Loading...
Setting Faceswap backend to CPU
08/22/2022 21:39:19 INFO Log level set to: INFO
08/22/2022 21:39:22 INFO Output Directory: D:\face\1
08/22/2022 21:39:22 INFO Loading Detect from S3Fd plugin...
08/22/2022 21:39:22 INFO Downloading model: 's3fd_keras' from: https://github.com/deepfakes-models/faceswap-models/releases/download/v11.2/s3fd_keras_v2.zip
08/22/2022 21:41:24 INFO Extracting: 's3fd_keras'
08/22/2022 21:41:24 ERROR Unable to extract model file: File is not a zip file
Process exited.
Alternatively, you can manually download the model from: https://github.com/deepfakes-models/faceswap-models/releases/download/v11.2/s3fd_keras_v2.zip and unzip the contents > to: C:\Users\20602\faceswap\.fs_cache
Alternatively, you can manually download the model from: https://github.com/deepfakes-models/faceswap-models/releases/download/v11.2/s3fd_keras_v2.zip and unzip the contents > to: C:\Users\20602\faceswap\.fs_cache
I have correctly downloaded all the ZIP I need and unzipped it to the correct folder. Ten minutes after the extraction operation ran, the error occurred again.
Loading...
Setting Faceswap backend to CPU
08/23/2022 08:13:29 INFO Log level set to: INFO
08/23/2022 08:13:31 INFO Output Directory: D:\face\1
08/23/2022 08:13:31 INFO Loading Detect from S3Fd plugin...
08/23/2022 08:13:31 INFO Loading Align from Fan plugin...
08/23/2022 08:13:31 INFO Loading Mask from Components plugin...
08/23/2022 08:13:31 INFO Loading Mask from Extended plugin...
08/23/2022 08:13:31 INFO Starting, this may take a while...
08/23/2022 08:13:31 INFO Initializing S3FD (Detect)...
08/23/2022 08:13:32 INFO Initialized S3FD (Detect) with batchsize of 4
08/23/2022 08:18:52 INFO Initializing FAN (Align)...
08/23/2022 08:18:59 INFO Initialized FAN (Align) with batchsize of 12
08/23/2022 08:20:01 INFO Initializing Components (Mask)...
08/23/2022 08:20:01 INFO Initialized Components (Mask) with batchsize of 1
08/23/2022 08:20:01 INFO Initializing Extended (Mask)...
08/23/2022 08:20:01 INFO Initialized Extended (Mask) with batchsize of 1
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5 already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
Process exited.
Not seen that error before, so can't help I'm afraid.
However you do not have a GPU, so using S3FD and FAN are unlikely to work for you.
Try MTCNN as the detector.
Indeed, as you said, there is something wrong with my selection. Now I have finished extracting facial information, but I get an error again when I start training. I know I'm annoying with CPU, and I'm really sorry. Can you help me again?
Loading...
Setting Faceswap backend to CPU
08/23/2022 15:51:55 INFO Log level set to: INFO
08/23/2022 15:52:13 INFO Model A Directory: 'D:\face\1' (346 images)
08/23/2022 15:52:13 INFO Model B Directory: 'D:\face\2' (393 images)
08/23/2022 15:52:13 INFO Training data directory: D:\face\Model
08/23/2022 15:52:13 INFO ===================================================
08/23/2022 15:52:13 INFO Starting
08/23/2022 15:52:13 INFO ===================================================
08/23/2022 15:52:13 INFO Loading data, this may take a while...
08/23/2022 15:52:13 INFO Loading Model from Original plugin...
08/23/2022 15:52:14 INFO No existing state file found. Generating.
08/23/2022 15:52:14 INFO Storing Mixed Precision compatible layers. Please ignore any following warnings about using mixed precision.
08/23/2022 15:52:14 WARNING Mixed precision compatibility check (mixed_float16): WARNING
The dtype policy mixed_float16 may run slowly because this machine does not have a GPU. Only Nvidia GPUs with compute capability of at least 7.0 run quickly with mixed_float16.
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
08/23/2022 15:52:16 INFO Loading Trainer from Original plugin...
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5 already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
Process exited.
Not seen that error before, so can't help I'm afraid.
However you do not have a GPU, so using S3FD and FAN are unlikely to work for you.
Try MTCNN as the detector.
Indeed, as you said, there is something wrong with my selection. Now I have finished extracting facial information, but I get an error again when I start training. I know I'm annoying with CPU, and I'm really sorry. Can you help me again?
Loading...
Setting Faceswap backend to CPU
08/23/2022 15:51:55 INFO Log level set to: INFO
08/23/2022 15:52:13 INFO Model A Directory: 'D:\face\1' (346 images)
08/23/2022 15:52:13 INFO Model B Directory: 'D:\face\2' (393 images)
08/23/2022 15:52:13 INFO Training data directory: D:\face\Model
08/23/2022 15:52:13 INFO ===================================================
08/23/2022 15:52:13 INFO Starting
08/23/2022 15:52:13 INFO ===================================================
08/23/2022 15:52:13 INFO Loading data, this may take a while...
08/23/2022 15:52:13 INFO Loading Model from Original plugin...
08/23/2022 15:52:14 INFO No existing state file found. Generating.
08/23/2022 15:52:14 INFO Storing Mixed Precision compatible layers. Please ignore any following warnings about using mixed precision.
08/23/2022 15:52:14 WARNING Mixed precision compatibility check (mixed_float16): WARNING
The dtype policy mixed_float16 may run slowly because this machine does not have a GPU. Only Nvidia GPUs with compute capability of at least 7.0 run quickly with mixed_float16.
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
08/23/2022 15:52:16 INFO Loading Trainer from Original plugin...
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5 already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
Process exited.
This is the information for me to search for error message files in this computer. Which one should I delete? https://ibb.co/xzvX421
Not seen that error before, so can't help I'm afraid.
However you do not have a GPU, so using S3FD and FAN are unlikely to work for you.
Try MTCNN as the detector.
Indeed, as you said, there is something wrong with my selection. Now I have finished extracting facial information, but I get an error again when I start training. I know I'm annoying with CPU, and I'm really sorry. Can you help me again?
Loading...
Setting Faceswap backend to CPU
08/23/2022 15:51:55 INFO Log level set to: INFO
08/23/2022 15:52:13 INFO Model A Directory: 'D:\face\1' (346 images)
08/23/2022 15:52:13 INFO Model B Directory: 'D:\face\2' (393 images)
08/23/2022 15:52:13 INFO Training data directory: D:\face\Model
08/23/2022 15:52:13 INFO ===================================================
08/23/2022 15:52:13 INFO Starting
08/23/2022 15:52:13 INFO ===================================================
08/23/2022 15:52:13 INFO Loading data, this may take a while...
08/23/2022 15:52:13 INFO Loading Model from Original plugin...
08/23/2022 15:52:14 INFO No existing state file found. Generating.
08/23/2022 15:52:14 INFO Storing Mixed Precision compatible layers. Please ignore any following warnings about using mixed precision.
08/23/2022 15:52:14 WARNING Mixed precision compatibility check (mixed_float16): WARNING
The dtype policy mixed_float16 may run slowly because this machine does not have a GPU. Only Nvidia GPUs with compute capability of at least 7.0 run quickly with mixed_float16.
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
08/23/2022 15:52:16 INFO Loading Trainer from Original plugin...
OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5 already initialized.
OMP: Hint This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see http://www.intel.com/software/products/support/.
Process exited.
If you delete the DLL file in the bin folder, WARNING information is still displayed, but the training has started successfully