h7e6b969_3    conda-forge
charset-normalizer        2.1.1              pyhd8ed1ab_0    conda-forge
click                     8.1.3           unix_pyhd8ed1ab_2    conda-forge
cloudpickle               2.2.0              pyhd8ed1ab_0    conda-forge
colorama                  0.4.6              pyhd8ed1ab_0    conda-forge
cryptography              39.0.0           py39he2a39a8_0    conda-forge
cycler                    0.11.0             pyhd8ed1ab_0    conda-forge
decorator                 5.1.1              pyhd8ed1ab_0    conda-forge
dm-tree                   0.1.7            py39h2666b31_0    conda-forge
expat                     2.5.0                hb7217d7_0    conda-forge
fastcluster               1.2.6                    pypi_0    pypi
ffmpeg                    5.1.2           gpl_hf318d42_105    conda-forge
ffmpy                     0.3.0              pyhb6f538c_0    conda-forge
flatbuffers               22.12.06             hb7217d7_2    conda-forge
font-ttf-dejavu-sans-mono 2.37                 hab24e00_0    conda-forge
font-ttf-inconsolata      3.000                h77eed37_0    conda-forge
font-ttf-source-code-pro  2.038                h77eed37_0    conda-forge
font-ttf-ubuntu           0.83                 hab24e00_0    conda-forge
fontconfig                2.14.1               h82840c6_0    conda-forge
fonts-conda-ecosystem     1                             0    conda-forge
fonts-conda-forge         1                             0    conda-forge
fonttools                 4.38.0           py39h02fc5c5_1    conda-forge
freetype                  2.12.1               hd633e50_1    conda-forge
frozenlist                1.3.3            py39h02fc5c5_0    conda-forge
gast                      0.4.0              pyh9f0ad1d_0    conda-forge
gettext                   0.21.1               h0186832_0    conda-forge
giflib                    5.2.1                h27ca646_2    conda-forge
gmp                       6.2.1                h9f76cd9_0    conda-forge
gnutls                    3.7.8                h9f1a10d_0    conda-forge
google-auth               2.15.0             pyh1a96a4e_0    conda-forge
google-auth-oauthlib      0.4.6              pyhd8ed1ab_0    conda-forge
google-pasta              0.2.0              pyh8c360ce_0    conda-forge
grpcio                    1.46.3           py39h365d37b_0    conda-forge
h5py                      3.6.0           nompi_py39hd982b79_100    conda-forge
hdf5                      1.12.1          nompi_hd9dbc9e_104    conda-forge
icu                       70.1                 h6b3803e_0    conda-forge
idna                      3.4                pyhd8ed1ab_0    conda-forge
imageio                   2.24.0             pyh24c5eb1_0    conda-forge
imageio-ffmpeg            0.4.8              pyhd8ed1ab_0    conda-forge
importlib-metadata        6.0.0              pyha770c72_0    conda-forge
joblib                    1.2.0              pyhd8ed1ab_0    conda-forge
jpeg                      9e                   he4db4b2_2    conda-forge
keras                     2.10.0                   pypi_0    pypi
keras-preprocessing       1.1.2              pyhd8ed1ab_0    conda-forge
kiwisolver                1.4.4            py39haaf3ac1_1    conda-forge
krb5                      1.20.1               h69eda48_0    conda-forge
lame                      3.100             h1a8c8d9_1003    conda-forge
lcms2                     2.14                 h481adae_1    conda-forge
lerc                      4.0.0                h9a09cb3_0    conda-forge
libabseil                 20220623.0      cxx17_h28b99d4_6    conda-forge
libaec                    1.0.6                hb7217d7_1    conda-forge
libblas                   3.9.0           16_osxarm64_openblas    conda-forge
libbrotlicommon           1.0.9                h1a8c8d9_8    conda-forge
libbrotlidec              1.0.9                h1a8c8d9_8    conda-forge
libbrotlienc              1.0.9                h1a8c8d9_8    conda-forge
libcblas                  3.9.0           16_osxarm64_openblas    conda-forge
libclang                  15.0.6.1                 pypi_0    pypi
libcurl                   7.87.0               h9049daf_0    conda-forge
libcxx                    14.0.6               h2692d47_0    conda-forge
libdeflate                1.17                 h1a8c8d9_0    conda-forge
libedit                   3.1.20191231         hc8eb9b7_2    conda-forge
libev                     4.33                 h642e427_1    conda-forge
libffi                    3.4.2                h3422bc3_5    conda-forge
libgfortran               5.0.0           11_3_0_hd922786_27    conda-forge
libgfortran5              11.3.0              hdaf2cc0_27    conda-forge
libiconv                  1.17                 he4db4b2_0    conda-forge
libidn2                   2.3.4                h1a8c8d9_0    conda-forge
libjpeg-turbo             2.1.4                h1a8c8d9_0    conda-forge
liblapack                 3.9.0           16_osxarm64_openblas    conda-forge
libnghttp2                1.51.0               hae82a92_0    conda-forge
libopenblas               0.3.21          openmp_hc731615_3    conda-forge
libpng                    1.6.39               h76d750c_0    conda-forge
libprotobuf               3.19.4               hccf11d3_0    conda-forge
libsqlite                 3.40.0               h76d750c_0    conda-forge
libssh2                   1.10.0               h7a5bd25_3    conda-forge
libtasn1                  4.19.0               h1a8c8d9_0    conda-forge
libtiff                   4.5.0                h5dffbdd_2    conda-forge
libunistring              0.9.10               h3422bc3_0    conda-forge
libvpx                    1.11.0               hc470f4d_3    conda-forge
libwebp-base              1.2.4                h57fd34a_0    conda-forge
libxcb                    1.13              h9b22ae9_1004    conda-forge
libxml2                   2.10.3               h87b0503_0    conda-forge
