sensity-ai / dot Goto Github PK

View Code? Open in Web Editor NEW

3.9K 3.9K 368.0 16.63 MB

The Deepfake Offensive Toolkit

License: BSD 3-Clause "New" or "Revised" License

Python 93.99% C++ 0.51% Cuda 3.25% Jupyter Notebook 1.86% Dockerfile 0.39%

dot's People

Contributors

Stargazers

Watchers

Forkers

gaganpreet arseniyshestakov roguesupport-scott srikwit mem0r1 mrtksn ziming 4lch4 dayglo sjfbo anshulsojatia gluhbirnecom security-geeks washingweb blka jilir pat-vdv deepb1t rinobatin kpgx gijs fortunewalla designium jackyyvan fabriziogiordano brenwhyte heliloop asiellb humandotlearning hirajanwin buffalonian hari7190 sinsixx entn-at maksim-m xyzzy3000 ubyjvovk dylanvolz mhkeller todjiang pplanel thearchiver rozgo edumzii saifrahmed loispostula srikalyan erahhal jerryrelmore johnjboren kubes conradakunga knicholes dootbin khattacorp trigunshin kamalkraj willshion gooshy jpsca nelseric naumix gottz thhepp ssteo pushpen cyberflamego trentsterling fullstackjohnmack techthiyanes konstantindjairo wottan32 jawond abishekmuthian christofersimbar timpara rioscode 83521166 nndnha jorik041 leonardotw jerrycastanos danaris mrcodechef shane-reaume tdhtttt iamsarthakjoshi mamkramer smu-rainflow heracraft kp-forks benderpan suryatmodulus iuriimattos2 gegai yupbank vukitoso keksbrot shaggyface coolashel

dot's Issues

Run dot on Silicon Mac M1/M2

How can I convert it into exe?

Hi
how can I convert dot fully with all of its library into exe?
I tried a few things it didn't work out for me.
Could anyone please guide me properly which things to use or anything else?

Thank You

Detect relatively small/far-away faces for swap

I noticed that the face is not always detected in target images and this happens when the face is relatively small in the target image. I have been digging into it a bit, but as far as I understand this has something to do with the implementation of the Google Mediapipe Face Mesh into Simswap. Face Mesh is not able to detect such small faces. But when using Simswap from the original repo this is not an issue and the swap always works fine. I also read that the Mediapipe has no solution yet for smaller faces in combination with the Face Mesh, tho they have it for Face Detection.

Is there a way to bypass the Face Mesh Pipeline and to make the swap happen using original Simswap? Or is there maybe another way to make swapping of relatively small faces possible or to implement something for this?

There is no "[python.exe]: fomm" in Windows dropdown

Following the guide on here https://github.com/sensity-ai/dot#virtual-camera-injection I can't find [python.exe]: fomm, I am using OBS 27.0.1 as you describe because the current version of OBS has built in virtual camera, there is no something like "[python.exe]: fomm" as you described here. (In the appeared window, choose "[python.exe]: fomm" in Window drop-down menu and press OK.) Also there is no In OBS Studio, go to Tools -> VirtualCam. Check AutoStart section on OBS What am i missing, what version of the OBS does this dot works with?

Issue with Colab Demo

Hello,

When running the colab demo I encounter this issue when attempting to run the final cell (the one that performs the swap on video):

python: can't open file 'scripts/video_swap.py': [Errno 2] No such file or directory

If I correct the path to /content/dot/scripts/video_swap.py I get this error:

Loading config: ./dot/simswap/configs/config.yaml
Traceback (most recent call last):
  File "scripts/video_swap.py", line 77, in <module>
    main()
  File "/usr/local/lib/python3.8/site-packages/click/core.py", line 1126, in __call__
    return self.main(*args, **kwargs)
  File "/usr/local/lib/python3.8/site-packages/click/core.py", line 1051, in main
    rv = self.invoke(ctx)
  File "/usr/local/lib/python3.8/site-packages/click/core.py", line 1393, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/usr/local/lib/python3.8/site-packages/click/core.py", line 752, in invoke
    return __callback(*args, **kwargs)
  File "scripts/video_swap.py", line 53, in main
    with open(config) as f:
FileNotFoundError: [Errno 2] No such file or directory: './dot/simswap/configs/config.yaml'

Finally, if I move the "dot" folder in "src" to the to the main "dot" folder (following the error above) I receive this error:

Traceback (most recent call last):
  File "/content/dot/scripts/video_swap.py", line 10, in <module>
    import dot
ModuleNotFoundError: No module named 'dot'

After that I am stumped, though I am sure there is something quite obvious that I am missing.

