-
```py
self.erosion_kernel = None
self.blurSize = 8 # Default: 2
self.seamlessClone = True # Default: False
self.maskType = 'FaceHullAndRect' # Default: Rect
```
In my testing, this produces far …
-
Hi,
while reading the code of the decoder I noticed that you are using PixelShuffler instead of Transposed Conv to increase the spatial dimension of the output. This is done by mapping some of the 'c…
-
First check this out, original paper included. https://github.com/titu1994/Image-Super-Resolution
One of the big problems with faceswaping is close-ups because generated faces are 64x64 -if it's no…
-
I'm working on Windows 10.
I've installed Cuda 9, CuDNN 7 and TensorFlow 1.5, and everything has been working fine for a week now.
I think it's a bit faster, but I have not measured it.
Is there an…
-
## Expected behavior
When performing extraction using the following switches, facial images and alignment data are extracted for each image.
```python Libraries/faceswap/faceswap.py extract -i /…
-
I try using python3 faceswap.py -h in terminal
And I keep getting:
>
Call this program like this:
./face_recognition.py shape_predictor_5_face_landmarks.dat dlib_face_recognition_resnet_mode…
-
Can we include the 128x128 input/output size? to have better face resolution
I not a programmer, but found the latest dfaker and Faceswap-GAN have included it
please see below link
https://gith…
-
(sry bad english)
What we can deal with this problem: for example,
we have 1 face at 90 deg, and 10 faces from 0 to 10 deg
set batch size to 1, and we can see when trainer hit 90 deg image, tra…
-
![screenshot_5](https://user-images.githubusercontent.com/13344308/35908209-b87…
-
Face detection is still perfectible. suggest better alternatives if you have some idea
Clorr updated
6 years ago