libzlib                   1.2.13               h03a7124_4    conda-forge
llvm-openmp               15.0.7               h7cfbb63_0    conda-forge
markdown                  3.4.1              pyhd8ed1ab_0    conda-forge
markupsafe                2.1.1            py39h02fc5c5_2    conda-forge
matplotlib                3.5.3            py39hdf13c20_2    conda-forge
matplotlib-base           3.5.3            py39ha500c34_2    conda-forge
multidict                 6.0.4            py39h02fc5c5_0    conda-forge
munkres                   1.1.4              pyh9f0ad1d_0    conda-forge
ncurses                   6.3                  h07bb92c_1    conda-forge
nettle                    3.8.1                h63371fa_1    conda-forge
numexpr                   2.8.3            py39hde7b980_1    conda-forge
numpy                     1.23.2           py39h3668e8b_0    conda-forge
nvidia-ml-py              11.525.84          pyhd8ed1ab_2    conda-forge
oauthlib                  3.2.2              pyhd8ed1ab_0    conda-forge
opencv-python             4.7.0.68                 pypi_0    pypi
openh264                  2.3.1                hb7217d7_1    conda-forge
openjpeg                  2.5.0                hbc2ba62_2    conda-forge
openssl                   3.0.7                h03a7124_1    conda-forge
opt_einsum                3.3.0              pyhd8ed1ab_1    conda-forge
p11-kit                   0.24.1               h29577a5_0    conda-forge
packaging                 23.0               pyhd8ed1ab_0    conda-forge
pexpect                   4.8.0              pyh1a96a4e_2    conda-forge
pillow                    9.4.0            py39h8bbe137_0    conda-forge
pip                       22.3.1             pyhd8ed1ab_0    conda-forge
pooch                     1.6.0              pyhd8ed1ab_0    conda-forge
protobuf                  3.19.4           py39hfb83b0d_0    conda-forge
psutil                    5.9.4            py39h02fc5c5_0    conda-forge
pthread-stubs             0.4               h27ca646_1001    conda-forge
ptyprocess                0.7.0              pyhd3deb0d_0    conda-forge
pyasn1                    0.4.8                      py_0    conda-forge
pyasn1-modules            0.2.7                      py_0    conda-forge
pycparser                 2.21               pyhd8ed1ab_0    conda-forge
pyjwt                     2.6.0              pyhd8ed1ab_0    conda-forge
pyopenssl                 23.0.0             pyhd8ed1ab_0    conda-forge
pyparsing                 3.0.9              pyhd8ed1ab_0    conda-forge
pysocks                   1.7.1              pyha2e5f31_6    conda-forge
python                    3.9.15          hea58f1e_0_cpython    conda-forge
python-dateutil           2.8.2              pyhd8ed1ab_0    conda-forge
python-flatbuffers        23.1.4             pyhd8ed1ab_0    conda-forge
python_abi                3.9                      3_cp39    conda-forge
pyu2f                     0.1.5              pyhd8ed1ab_0    conda-forge
re2                       2022.06.01           h9a09cb3_1    conda-forge
readline                  8.1.2                h46ed386_0    conda-forge
requests                  2.28.2             pyhd8ed1ab_0    conda-forge
requests-oauthlib         1.3.1              pyhd8ed1ab_0    conda-forge
rsa                       4.9                pyhd8ed1ab_0    conda-forge
scikit-learn              1.2.0            py39h57c6424_0    conda-forge
scipy                     1.10.0           py39h18313fe_0    conda-forge
setuptools                66.0.0             pyhd8ed1ab_0    conda-forge
six                       1.16.0             pyh6c4a22f_0    conda-forge
snappy                    1.1.9                h17c5cce_2    conda-forge
svt-av1                   1.4.1                h7ea286d_0    conda-forge
tensorboard               2.10.1                   pypi_0    pypi
tensorboard-data-server   0.6.1            py39he2a39a8_4    conda-forge
tensorboard-plugin-wit    1.8.1              pyhd8ed1ab_0    conda-forge
tensorflow-deps           2.10.0                        0    apple
tensorflow-estimator      2.10.0                   pypi_0    pypi
tensorflow-macos          2.10.0                   pypi_0    pypi
tensorflow-metal          0.5.1                    pypi_0    pypi
tensorflow-probability    0.7                        py_1    conda-forge
termcolor                 2.2.0              pyhd8ed1ab_0    conda-forge
threadpoolctl             3.1.0              pyh8a188c0_0    conda-forge
tk                        8.6.12               he1e0b03_0    conda-forge
tornado                   6.2              py39h02fc5c5_1    conda-forge
tqdm                      4.64.1             pyhd8ed1ab_0    conda-forge
typing-extensions         4.4.0                hd8ed1ab_0    conda-forge
typing_extensions         4.4.0              pyha770c72_0    conda-forge
tzdata                    2022g                h191b570_0    conda-forge
unicodedata2              15.0.0           py39h02fc5c5_0    conda-forge
urllib3                   1.26.14            pyhd8ed1ab_0    conda-forge
werkzeug                  2.2.2              pyhd8ed1ab_0    conda-forge
wheel                     0.38.4             pyhd8ed1ab_0    conda-forge
wrapt                     1.14.1           py39h02fc5c5_1    conda-forge
x264                      1!164.3095           h57fd34a_2    conda-forge
x265                      3.5                  hbc6ce65_3    conda-forge
xorg-libxau               1.0.9                h27ca646_0    conda-forge
xorg-libxdmcp             1.1.3                h27ca646_0    conda-forge
xz                        5.2.6                h57fd34a_0    conda-forge
yarl                      1.8.2            py39h02fc5c5_0    conda-forge
zipp                      3.11.0             pyhd8ed1ab_0    conda-forge
zlib                      1.2.13               h03a7124_4    conda-forge
zstd                      1.5.2                h8128057_4    conda-forge

