DeepFaceLab
the leading software for creating deepfakes |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
|
More than 95% of deepfake videos are created with DeepFaceLab. DeepFaceLab is used by such popular youtube channels as
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
What can I do using DeepFaceLab? |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Replace the face |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
De-age the face
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Replace the head
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Change the lip movement of politicians*
* also requires a skill in video editors such as Adobe After Effects or Davinci Resolve |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Deepfake native resolution progress |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
 Unfortunately, there is no "make everything ok" button in DeepFaceLab. You should spend time studying the workflow and growing your skills. A skill in programs such as AfterEffects or Davince Resolve is also desirable. |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Mini tutorial |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Releases
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Links
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
How I can help the project?
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Meme zone
|
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
| #deepfacelab #deepfakes #faceswap #face-swap #deep-learning #deeplearning #deep-neural-networks #deepface #deep-face-swap #fakeapp #fake-app #neural-networks #neural-nets #tensorflow #cuda #nvidia |
||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
DeepFaceLab is the leading software for creating deepfakes.
More than 95% of deepfake videos are created with DeepFaceLab. DeepFaceLab is used by such popular youtube channels as
Information
| Category: Python / Deep Learning |
| Watchers: 1.1k |
| Star: 43.6k |
| Fork: 9.8k |
| Last update: Dec 8, 2023 |
Resource links
548 Open
More issues
Closed
My gtx1060 6GB can run recycle only with 1 batch size.
what I got on first epochs, predictings just stuck on dots, is it normal?
any advices???
opened Dec 24, 2018 by iperov 51
Closed
Run Xseg train , it always stop this view and not update ,
Using 141 segmented samples. ============= Model Summary ============= == == == Model name: XSeg == == == == Current iteration: 1 == == == ==----------- Model Options -----------== == == == face_type: wf == == batch_size: 16 == == == ==------------ Running On -------------== == == == Device index: 0 == == Name: GeForce RTX 3090 == == VRAM: 24.00GB == == ==
Starting. Press "Enter" to stop training and save model. [19:07:51][#000002][3865ms][0.6886]
Driver: 457.51 CUDA 11.2 CUDNN 11.1
opened Dec 6, 2020 by PeiCinh 39
Closed
Error：nnlib.pynvml.NVMLError_Uninitialized: Uninitialized
when I extract face, the following error occurs. Can you give me some advice ?
mosheng@server:~/work2/project/shliang/2_DeepFaceLab_20190217$ python main.py extract --input-dir workspace/data_dst/ --output-dir test/ --detector mt --multi-gpu Running extractor.
Performing 1st pass... Running on GeForce GTX 1080 Ti #0. Running on GeForce GTX 1080 Ti #1. Exception while initialization: Traceback (most recent call last): File "/data2/work/project/shliang/2_DeepFaceLab_20190217/utils/SubprocessorBase.py", line 225, in subprocess fail_message = self.onClientInitialize(client_dict) File "/data2/work/project/shliang/2_DeepFaceLab_20190217/mainscripts/Extractor.py", line 269, in onClientInitialize device_config = nnlib.DeviceConfig ( cpu_only=self.cpu_only, force_gpu_idx=self.device_idx, allow_growth=True) File "/data2/work/project/shliang/2_DeepFaceLab_20190217/nnlib/devicelib.py", line 50, in init gpu_idx = force_gpu_idx if (force_gpu_idx >= 0 and devicelib.isValidDeviceIdx(force_gpu_idx)) else devicelib.getBestDeviceIdx() if not choose_worst_gpu else devicelib.getWorstDeviceIdx() File "/data2/work/project/shliang/2_DeepFaceLab_20190217/nnlib/devicelib.py", line 153, in isValidDeviceIdx return (idx < nvmlDeviceGetCount()) File "/data2/work/project/shliang/2_DeepFaceLab_20190217/nnlib/pynvml.py", line 799, in nvmlDeviceGetCount _nvmlCheckReturn(ret) File "/data2/work/project/shliang/2_DeepFaceLab_20190217/nnlib/pynvml.py", line 310, in _nvmlCheckReturn raise NVMLError(ret) nnlib.pynvml.NVMLError_Uninitialized: Uninitialized
opened Feb 18, 2019 by shliang0603 36
Closed
Get this when trying base settings. Just downloaded the Windows App, latest ver.