Using dot with other/individual faces?

❓ Ask a Question:

Can I use dot with my own preferred faces? If yes, what would I need?

Did you include a watermark in DOT?

Does the DOT have a watermark that can be used to determine the stream uses DOT?

Description:

For the DOT to work reliably independent of whether or not an authenticator used the/a watermark detector, it is important the DOT is indistinguishable from an arbitrary real stream. Hence, I was wondering whether you included a watermark or not. Additionally, I would like to kindly ask: would you perhaps be able to enlighten us on whether there are data characteristics/signatures that hint on the DOT being used instead of an arbitrary video?

How to run dot?

Ask a Question:

Did everything as described. But zoom/obs is not showing anything, only a black screen of obs and my mouse movements.

How to I set it up to use the facecam?

Description:

Add Colab demo for testing without webcam

Please add Colab demo for testing without webcam, thanks!

Accidently submited this

❓ Ask a Question:

Description:

Run dot on cloud GPU

For users without an available local GPU, we should support cloud GPU compute.

See:
https://github.com/cmusatyalab/openrtist
https://github.com/alievk/avatarify-python#news

Speed up SimSwap's `reverse2original`

The bottleneck for speed isn't the SimSwap model, but the image paste back algorithm. We should speed that up to allow higher FPS: reverse2original.py

command name clash

dot is already a command from the Graphviz project: https://graphviz.org/doc/info/command.html . It is very likely that other programs might launch dot expecting different outcome.

Easy solution for start would be not to encourage pip install -e . and run from a venv.

Run dot with docker

An issue with windows installation

I just download Conda from https://www.anaconda.com/products/distribution
after that, I checked my CUDA version and got 12.0
Tried to create a .yaml file but didn't succeed

PS E:\DeepFace\dot-1.1.0\dot-1.1.0> conda env create -f envs/environment-gpu.yaml

EnvironmentFileNotFound: 'E:\DeepFace\dot-1.1.0\dot-1.1.0\envs\environment-gpu.yaml' file not found

Tried to install cudatoolkit but didn't succeed (11.1, 12.0, and 11.8.0)

PS E:\DeepFace\dot-1.1.0\dot-1.1.0\envs> conda install cudatoolkit=11.1
Collecting package metadata (current_repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Collecting package metadata (repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.

PackagesNotFoundError: The following packages are not available from current channels:

  - cudatoolkit=11.1

Current channels:

  - 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

To search for alternate channels that may provide the conda package you're
looking for, navigate to

    https://anaconda.org

and use the search bar at the top of the page.

this is my nvidia-smi

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 528.24       Driver Version: 528.24       CUDA Version: 12.0     |
|-------------------------------+----------------------+----------------------+
| 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 ... WDDM  | 00000000:2D:00.0  On |                  N/A |
|  0%   43C    P8    33W / 340W |   1504MiB / 10240MiB |      1%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

any ideas?

Thanks

EnvironmentFileNotFound: 'C:\Users\envs\environment-cpu.yaml' file not found

By entering the conda env create -f envs/environment-gpu.yaml at the frist step.

What am I doing wrong? I open anaconda prompt and enter the code.

Best regards

Measure FPS for different hardware

Include stats in the README

Torch and torchvision check issue

❓ Ask a Question:

Description:

last step was installing torch and toch vision:

conda install pytorch torchvision torchaudio pytorch-cuda=11.7 -c pytorch -c nvidia

after checking with:

python -c "import torch; print(torch.cuda.is_available())

I get error:

Traceback (most recent call last):
File "", line 1, in
File "C:\Users\user1\miniconda3\envs\dot\lib\site-packages\torch_init_.py", line 122, in
raise err
OSError: [WinError 127] Die angegebene Prozedur wurde nicht gefunden. Error loading "C:\Users\user1\miniconda3\envs\dot\lib\site-packages\torch\lib\caffe2_detectron_ops.dll" or one of its dependencies.