================= Configs ==================
--------- convert.ini ---------

[color.color_transfer]
clip:                     True
preserve_paper:           True

[color.match_hist]
threshold:                99.0

[color.manual_balance]
colorspace:               HSV
balance_1:                0.0
balance_2:                0.0
balance_3:                0.0
contrast:                 0.0
brightness:               0.0

[writer.pillow]
format:                   png
draw_transparent:         False
separate_mask:            False
optimize:                 False
gif_interlace:            True
jpg_quality:              75
png_compress_level:       3
tif_compression:          tiff_deflate

[writer.ffmpeg]
container:                mp4
codec:                    libx264
crf:                      23
preset:                   medium
tune:                     none
profile:                  auto
level:                    auto
skip_mux:                 False

[writer.gif]
fps:                      25
loop:                     0
palettesize:              256
subrectangles:            False

[writer.opencv]
format:                   png
draw_transparent:         False
separate_mask:            False
jpg_quality:              75
png_compress_level:       3

[mask.mask_blend]
type:                     normalized
kernel_size:              3
passes:                   4
threshold:                4
erosion:                  0.0
erosion_top:              0.0
erosion_bottom:           0.0
erosion_left:             0.0
erosion_right:            0.0

[scaling.sharpen]
method:                   none
amount:                   150
radius:                   0.3
threshold:                5.0

--------- gui.ini ---------

[global]
fullscreen:               False
tab:                      extract
options_panel_width:      30
console_panel_height:     20
icon_size:                14
font:                     default
font_size:                9
autosave_last_session:    prompt
timeout:                  120
auto_load_model_stats:    True

--------- .faceswap ---------
backend:                  apple_silicon

--------- extract.ini ---------

[global]
allow_growth:             False
aligner_min_scale:        0.07
aligner_max_scale:        2.0
aligner_distance:         22.5
aligner_roll:             45.0
aligner_features:         True
filter_refeed:            True
save_filtered:            False
realign_refeeds:          True
filter_realign:           True

[detect.mtcnn]
minsize:                  20
scalefactor:              0.709
batch-size:               8
cpu:                      True
threshold_1:              0.6
threshold_2:              0.7
threshold_3:              0.7

[detect.cv2_dnn]
confidence:               50

[detect.s3fd]
confidence:               70
batch-size:               4

[align.fan]
batch-size:               12

[mask.unet_dfl]
batch-size:               8

[mask.custom]
batch-size:               8
centering:                face
fill:                     False

[mask.vgg_obstructed]
batch-size:               2

[mask.vgg_clear]
batch-size:               6

[mask.bisenet_fp]
batch-size:               8
cpu:                      False
weights:                  faceswap
include_ears:             False
include_hair:             False
include_glasses:          True

[recognition.vgg_face2]
batch-size:               16
cpu:                      False