Model options: |== batch_size : 4 |== sort_by_yaw : False |== random_flip : True |== resolution : 128 |== face_type : f |== learn_mask : True |== archi : df |== ae_dims : 512 |== ed_ch_dims : 42 |== lighter_encoder : False |== multiscale_decoder : True |== pixel_loss : False |== face_style_power : 0.0 |== bg_style_power : 0.0 Running on: |== [0 : Tesla V100-SXM2-32GB]
Saving... Starting. Press "Enter" to stop training and save model. 2019-02-28 15:24:17.061889: I tensorflow/stream_executor/dso_loader.cc:152] successfully opened CUDA library cublas64_100.dll locally 2019-02-28 15:24:19.501210: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.524294: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.537892: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.550181: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.560771: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.572558: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.583995: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.597609: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.612175: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.623017: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.634949: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.646698: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.659910: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.672570: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.684968: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR 2019-02-28 15:24:19.695337: E tensorflow/stream_executor/cuda/cuda_dnn.cc:334] Could not create cudnn handle: CUDNN_STATUS_INTERNAL_ERROR Error: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[{{node truediv_1}}]] [[{{node Mean_6}}]] Traceback (most recent call last):
File "C:\Users\peter\Downloads\DeepFaceLabCUDA_internal\bin\DeepFaceLab\mainscripts\Trainer.py", line 75, in trainerThread loss_string = model.train_one_epoch() File "C:\Users\peterDownloads\DeepFaceLabCUDA_internal\bin\DeepFaceLab\models\ModelBase.py", line 309, in train_one_epoch losses = self.onTrainOneEpoch(sample, self.generator_list) File "C:\Users\peter\Downloads\DeepFaceLabCUDA_internal\bin\DeepFaceLab\models\Model_SAE\Model.py", line 385, in onTrainOneEpoch src_loss, dst_loss, = self.src_dst_train (feed) File "C:\Users\peter\Downloads\DeepFaceLabCUDA_internal\bin\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in call return self._call(inputs) File "C:\Users\peter\Downloads\DeepFaceLabCUDA_internal\bin\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call fetched = self._callable_fn(*array_vals) File "C:\Users\peter\Downloads\DeepFaceLabCUDA_internal\bin\lib\site-packages\tensorflow\python\client\session.py", line 1439, in call run_metadata_ptr) File "C:\Users\peter\Downloads\DeepFaceLabCUDA_internal\bin\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in exit c_api.TF_GetCode(self.status.status)) tensorflow.python.framework.errors_impl.UnknownError: Failed to get convolution algorithm. This is probably because cuDNN failed to initialize, so try looking to see if a warning log message was printed above. [[{{node truediv_1}}]] [[{{node Mean_6}}]] Done.
opened Feb 28, 2019 by Tesla32X 28
Closed
Expected behavior
i'm following Basic workflow video and data_dst and data_src extract faces (any bat) don't work
Actual behavior
all images found 0 faces detected
Steps to reproduce
-i'm using the default videos (iron man and chroma keyer guy) -i extract images from data_src and data_dst (this bats work normally) -i run the extract face bats, it found images but not the faces -if i use the MANUAL.bat it work and save some faces on aligned folder, but it cost a lot of time and lost a lot of faces -at this point i don't have enough images to proceed
Other relevant information
my rig: MOBO ASUS m5a97 EVO R2.0 fx8320 Gigabyte RX580 8gb vengeance 8gb 1600mhz ssd 120gb win 10 no overclock, all drivers up to date python last versions instaled no firewall interruptions
data_dst extract faces S3FD best GPU log (same result of others extract face bats):
Performing 1st pass...
Running on Advanced Micro Devices, Inc. Ellesmere (OpenCL).
Using plaidml.keras.backend backend.
