Use CNNs to generate images

cnn-vis Inspired by Google's recent Inceptionism blog post, cnn-vis is an open-source tool that lets you use convolutional neural networks to generate images. Here's an example: You can find many more examples, along with scri

Related Repos



harveyslash Deep-Steganography Tensorflow Implementation of Hiding Images in Plain Sight: Deep Steganography (unofficial) Steganography is the science of Hiding a message in another message. In this case, a Picture is hidden inside another
 

mxbi mlcrate A collection of handy python tools and helper functions, mainly for machine learning-related packages and Kaggle. The methods in this package aren't revolutionary, and most of them are very simple. They are largely bu
 

lukalabs Note on the top: the project is unmaintained. Transformer-based dialog models work better and we recommend using them instead of RNN-based CakeChat. See, for example https://github.com/microsoft/DialoGPT CakeChat: Emotional Ge
 

volotat ConGAN Continuous Adversarial Image Generator that can produce good images with relatively small number of examples and without any resolution dependencies. While training it creates small examples of generated images into 'imag
 

chenchongthu DeepCoNN This is our implementation for the paper: Lei Zheng, Vahid Noroozi, and Philip S Yu. 2017. Joint deep modeling of users and items using reviews for recommendation. In WSDM. ACM, 425-434. Two models: 1、DeepCoNN: This i
 

Randl MobileNetv2 in PyTorch An implementation of MobileNetv2 in PyTorch. MobileNetv2 is an efficient convolutional neural network architecture for mobile devices. For more information check the paper: Inverted Residuals and Linear Bot
 

shinseung428 Tensorflow implementation of AmbientGAN Tensorflow implementation of AmbientGAN on celebA dataset. The implicit generative model learns to recover true underlying distribution given only lossy measurement models. Netwo
 

analysiscenter RadIO RadIO is a framework for data science research of computed tomography (CT) imaging. Main features: Asynchronously load DICOM and MetaImage (mhd/raw) files Dump files to blosc to compress datasets and thus accelerate