the conversion between image and image is a typical application. Therefore, the technology is studied and operated.
The main reference code of this experiment is: Https://github.com/affinelayer/pix2pix-tensorflow
(1) First download data set, https://people.eecs.berkeley.edu/~tinghuiz/projects/pix2pix/datasets/, from this site can download a lot of classic application data set. In this paper, only facades i
(GitHub 3371 stars)
Link: https://github.com/PAIR-code/facets
Content reference to: Google Open source machine learning visualization tool Facets: Look at the data from a new angle
No.11
Style2paints:ai Comic Line coloring tool from Suzhou University (GitHub 3310 Stars)
Link: https://github.com/lllyasviel/style2paints
Content reference to: style2paints: Professional AI comic line automatic coloring tool
No.12
Tensor2tensor: Tool library for generalized sequence-sequence models, from Ryan
"adversarial generator-encoder Networks".
6.CycleGAN and Pix2pix in Pytorch
Https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix.git
The translation of diagrams to graphs, the famous Cyclegan and the Pytorch implementations of Pix2pix.
7.Weight normalized GAN
Https://github.com/stormraiser/GAN-weight-norm.git
The generative implementation of the effects of Batch and Weight normalization in adversarial N
or even unconditional.
That is to say, in the training process of this model, no other manual definition rules are added except for the confrontation rules, and no rules are used to force the generator's neural network to draw pictures according to the line, instead, we discovered through neural networks that, if we followed the line draft, we would be more likely to cheat the identification tool.
Similar models, such as pix2pix and CycleGAN, add l1
, show attend and tell, and more. At the end of the course, the text generation image of inverse problem is described, and the anti-neural network is introduced. After learning 567 courses, students should have a deep understanding of the application of convolutional neural networks and recurrent neural networks. ... the 9th chapter of the Anti-neural network This course is an explanation of the latest progress in deep learning--the anti-neural network. It mainly includes the idea of resisting t
expressed in English or French, a scene may be expressed in RGB images, gradient fields, edge graphs, a semantic tag graph, and so on. In the metaphor of automatic language translation, we define the automatic conversion of pictures to pictures to convert the possible representation of a scene into another when enough training sets have been given. content
A) objective
: Traditional pictures to the "transformation" of the picture usually requires the artificial construction of complex and reaso
L. Wasserstein gan[j]. ArXiv preprint arxiv:1701.07875 (Wgan) [PDF] Zhu J Y, Park T, Isola P, et al. unpaired image-to-image translation using Cycle-consistent adversarial networks[j]. ArXiv preprint arxiv:1703.10593 (Cyclegan) [PDF] Yi Z, Zhang H, Gong P T. dualgan:unsupervised Dual Learning for Im Age-to-image Translation[j]. ArXiv preprint arxiv:1704.02510 (Dualgan) [PDF] Isola P, Zhu J Y, Zhou T, et al image-to-image translation with con Ditional adversarial networks[j]. ArXiv preprint arxi
Google brain)
SOURCE Link: https://github.com/PAIR-code/facets
11.style2paints: Tools for quick coloring of lines with AI technology (GitHub 3310 stars)
SOURCE Link: https://github.com/lllyasviel/style2paints
12.tensor2tensor: A library for generalized sequence-sequence models-Google Analytics (GitHub 3087 stars, contributors are Google brain's Ryan Sepassi)
SOURCE Link: https://github.com/tensorflow/tensor2tensor
13. Image conversion based on Pytorch implementation (GitHub 2847 stars, contri
The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion;
products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the
content of the page makes you feel confusing, please write us an email, we will handle the problem
within 5 days after receiving your email.
If you find any instances of plagiarism from the community, please send an email to:
info-contact@alibabacloud.com
and provide relevant evidence. A staff member will contact you within 5 working days.