INFO:plaidml:Opening device "opencl_amd_ellesmere.0"
0%| | 0/1538 [00:00<?, ?it/s]INFO:plaidml:Analyzing Ops: 38 of 254 operations complete
INFO:plaidml:Analyzing Ops: 89 of 254 operations complete
INFO:plaidml:Analyzing Ops: 147 of 254 operations complete
INFO:plaidml:Analyzing Ops: 47 of 254 operations complete
INFO:plaidml:Analyzing Ops: 114 of 254 operations complete
INFO:plaidml:Analyzing Ops: 147 of 254 operations complete
100%|##############################################################################| 1538/1538 [05:18<00:00, 4.82it/s]
Performing 2nd pass...
Running on Advanced Micro Devices, Inc. Ellesmere (OpenCL).
Using plaidml.keras.backend backend.
INFO:plaidml:Opening device "opencl_amd_ellesmere.0"
0%|2 | 5/1538 [00:00<00:52, 29.07it/s]INFO:plaidml:Analyzing Ops: 393 of 3771 operations complete
INFO:plaidml:Analyzing Ops: 830 of 3771 operations complete
INFO:plaidml:Analyzing Ops: 1312 of 3771 operations complete
INFO:plaidml:Analyzing Ops: 1783 of 3771 operations complete
INFO:plaidml:Analyzing Ops: 2273 of 3771 operations complete
INFO:plaidml:Analyzing Ops: 2745 of 3771 operations complete
INFO:plaidml:Analyzing Ops: 3228 of 3771 operations complete
INFO:plaidml:Analyzing Ops: 3698 of 3771 operations complete
INFO:plaidml:Analyzing Ops: 30 of 254 operations complete
INFO:plaidml:Analyzing Ops: 63 of 254 operations complete
INFO:plaidml:Analyzing Ops: 131 of 254 operations complete
Advanced Micro Devices, Inc. Ellesmere (OpenCL) doesnt response, terminating it.
0%|2 | 5/1538 [01:00<5:10:02, 12.13s/it]
Performing 3rd pass...
Running on CPU0.
Running on CPU1.
Running on CPU2.
Running on CPU3.
Running on CPU4.
Running on CPU5.
Running on CPU6.
Running on CPU7.
100%|####################################################################################| 5/5 [00:00<00:00, 5.12it/s]
-------------------------
Images found: 1538
Faces detected: 0
-------------------------
Done.
Pressione qualquer tecla para continuar. . .
ps: sorry my english XD
opened Aug 8, 2019 by Ozamatheus 26
Closed
cannot train the error is cannot import name 'normalize_data_format'
ubuntu 16.04
keras 2.1.6
opened Sep 8, 2018 by oracle9i88 26
Open
**Hi. I constantly encounter this error while training with Train SAEHD. Even if I lower the resolution or batch size, I continue to get errors. How can I solve the problem? Please help me.
My system:
11th Gen Intel(R) Core(TM) i7-11800H @ 2.30GHz RTX 3060 16GB RAM**
Initializing models: 80%|##################################################4 | 4/5 [00:11<00:02, 2.94s/it]
[163840,300] and type float
[[node src_dst_opt/vs_inter_B/dense1/weight_0/Initializer/Const (defined at C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py:38) ]]
Original stack trace for 'src_dst_opt/vs_inter_B/dense1/weight_0/Initializer/Const':
File "threading.py", line 884, in bootstrap
File "threading.py", line 916, in bootstrap_inner
File "threading.py", line 864, in run
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
debug=debug)
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\models\ModelBase.py", line 193, in init
self.on_initialize()
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 341, in on_initialize
self.src_dst_opt.initialize_variables (self.src_dst_saveable_weights, vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 38, in initialize_variables
vs = { v.name : tf.get_variable ( f'vs{v.name}'.replace(':',''), v.shape, dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v in trainable_weights }
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 38, in
Traceback (most recent call last): File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1375, in _do_call return fn(*args) File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1360, in _run_fn target_list, run_metadata) File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1453, in _call_tf_sessionrun run_metadata) tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor of shape [163840,300] and type float [[{{node src_dst_opt/vs_inter_B/dense1/weight_0/Initializer/Const}}]]
