All Projects → volotat → Continuous-Image-Autoencoder

volotat / Continuous-Image-Autoencoder

Licence: other
Deep learning image autoencoder that not depends on image resolution

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Continuous-Image-Autoencoder

Focal Frequency Loss
Focal Frequency Loss for Generative Models
Stars: ✭ 141 (+605%)
Mutual labels:  autoencoder, image-generation
Rnn Vae
Variational Autoencoder with Recurrent Neural Network based on Google DeepMind's "DRAW: A Recurrent Neural Network For Image Generation"
Stars: ✭ 39 (+95%)
Mutual labels:  autoencoder, image-generation
adversarial-autoencoder
Tensorflow 2.0 implementation of Adversarial Autoencoders
Stars: ✭ 17 (-15%)
Mutual labels:  autoencoder
GATE
The implementation of "Gated Attentive-Autoencoder for Content-Aware Recommendation"
Stars: ✭ 65 (+225%)
Mutual labels:  autoencoder
texturize
🤖🖌️ Generate photo-realistic textures based on source images. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
Stars: ✭ 495 (+2375%)
Mutual labels:  image-generation
EZyRB
Easy Reduced Basis method
Stars: ✭ 49 (+145%)
Mutual labels:  autoencoder
netflix-show-generator
A tool for generating Netflix show image
Stars: ✭ 18 (-10%)
Mutual labels:  image-generation
CycleGAN-Models
Models generated by CycleGAN
Stars: ✭ 42 (+110%)
Mutual labels:  image-generation
Dual-CNN-Models-for-Unsupervised-Monocular-Depth-Estimation
Dual CNN Models for Unsupervised Monocular Depth Estimation
Stars: ✭ 36 (+80%)
Mutual labels:  autoencoder
Image-Retrieval
Image retrieval program made in Tensorflow supporting VGG16, VGG19, InceptionV3 and InceptionV4 pretrained networks and own trained Convolutional autoencoder.
Stars: ✭ 56 (+180%)
Mutual labels:  autoencoder
probabilistic nlg
Tensorflow Implementation of Stochastic Wasserstein Autoencoder for Probabilistic Sentence Generation (NAACL 2019).
Stars: ✭ 28 (+40%)
Mutual labels:  autoencoder
tensorflow-mnist-AAE
Tensorflow implementation of adversarial auto-encoder for MNIST
Stars: ✭ 86 (+330%)
Mutual labels:  autoencoder
eForest
This is the official implementation for the paper 'AutoEncoder by Forest'
Stars: ✭ 71 (+255%)
Mutual labels:  autoencoder
Face-Landmarking
Real time face landmarking using decision trees and NN autoencoders
Stars: ✭ 73 (+265%)
Mutual labels:  autoencoder
vqgan-clip-app
Local image generation using VQGAN-CLIP or CLIP guided diffusion
Stars: ✭ 94 (+370%)
Mutual labels:  image-generation
sText2Image
Attribute-Guided Sketch-to-Image Generation
Stars: ✭ 67 (+235%)
Mutual labels:  image-generation
seq2seq-autoencoder
Theano implementation of Sequence-to-Sequence Autoencoder
Stars: ✭ 12 (-40%)
Mutual labels:  autoencoder
multiple-objects-gan
Implementation for "Generating Multiple Objects at Spatially Distinct Locations" (ICLR 2019)
Stars: ✭ 111 (+455%)
Mutual labels:  image-generation
dltf
Hands-on in-person workshop for Deep Learning with TensorFlow
Stars: ✭ 14 (-30%)
Mutual labels:  autoencoder
topological-autoencoders
Code for the paper "Topological Autoencoders" by Michael Moor, Max Horn, Bastian Rieck, and Karsten Borgwardt.
Stars: ✭ 82 (+310%)
Mutual labels:  autoencoder

Continuous-Image-Autoencoder

Deep learning image autoencoder that not depends on image resolution

How to use:

You should provide path to dataset file and number of examples in it to train new model, like so:

CIA.py -f cars.png -e 20

In dataset image there should be 10 pictures in row and as many rows as you want. By default each picture individually expect to have 200x200 resolution, but you can change it through "size" parameter in script if it's necessary. If you want to generate new images with pretrained model just add "--no-train" parameter.
Be patient while image generating, its might take quite a time.

Model structure:

model_structure

Results example:

  • Cars: 20 examples, 3D Latent space
    exmpls_cars
  • Faces: 30 examples, 5D Latent space
    exmpls_faces

You will find more examples in folders in "out.png" files.

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].