woctezuma / stylegan2-projecting-images Goto Github PK
View Code? Open in Web Editor NEWProjecting images to latent space with StyleGAN2.
Home Page: https://colab.research.google.com/
License: MIT License
Projecting images to latent space with StyleGAN2.
Home Page: https://colab.research.google.com/
License: MIT License
How do I manipulate the seed of the initial face (and change it) used in projections?
I tested Expression transfer, but the effect is average. You mentioned "https://github.com/a312863063/seeprettyface-face_editor". I looked at the code, which contains png and. txt files randomly generated through the trained model, and then the properties can be modified, and the performance effect is still very good. If I take a selfie with one of my photos, how to deal with the property modification? Looking forward to your answer, thank you!
Was any efforts made to upgrade to stylegan2-ada?
can you implement faceshifter to swap identity between latent codes?
like this:
https://github.com/dayu1979/stylegan2-faceshifter
When I was training the '. NPY' file, '-- num steps' I used 50000 steps and' -- no tiled '. The training picture was close to the original picture. I started to carry out style transfer, The result is not good. I think it may be that the '-- num steps' in the training'. NPY 'file is not enough. Now I am continuing training with the goal of 300000' - num steps'. Once again, I would like to express my most sincere thanks!
NameError Traceback (most recent call last)
in ()
5 dlib_output_faces=faces,
6 face_no=face_no,
----> 7 fig_size=fig_size)
in display_landmarks(image_name, dlib_output_faces, face_no, fig_size)
31 face_parts = current_face.parts()
32
---> 33 preds = np.array([
34 [v.x, v.y]
35 for v in face_parts
NameError: name 'np' is not defined
python project_images.py datasets/aligned_images/ results/generated_images_tiled_10000steps/ --video True --video-mode 2
I want to get night pictures's ".npy"
Can you tell me your value of "--num-steps"?
Hello, I am trying to learn the face information of each frame in a video. For example, I have got the first frame of image through num steps 5000 times. How to use this.Npy to continue training the second frame picture? I look forward to your reply, thank you!
tying to project some images on coolab , with tf1.14.0 got this issue
File "project_images.py", line 103, in main _G, _D, Gs = pretrained_networks.load_networks(args.network_pkl) File "/content/stylegan2/pretrained_networks.py", line 76, in load_networks G, D, Gs = pickle.load(stream, encoding='latin1') File "/content/stylegan2/dnnlib/tflib/network.py", line 297, in __setstate__ self._init_graph() File "/content/stylegan2/dnnlib/tflib/network.py", line 154, in _init_graph out_expr = self._build_func(*self.input_templates, **build_kwargs) File "<string>", line 439, in G_synthesis File "<string>", line 392, in layer File "<string>", line 105, in modulated_conv2d_layer File "<string>", line 50, in apply_bias_act TypeError: fused_bias_act() got an unexpected keyword argument 'clamp'
root@25f892c013fc:/stylegan2# python project_images.py datasets/aligned_images/ results/generated_images_tiled/ --video True --video-mode 2
Loading networks from "./stylegan2-ffhq-config-f.pkl"...
Setting up TensorFlow plugin "fused_bias_act.cu": Preprocessing... Loading... Done.
Setting up TensorFlow plugin "upfirdn_2d.cu": Preprocessing... Loading... Done.
Traceback (most recent call last):
File "project_images.py", line 126, in
main()
File "project_images.py", line 110, in main
tiled = args.tiled
TypeError: init() got an unexpected keyword argument 'vgg16_pkl'
The face data file in "datasets / aligned"_ Images / "inside," results / generated_ images_ Tiled / "training export file," stylegan2-ffhq-config-f.pkl "and" vgg16 "_ zhang_ perceptual.pkl "Both files are local, using". / "to call, I am more confused about the cause of the current error, looking forward to your help me, thank you!
The bot created this issue to inform you that pyup.io has been set up on this repo.
Once you have closed it, the bot will open pull requests for updates as soon as they are available.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.