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread debug=debug) File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\models\ModelBase.py", line 193, in init self.on_initialize() File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 657, in on_initialize model.init_weights() File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\core\leras\layers\Saveable.py", line 106, in init_weights nn.init_weights(self.get_weights()) File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\core\leras\ops_init_.py", line 48, in init_weights nn.tf_sess.run (ops) File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 968, in run run_metadata_ptr) File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1191, in _run feed_dict_tensor, options, run_metadata) File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1369, in _do_run run_metadata) File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\python-3.6.8\lib\site-packages\tensorflow\python\client\session.py", line 1394, in _do_call raise type(e)(node_def, op, message) # pylint: disable=no-value-for-parameter tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor of shape [163840,300] and type float [[node src_dst_opt/vs_inter_B/dense1/weight_0/Initializer/Const (defined at C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py:38) ]]
Original stack trace for 'src_dst_opt/vs_inter_B/dense1/weight_0/Initializer/Const':
File "threading.py", line 884, in bootstrap
File "threading.py", line 916, in bootstrap_inner
File "threading.py", line 864, in run
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\mainscripts\Trainer.py", line 58, in trainerThread
debug=debug)
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\models\ModelBase.py", line 193, in init
self.on_initialize()
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\models\Model_SAEHD\Model.py", line 341, in on_initialize
self.src_dst_opt.initialize_variables (self.src_dst_saveable_weights, vars_on_cpu=optimizer_vars_on_cpu, lr_dropout_on_cpu=self.options['lr_dropout']=='cpu')
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 38, in initialize_variables
vs = { v.name : tf.get_variable ( f'vs{v.name}'.replace(':',''), v.shape, dtype=v.dtype, initializer=tf.initializers.constant(0.0), trainable=False) for v in trainable_weights }
File "C:\Users\Ersin\Desktop\DeepFaceLab\DeepFaceLab_NVIDIA_RTX3000_series_build_11_20_2021\DeepFaceLab_NVIDIA_RTX3000_series_internal\DeepFaceLab\core\leras\optimizers\AdaBelief.py", line 38, in
opened Nov 2, 2023 by ismailyugirov 0
Open
THIS IS NOT TECH SUPPORT FOR NEWBIE FAKERS POST ONLY ISSUES RELATED TO BUGS OR CODE
Expected behavior
extract face sets
Describe, in some detail, what you are trying to do and what the output is that you expect from the program.
Tt no longer recognizing any face in any videos including the default videos. iv tried a few different types of video but all fail.
Actual behavior it says images found :zero faces detected: zero. it give no callback to what went wrong. there is no info i can pass on unless some tells me how to do so please.
Describe, in some detail, what the program does instead. Be sure to include any error message or screenshots.
it say says images found zero, faces detected zero. even on default videos
Steps to reproduce
i dont know how it can be reproduced by others sorry, it was working fine then it stropped recognizing faces. Describe, in some detail, the steps you tried that resulted in the behavior described above. i tried to initiated a routine session, begining at ''clear work space'' the following the usual steps to tried to xtract images
Other relevant information
after several failed attemps i tried reinstalling gpu , and that failed so i tryed reinstalling fresh copy of deep face lab in another draddrive , but that copy also does the same thing and also wont recognize faces too.
-
Command lined used (if not specified in steps to reproduce): main.py ...
-
data scr faces extract bat
-
Operating system and version: Windows, macOS, Linux
-
win 10, build 10.0.1945 , 3090 gpu i.5 12600kf
-
Python version: 3.5, 3.6.4, ... (if you are not using prebuilt windows binary) 3.10
opened Oct 24, 2023 by 2037247S16618224E 0
Open
i'm trying to start bat file 2) extract images from video data_src. But see these errors
opened Oct 17, 2023 by LanaZet 1
Open
Hi All. Been using DFL now for a few years and made hundreds of videos with no issues at all until now...
Every feature and program works as it should within the DFL folder, image extraction/face extraction/training (xseg and SAEHD) all performing fine with no errors. My issue seems to be in the final stage of merging.
