Brief Description: A Jittor implementation of Conditional GAN(CGAN).
Language Applied: Jittor
What is GAN?
A generative adversarial network (GAN) is a class of machine learning frameworks designed by Ian Goodfellow and his colleagues in June 2014.
Given a training set, this technique learns to generate new data with the same statistics as the training set. For example, a GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers, having many realistic characteristics. Though originally proposed as a form of generative model for unsupervised learning, GANs have also proved useful for semi-supervised learning, fully supervised learning, and reinforcement learning.[from Wiki]
What is Jittor?
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators. The whole framework and meta-operators are compiled just-in-time. A powerful op compiler and tuner are integrated into Jittor. It allowed us to generate high-performance code with specialized for your model. Jittor also contains a wealth of high-performance model libraries, including: image recognition, detection, segmentation, generation, differentiable rendering, geometric learning, reinforcement learning, etc. .[https://github.com/Jittor/jittor]
What is this project about?
This project aims to train models on popular handwriting dataset MNIST which has been included in Jittor and then turn a given string of numbers into handwriting form. Its output is a picture of that.
关于
This is one of my homeworks of lesson Computer Graphics. This is the link of the competition: https://www.educoder.net/competitions/index/Jittor-3.
CGAN_Jittor
Basic informations
What is GAN?
A generative adversarial network (GAN) is a class of machine learning frameworks designed by Ian Goodfellow and his colleagues in June 2014. Given a training set, this technique learns to generate new data with the same statistics as the training set. For example, a GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers, having many realistic characteristics. Though originally proposed as a form of generative model for unsupervised learning, GANs have also proved useful for semi-supervised learning, fully supervised learning, and reinforcement learning.[from Wiki]
What is Jittor?
Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators. The whole framework and meta-operators are compiled just-in-time. A powerful op compiler and tuner are integrated into Jittor. It allowed us to generate high-performance code with specialized for your model. Jittor also contains a wealth of high-performance model libraries, including: image recognition, detection, segmentation, generation, differentiable rendering, geometric learning, reinforcement learning, etc. .[https://github.com/Jittor/jittor]
What is this project about?
This project aims to train models on popular handwriting dataset MNIST which has been included in Jittor and then turn a given string of numbers into handwriting form. Its output is a picture of that.