seranus / faceswap-notebooks Goto Github PK

Hello,

It seems the latest version of Faceswap requires python 3.7 .
Do you think it is possible to update the python version on a Google Colab instance ? Or should I be looking at getting a dedicated server to run this code ? What is your opinion on this matter ?

Thanks

I had to add
tensorflow==2.6.0
imgaug<0.2.7,>=0.2.5
to end of the /content/faceswap/_requirements_base.txt
and make it load /content/faceswap/requirements_nvidia.txt
before I could run the training.

This seems to fix the following dependency issues I had:
tensorflow 2.7.0 requires keras<2.8,>=2.7.0rc0, but you have keras 2.6.0 which is incompatible.
tensorflow 2.7.0 requires tensorflow-estimator<2.8,~=2.7.0rc0, but you have tensorflow-estimator 2.6.0 which is incompatible.
albumentations 0.1.12 requires imgaug<0.2.7,>=0.2.5, but you have imgaug 0.2.9 which is incompatible.

But now training bombs with
tensorflow.python.framework.errors_impl.UnknownError: 2 root error(s) found.

[[node villain/encoder/conv_128_0_conv2d/Conv2D_1 (defined at content/faceswap/plugins/train/trainer/_base.py:193) ]]
[[gradient_tape/LossWrapper_1/DSSIMObjective_2/Reshape_2/_30]]
(1) Unknown: 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 villain/encoder/conv_128_0_conv2d/Conv2D_1 (defined at content/faceswap/plugins/train/trainer/_base.py:193) ]]
0 successful operations.
0 derived errors ignored. [Op:__inference_train_function_14648]

Any hints on how to proceed to fixing this.

Hi,

I just tried running faceswap on google colab by myself, then tried again with your notebook, and got the same error twice:

ValueError: Tensor("conv2d_9/kernel:0", shape=(5, 5, 3, 128), dtype=float32_ref) must be from the same graph as Tensor("face:0", shape=(?, 64, 64, 3), dtype=float32).
06/08/2019 18:54:42 CRITICAL An unexpected crash has occurred. 

Can you reproduce that and any idea what's going on? I'm guessing the version of some colab packages is not good, but I'm not sure.

I use the notebook to train. Athough I follow the way to work， the preview always empty. The size of preview image which saved in root directory is empty.Help me please.