The last 3 attempts I have made to merge a video have thrown up this error during merging (see image). I tend to input some standard settings in the dos box for the merger settings and set it going keeping a finger on the arrow until I need to change some settings based on what I see in the interactive merger preview window - Ive always done it this way with no issues. I get some way through merging the whole project and all of a sudden it hits a particular point where it gives this error and continues to give the error for every frame afterwards whilst you are keeping your finger on the 'next' arrow trying to merge the remainder. The interactive merger window freezes and the green egg-timer symbol remains static in the top left corner of the screen.
I have tried just deleting everything and starting again - same issue. Can someone decipher the error code and give me an idea as to what might be happening? It's odd that its started happening all of a sudden... I've done this for years with zero issues. Ive tried updating my graphics and display drivers an that didnt help.
Look forward to any input.
Thanks
opened Oct 17, 2023 by Volvic1974 0
Open
After following the instructions and selecting a video file, the application stops working. It responds to inputs, but does not detect faces, swap them, or play the video.
OS: Windows 11 GPU: RX 7900 XTX 24Gb (latest drivers)
opened Oct 16, 2023 by f1am3d 0
Open
Expected behavior
Attempting to train XSeg by running 5.XSeg) train.bat after generating masks using the default generic XSeg model.
After the XSeg trainer has loaded samples, it should continue on to the filtering stage and then begin training.
Actual behavior
Instead of the trainer continuing after loading samples, it sits idle doing nothing infinitely like this:
There are no errors visibly being logged.
Steps to reproduce
- Run
5.XSeg) train.bat - Select NVIDIA GeForce RTX 2080 SUPER GPU
- Use whole face type
- Use a batch size of 8
- Do not enable pretraining mode
Other relevant information
OS: Windows 10 GPU: NVIDIA GeForce RTX 2080 SUPER CPU: AMD Ryzen 9 3900X RAM: 16GB
I've tried modifying virtual ram and changing drivers.
opened Oct 10, 2023 by arcvaw 0
Contents
Share this repo
Related Repos
837
Zarr Latest Release Package Status License Build Status Coverage Downloads Gitter Citation What is it? Zarr is a Python package providing an implement
317
Hydrosphere Mist Hydrosphere Mist is a serverless proxy for Spark cluster. Mist provides a new functional programming framework and deployment model f
2.5k
Distributed TensorFlow, PyTorch, Keras and BigDL on Apache Spark & Ray Analytics Zoo is an open source Big Data AI platform, and includes the followin
Cairo Black-Scholes Library Black-Scholes library implemented as a Cairo smart contract. All inputs, outputs, and internal calculations use 27-digit f
IC Logger This motoko library provides a module to help create an append-only logger actor. Usage You can use this library with the vessel package man
LeetCode_Solution LeetCode: https://leetcode.com/problemset/all/ # Title Difficulty Colab Code 1 Two Sum Easy 2 Add Two Numbers Medium 3 Longest Subst
ocrd_detectron2 OCR-D wrapper for detectron2 based segmentation models
Introduction Installation Usage OCR-D processor interface ocrd-detectron2-segm
134
LDAP Relay Scan A tool to check Domain Controllers for LDAP server protections regarding the relay of NTLM authentication. If you're interested in the
Fuzzware Fuzzware is a project for automated, self-configuring fuzzing of firmware images. The idea of this project is to configure the memory ranges
TWAM • Time Weighted Asset Mints A minting harness enabling time-weighted assets to determine minting prices. How it works Requirements: maxMintingAmo
ffcv ImageNet Training A minimal, single-file PyTorch ImageNet training script designed for hackability. Run train_imagenet.py to get... ...high accur
📖 เอกสารประกอบการสอน (PDF) 🔏 Blockchain & Smart Contract Blockchain เบื้องต้น Smart Contract & Solidity เบื้องต้น 💻 Programming เขียนโปรแกรมภาษา Ja
Omnivore: A Single Model for Many Visual Modalities [paper][website] OMNIVORE is a single vision model for many different visual modalities. It learns
pylox Python implementation of the Lox language from Robert Nystrom's Crafting Interpreters. https://craftinginterpreters.com. This only implements th
ParaGen ParaGen is a PyTorch deep learning framework for parallel sequence generation. Apart from sequence generation, ParaGen also enhances various N