Wrong torch or cudatoolkit version?

I downloaded pytorch cuda 11.7 and cudatoolki 11.3.1 ( conda install -c anaconda cudatoolkit).

Need help

How to set DOT on windows?

I can’t figure out the installation, there are no options for installing on windows in the documentation, although the instructions for installing on windows are written only for Obs studio. please give advice.

ERROR: Package 'dot' requires a different Python: 3.10.8 not in '<3.9,>=3.8'

🐛 Bug Report

Python downgrade?

Description:

Python 3.10.8 latest miniconda installed. Do I need a downgrade? if yes to which version exactly?

Expected Behavior:

If I run on google colab how will I verify on my laptop if verification is needed by apps

I don't have a laptop with GPU I am plannng to run on google colab, so my question is how will i verify if certain apps ask for verification because my laptop is local?

Does this only work with camera footage or can a video be imported?

❓ Ask a Question:

Description:

Save model checkpoints as binaries in the releases. Remove GDrive links

help in making dot work properly

delete

Need info

Hello, I'm new to programming and stuff and I had great difficulties to successfully install dot but I did.
So I just wanna ask if I only have to know about python to successfully use dot?

Warnings when running dot

🐛 Bug Report

Description:

Getting warnings when running dot. This issue was mentioned in #59.

PS E:\DeepFace\dot-1.1.0\dot-1.1.0> dot -c ./configs/simswap.yaml --target 0 --source "./data" --use_gpu
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.parallel.data_parallel.DataParallel' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'models.ArcMarginModel' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'models.ResNet' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.batchnorm.BatchNorm2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.activation.PReLU' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.pooling.MaxPool2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.container.Sequential' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'models.SEBlock' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.pooling.AdaptiveAvgPool2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.linear.Linear' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.activation.Sigmoid' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.dropout.Dropout' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Python\lib\site-packages\torch\serialization.py:671: SourceChangeWarning: source code of class 'torch.nn.modules.batchnorm.BatchNorm1d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
'strict' is an invalid keyword argument for load()
=== Control keys ===
1-9: Change avatar
1: .\data\ronaldo.png
2: .\data\schwarzenegger.png
3: .\data\Brad Pitt.jpg
4: .\data\David Beckham.jpg
5: .\data\einstein.jpg
6: .\data\eminem.jpg
7: .\data\jobs.jpg
8: .\data\Joe Biden.jpg
9: .\data\Leonardo Dicaprio.jpg
10: .\data\Markiplier.jpg
11: .\data\mona.jpg
12: .\data\obama.jpg
13: .\data\Pewdiepie.jpg
14: .\data\potter.jpg
15: .\data\Tom Cruise.jpg
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
C:\Python\lib\site-packages\torch\nn\functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
  warnings.warn(

run dot

When I try to start the point, it gives an error, what do I have to do?

(dot) C:\Users\1\dot-main>dot -c ./configs/simswap.yaml --target 0 --source "./data" --use_gpu
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
Traceback (most recent call last):
File "C:\Users\1\miniconda3\envs\dot\lib\runpy.py", line 194, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Users\1\miniconda3\envs\dot\lib\runpy.py", line 87, in run_code
exec(code, run_globals)
File "C:\Users\1\miniconda3\envs\dot\Scripts\dot.exe_main.py", line 7, in
File "C:\Users\1\miniconda3\envs\dot\lib\site-packages\click\core.py", line 1130, in call
return self.main(*args, **kwargs)
File "C:\Users\1\miniconda3\envs\dot\lib\site-packages\click\core.py", line 1055, in main
rv = self.invoke(ctx)
File "C:\Users\1\miniconda3\envs\dot\lib\site-packages\click\core.py", line 1404, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\1\miniconda3\envs\dot\lib\site-packages\click\core.py", line 760, in invoke
return callback(*args, **kwargs)
File "C:\Users\1\dot-main\src\dot_main.py", line 206, in main
run(
File "C:\Users\1\dot-main\src\dot_main.py", line 67, in run
dot.generate(
File "C:\Users\1\dot-main\src\dot\dot.py", line 131, in generate
option.generate_from_camera(
File "C:\Users\1\dot-main\src\dot\commons\model_option.py", line 184, in generate_from_camera
self.create_model(opt_crop_size=opt_crop_size, **kwargs)
File "C:\Users\1\dot-main\src\dot\simswap\option.py", line 80, in create_model
self.spNorm = SpecificNorm(use_gpu=self.use_gpu)
File "C:\Users\1\dot-main\src\dot\simswap\util\norm.py", line 17, in init
self.mean = torch.from_numpy(self.mean).float().cuda()
File "C:\Users\1\miniconda3\envs\dot\lib\site-packages\torch\cuda_init.py", line 221, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled

(dot) C:\Users\1\dot-main>dot
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
Usage: dot [OPTIONS]
Try 'dot --help' for help.