--------- train.ini ---------

[global]
centering:                face
coverage:                 87.5
icnr_init:                False
conv_aware_init:          False
optimizer:                adam
learning_rate:            5e-05
epsilon_exponent:         -7
autoclip:                 False
reflect_padding:          False
allow_growth:             False
mixed_precision:          False
nan_protection:           True
convert_batchsize:        16

[global.loss]
loss_function:            ssim
loss_function_2:          mse
loss_weight_2:            100
loss_function_3:          none
loss_weight_3:            0
loss_function_4:          none
loss_weight_4:            0
mask_loss_function:       mse
eye_multiplier:           3
mouth_multiplier:         2
penalized_mask_loss:      True
mask_type:                extended
mask_blur_kernel:         3
mask_threshold:           4
learn_mask:               False

[model.phaze_a]
output_size:              128
shared_fc:                none
enable_gblock:            True
split_fc:                 True
split_gblock:             False
split_decoders:           False
enc_architecture:         fs_original
enc_scaling:              7
enc_load_weights:         True
bottleneck_type:          dense
bottleneck_norm:          none
bottleneck_size:          1024
bottleneck_in_encoder:    True
fc_depth:                 1
fc_min_filters:           1024
fc_max_filters:           1024
fc_dimensions:            4
fc_filter_slope:          -0.5
fc_dropout:               0.0
fc_upsampler:             upsample2d
fc_upsamples:             1
fc_upsample_filters:      512
fc_gblock_depth:          3
fc_gblock_min_nodes:      512
fc_gblock_max_nodes:      512
fc_gblock_filter_slope:   -0.5
fc_gblock_dropout:        0.0
dec_upscale_method:       subpixel
dec_upscales_in_fc:       0
dec_norm:                 none
dec_min_filters:          64
dec_max_filters:          512
dec_slope_mode:           full
dec_filter_slope:         -0.45
dec_res_blocks:           1
dec_output_kernel:        5
dec_gaussian:             True
dec_skip_last_residual:   True
freeze_layers:            keras_encoder
load_layers:              encoder
fs_original_depth:        4
fs_original_min_filters:  128
fs_original_max_filters:  1024
fs_original_use_alt:      False
mobilenet_width:          1.0
mobilenet_depth:          1
mobilenet_dropout:        0.001
mobilenet_minimalistic:   False

[model.realface]
input_size:               64
output_size:              128
dense_nodes:              1536
complexity_encoder:       128
complexity_decoder:       512

[model.dfl_sae]
input_size:               128
architecture:             df
autoencoder_dims:         0
encoder_dims:             42
decoder_dims:             21
multiscale_decoder:       False

[model.unbalanced]
input_size:               128
lowmem:                   False
nodes:                    1024
complexity_encoder:       128
complexity_decoder_a:     384
complexity_decoder_b:     512

[model.dlight]
features:                 best
details:                  good
output_size:              256

[model.villain]
lowmem:                   False

[model.dfaker]
output_size:              128

[model.original]
lowmem:                   False

[model.dfl_h128]
lowmem:                   False

[trainer.original]
preview_images:           14
zoom_amount:              5
rotation_range:           10
shift_range:              5
flip_chance:              50
color_lightness:          30
color_ab:                 8
color_clahe_chance:       50
color_clahe_max_size:     4
User avatar
torzdf
Posts: 2202
Joined: Fri Jul 12, 2019 12:53 am
Answers: 141
Has thanked: 108 times
Been thanked: 502 times

Re: M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by torzdf »

Ok, I think I know the issue, but don't have a Mac to test with.

I think the version of tensorflow-metal (Mac backend) is not compatible with your installed Tensorflow. If you could confirm if the following does or does not fix the issue, I can look to fix the problem permanently. Can you please do the following.

Open up a terminal emulator and enter each of the following commands one by one:

Code: Select all

conda activate faceswap
pip install tensorflow-metal==0.6.0

My word is final

User avatar
callumfowler101
Posts: 3
Joined: Tue Jan 17, 2023 5:21 pm

Re: M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by callumfowler101 »

yes that worked, thank you!

User avatar
torzdf
Posts: 2202
Joined: Fri Jul 12, 2019 12:53 am
Answers: 141
Has thanked: 108 times
Been thanked: 502 times

Re: M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by torzdf »

Thanks for the feedback. I have marked this as a bug and will look to put in a proper fix in the coming days.

My word is final

User avatar
torzdf
Posts: 2202
Joined: Fri Jul 12, 2019 12:53 am
Answers: 141
Has thanked: 108 times
Been thanked: 502 times

Re: M1 Mac - Exit with METAL, no compute capability (probably not an Nvidia GPU)

Post by torzdf »

I have update the tensorflow-metal requirement to the correct version, so hopefully that is enough to fix this bug

My word is final

Post Reply