Error: Missing option '--source'.

Add Python 3.10 support

✨ Feature Request

Description:

As a code owner, I want to add Python 3.10 support for dot.

Acceptance Criteria:

update setup.cfg
update GA workflows + run unit tests

Error no Face detected!

When I run on cpu i got the following errors an I followed everything correctly:
'strict' is an invalid keyword argument for load()
=== Control keys ===
1-9: Change avatar
1: .\data\ronaldo.png
2: .\data\schwarzenegger.png
3: .\data\Brad Pitt.jpg
4: .\data\David Beckham.jpg
5: .\data\einstein.jpg
6: .\data\eminem.jpg
7: .\data\jobs.jpg
8: .\data\Joe Biden.jpg
9: .\data\Leonardo Dicaprio.jpg
10: .\data\Markiplier.jpg
11: .\data\mona.jpg
12: .\data\obama.jpg
13: .\data\Pewdiepie.jpg
14: .\data\potter.jpg
15: .\data\Tom Cruise.jpg
C:\Users\Pro\miniconda3\envs\dot\lib\site-packages\torch\nn\functional.py:718: UserWarning: Named tensors and all their associated APIs are an experimental feature and subject to change. Please do not use them for anything important until they are released as stable. (Triggered internally at ..\c10/core/TensorImpl.h:1156.)
return torch.max_pool2d(input, kernel_size, stride, padding, dilation, ceil_mode)
C:\Users\Pro\miniconda3\envs\dot\lib\site-packages\torch\nn\functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.
warnings.warn(
ERROR: No face detected!
ERROR: No face detected!
ERROR: No face detected!
ERROR: No face detected!

Aborted!

ERROR: No matching distribution found for onnxruntime-gpu==1.9.0

❓ Ask a Question:

I am trying to install DOT but I have an issue while running creating conda environment.

Description:

I have followed the steps to install DOT, but I'm facing this issue:

(base) ➜  dot git:(main) ✗ conda env create -f envs/environment-gpu.yaml
Collecting package metadata (repodata.json): done
Solving environment: done

Downloading and Extracting Packages

Preparing transaction: done
Verifying transaction: done
Executing transaction: done
Installing pip dependencies: | Ran pip subprocess with arguments:
['/Users/lfabbro/.miniconda/envs/dot/bin/python', '-m', 'pip', 'install', '-U', '-r', '/Users/lfabbro/Documents/code/dot/envs/condaenv.ywrul920.requirements.txt', '--exists-action=b']
Pip subprocess output:

Pip subprocess error:
ERROR: Could not find a version that satisfies the requirement onnxruntime-gpu==1.9.0 (from versions: none)
ERROR: No matching distribution found for onnxruntime-gpu==1.9.0

failed

CondaEnvException: Pip failed

Additional info:

(base) ➜  dot git:(main) ✗ conda --version
conda 23.3.1
(base) ➜  dot git:(main) ✗ python --version
Python 3.10.9
(base) ➜  dot git:(main) ✗ uname -a
Darwin xwing.local 22.3.0 Darwin Kernel Version 22.3.0: Mon Jan 30 20:38:37 PST 2023; root:xnu-8792.81.3~2/RELEASE_ARM64_T6000 arm64
(base) ➜  dot git:(main) ✗

SimSwap & SimSwap HQ are not working

🐛 Bug Report

SimSwap and SimswapHQ are not working.
FOMM and faceswapping are.

As I try to run SimSwap I get the error code below:

(dot) C:\Users\alber\Desktop\dot-main>dot -c ./configs/simswap.yaml --target 0 --source "./data" --use_gpu
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.parallel.data_parallel.DataParallel' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'models.ArcMarginModel' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'models.ResNet' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.conv.Conv2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.batchnorm.BatchNorm2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.activation.PReLU' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.pooling.MaxPool2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.container.Sequential' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'models.SEBlock' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.pooling.AdaptiveAvgPool2d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.linear.Linear' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.activation.Sigmoid' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.dropout.Dropout' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py:888: SourceChangeWarning: source code of class 'torch.nn.modules.batchnorm.BatchNorm1d' has changed. you can retrieve the original source code by accessing the object's source attribute or set `torch.nn.Module.dump_patches = True` and use the patch tool to revert the changes.
  warnings.warn(msg, SourceChangeWarning)
Traceback (most recent call last):
  File "C:\Users\alber\miniconda3\envs\dot\lib\runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Users\alber\miniconda3\envs\dot\lib\runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "C:\Users\alber\miniconda3\envs\dot\Scripts\dot.exe\__main__.py", line 7, in <module>
  File "C:\Users\alber\miniconda3\envs\dot\lib\site-packages\click\core.py", line 1130, in __call__
    return self.main(*args, **kwargs)
  File "C:\Users\alber\miniconda3\envs\dot\lib\site-packages\click\core.py", line 1055, in main
    rv = self.invoke(ctx)
  File "C:\Users\alber\miniconda3\envs\dot\lib\site-packages\click\core.py", line 1404, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "C:\Users\alber\miniconda3\envs\dot\lib\site-packages\click\core.py", line 760, in invoke
    return __callback(*args, **kwargs)
  File "C:\Users\alber\Desktop\dot-main\src\dot\__main__.py", line 206, in main
    run(
  File "C:\Users\alber\Desktop\dot-main\src\dot\__main__.py", line 67, in run
    _dot.generate(
  File "C:\Users\alber\Desktop\dot-main\src\dot\dot.py", line 131, in generate
    option.generate_from_camera(
  File "C:\Users\alber\Desktop\dot-main\src\dot\commons\model_option.py", line 184, in generate_from_camera
    self.create_model(opt_crop_size=opt_crop_size, **kwargs)
  File "C:\Users\alber\Desktop\dot-main\src\dot\simswap\option.py", line 100, in create_model
    self.model = create_model(
  File "C:\Users\alber\Desktop\dot-main\src\dot\simswap\models\models.py", line 31, in create_model
    model.initialize(
  File "C:\Users\alber\Desktop\dot-main\src\dot\simswap\fs_model.py", line 76, in initialize
    netArc_checkpoint = torch.load(arcface_model_path)
  File "C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py", line 815, in load
    return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
  File "C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\serialization.py", line 1043, in _legacy_load
    result = unpickler.load()
  File "C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\optim\sgd.py", line 30, in __setstate__
    super().__setstate__(state)
  File "C:\Users\alber\miniconda3\envs\dot\lib\site-packages\torch\optim\optimizer.py", line 214, in __setstate__
    self.defaults.setdefault('differentiable', False)
AttributeError: 'SGD' object has no attribute 'defaults'
[ WARN:[email protected]] global D:\a\opencv-python\opencv-python\opencv\modules\videoio\src\cap_msmf.cpp (539) `anonymous-namespace'::SourceReaderCB::~SourceReaderCB terminating async callback

Best regards

Fix `--save_folder` CLI Option

🐛 Bug Report

Description:

Actual Behavior:

See #12 (comment) for details.

Expected Behavior:

The output path using --save_folder should save the files in chosen folder, instead of the root directory

Integration with Hugging Face/Space with Gradio

During the dot installation phase, an error appears

I get an error when I follow the instructions, tell me what's wrong

Install dot

pip install -e .

(dot) C:\Users\Александр>pip install -e .

Obtaining file:///C:/Users/%D0%90%D0%BB%D0%B5%D0%BA%D1%81%D0%B0%D0%BD%D0%B4%D1%80
ERROR: file:///C:/Users/%D0%90%D0%BB%D0%B5%D0%BA%D1%81%D0%B0%D0%BD%D0%B4%D1%80 does not appear to be a Python project: neither 'setup.py' nor 'pyproject.toml' found.

Add FAQ section

windows installation

Can you make an UPDATED step-by-step detailed instructions for windows? At the moment, the steps you have provided do not result in a successful installation of dot on windows.
Please provide exact version of supported CUDA, conda, windows, and what should I type in console to get working pytorch.
I am constantly getting different errors during various methods of installations.
I even re-installed windows, I've tried many versions of conda, different command lines to get torch etc...
The worst thing is that if you did any of the steps wrong, it becomes clear only at the end. And so you have to try do all the NEW steps (using google) at half-random, including the command lines in terminal. And at the end you will get an new error and you have to do it all over and over again. At this time it's more like a lottery than an installation. Help me, please
It would be great if we had step-by-step tutorial with screenshots and exact versions of each component & command lines to get them.

How to enable super resolution

dot
-c ./configs/simswap.yaml
--target 0
--source "./data"
--show_fps
--gpen_type gpen_256

I used this command, but my GUP doesn't seem to be working and the video is very stuttering. I use a 2060 12G graphics card

Check if camera is available before loading models

If the selected camera input is not available, the CLI fails with RuntimeError: Cannot open camera. This happens after a long process of loading models etc. Instead, it should fail as fast as possible.

Can Dot work good on a laptop core5 with Nvidia GTX 750?

I don't have money to buy an expensive laptop I tried dot on a normal laptop with CPU alone it was super slow with lagging image head rotation. My question is Can Dot work good on a laptop core5 with Nvidia GTX 750?

(Degree of) Anonymity of the Deepfake Offensive Toolkit?

Would you be able to elaborate on the degree of anonymity when using your Deepfake Offensive Toolkit?

Description:

Thank you for your work, and for sharing it with the world! For some applications, a red-teamer may want to demonstrate the red-teamer was able to perform certain actions without being identified. This leads me to wonder what the degree of anonymity is when using the DOT. To be specific;

Does the DOI feed allow for reverse engineering Face Feature Points for face detection of the original user?
Would you be able to provide the average number of identifying bits that are shared per millisecond using DOT?
In extension to 2, would you perhaps be able to provide a graph with time in milliseconds seconds on the x-axis and the (average*) possible matches based on facial movement patterns on the y-axis? (Analogue to the number of identifying bits of information as demonstrated by Panopticlick 3.0.)

I assume some people's mimics are more easily identifiable/unique than others, yet taking this difference into account makes the analysis significantly more difficult.

Missing application icon while running

The application is running in ubuntu without an icon. We should use one.

Possible to convert into exe?

is it possible to convert dot into exe with all its libraries?

GFPGAN

I believe that incorporating GFPGAN v3 instead of GPEN can give significant image quality improvement

GPU tesla_a100

I have difficulty running dot with GPU tesla_a100, any suggestions?

My face is appearing in Cam and FOMM but the dot can't swap face in my cam and images from the data folder

My face is appearing in Cam and FOMM but the dot can't swap face in my cam and images from the data folder the commands are appearing on windows cmd for key controls to select from the data folder, what am I doing wrong I use CPU laptop? see the screenshot I have covered the camera for me not to show my face so to upload the image on here.

Faceswap on image with Simswap `--use_image` from run_without_camera.md gives incorrect output

The faceswap options Using Images from run_without_camera.md gives weird result. Resolution of face wont match the target image or a face is not detected in the image. Is this a known issue?

How to use OBS Virtual Camera as captured camera

❓ Ask a Question:

Description:

I want to use obs virtual camera as captured camera. I want to swap faces on picture due obs. How can I do it?

sensity-ai / dot Goto Github PK

dot's People

Contributors

Stargazers

Watchers

Forkers

dot's Issues

❓ Ask a Question:

Does the DOT have a watermark that can be used to determine the stream uses DOT?

Description:

Description:

❓ Ask a Question:

Description:

❓ Ask a Question:

Description:

🐛 Bug Report

Description:

Expected Behavior:

❓ Ask a Question:

Description:

🐛 Bug Report

Description:

✨ Feature Request

Description:

Acceptance Criteria:

❓ Ask a Question:

Description:

🐛 Bug Report

🐛 Bug Report

Description:

Actual Behavior:

Expected Behavior:

Install dot

Would you be able to elaborate on the degree of anonymity when using your Deepfake Offensive Toolkit?

Description:

❓ Ask a Question:

Description:

Recommend Projects

Recommend Topics

Recommend Org

Jobs