Implementations of CNNs, RNNs, GANs, etc

Overview

Tensorflow Programs and Tutorials

This repository will contain Tensorflow tutorials on a lot of the most popular deep learning concepts. It'll also contain some experiments on cool papers that I read. Hopefully, the notebooks will be helpful to anyone reading!

  • CNN's with Noisy Labels - This notebook looks at a recent paper that discusses how convolutional neural networks that are trained on random labels (with some probability) are still able to acheive good accuracy on MNIST. I thought that the paper showed some eye-brow raising results, so I went ahead and tried it out for myself. It was pretty amazing to see that even when training a CNN with random labels 50% of the time, and the correct labels the other 50% of the time, the network was still able to get a 90+% accuracy.

  • Character Level RNN (Work in Progress) - This notebook shows you how to train a character level RNN in Tensorflow. The idea was inspired by Andrej Karpathy's famous blog post and was based on this Keras implementation. In this notebook, you'll learn more about what the model is doing, and how you can input your own dataset, and train a model to generate similar looking text.

  • Convolutional Neural Networks - This notebook goes through a simple convolutional neural network implementation in Tensorflow. The model is very similar to the own described in the Tensorflow docs. Hopefully this notebook can give you a better understanding of what is necessary to create and train your own CNNs. For a more conceptual view of CNNs, check out my introductory blog post on them.

  • Generative Adversarial Networks - This notebook goes through the creation of a generative adversarial network. GANs are one of the hottest topics in deep learning. From a high level, GANs are composed of two components, a generator and a discriminator. The discriminator has the task of determining whether a given image looks natural (ie, is an image from the dataset) or looks like it has been artificially created. The task of the generator is to create natural looking images that are similar to the original data distribution, images that look natural enough to fool the discriminator network.For more of a conceptual view of GANs, check out my blog post.

  • Linear and Logistic Regression - This notebook shows you how Tensorflow is not just a deep learning library, but is a library centered on numerical computation, which allows you to create classic machine learning models relatively easily. Linear regression and logistic regression are two of the most simple, yet useful models in all of machine learning.

  • Simple Neural Networks - This notebook shows you how to create simple 1 and 2 layer neural networks. We'll then see how these networks perform on MNIST, and look at the type of hyperparamters that affect a model's accuracy (network architecture, weight initialization, learning rate, etc)

  • Math in Tensorflow - This notebook introduces you to variables, constants, and placeholders in Tensorflow. It'll go into describing sessions, and showinng you how to perform typical mathematical operations and deal with large matrices.

  • Question Pair Classification with RNNs (Work in Progress) - This notebook looks at the newly released question pair dataset released by Quora a little earlier this year. It looks at the ways in which you can build a machine learning model to predict whether two sentences are duplicates of one another. Before running this notebook, it's very important to extract all the data. We'll run the following command to get our word vectors and training/testing matrices.

    tar -xvzf Data/Quora/QuoraData.tar.gz
  • SELU Nonlinearity - A recent paper titled "Self Normalizing Neural Networks" started getting a lot of buzz starting in June 2017. The main contribution of the paper was this new nonlinear activation function called a SELU (scaled exponential linear unit). We'll be looking at how this function performs in practice with simple neural nets and CNNs.

  • Sentiment Analysis with LSTMs - In this notebook, we'll be looking at how to apply deep learning techniques to the task of sentiment analysis. Sentiment analysis can be thought of as the exercise of taking a sentence, paragraph, document, or any piece of natural language, and determining whether that text's emotional tone is positive, negative or neutral. We'll look at why RNNs and LSTMs are the most popular choices for handling natural language processing tasks. Be sure to run the following commands to get our word vectors and training data.

    tar -xvzf Data/Sentiment/models.tar.gz
    tar -xvzf Data/Sentiment/training_data.tar.gz
  • Universal Approximation Theorem (Work in Progress) - The Universal Approximation Theorem states that any feed forward neural network with a single hidden layer can model any function. In this notebook, I'll go through a practical example of illustrating why this theorem works, and talk about what the implications are for when you're training your own neural networks. cough Overfitting cough

  • Learning to Model the XOR Function (Work in Progress) - XOR is one of the classic functions we see in machine learning theory textbooks. The significance is that we cannot fit a linear model to this function no matter how hard we try. In this notebook, you'll see proof of that, and you'll see how adding a simple hidden layer to the neural net can solve the problem.

Owner
Adit Deshpande
Engineering at Forward | UCLA CS '19
Adit Deshpande
StyleGAN-Human: A Data-Centric Odyssey of Human Generation

StyleGAN-Human: A Data-Centric Odyssey of Human Generation Abstract: Unconditional human image generation is an important task in vision and graphics,

stylegan-human 762 Jan 08, 2023
TensorFlow 2 AI/ML library wrapper for openFrameworks

ofxTensorFlow2 This is an openFrameworks addon for the TensorFlow 2 ML (Machine Learning) library

Center for Art and Media Karlsruhe 96 Dec 31, 2022
Job-Recommend-Competition - Vectorwise Interpretable Attentions for Multimodal Tabular Data

SiD - Simple Deep Model Vectorwise Interpretable Attentions for Multimodal Tabul

Jungwoo Park 40 Dec 22, 2022
unofficial pytorch implement of "Squareplus: A Softplus-Like Algebraic Rectifier"

SquarePlus (Pytorch implement) unofficial pytorch implement of "Squareplus: A Softplus-Like Algebraic Rectifier" SquarePlus Squareplus is a Softplus-L

SeeFun 3 Dec 29, 2021
计算机视觉中用到的注意力模块和其他即插即用模块PyTorch Implementation Collection of Attention Module and Plug&Play Module

PyTorch实现多种计算机视觉中网络设计中用到的Attention机制,还收集了一些即插即用模块。由于能力有限精力有限,可能很多模块并没有包括进来,有任何的建议或者改进,可以提交issue或者进行PR。

PJDong 599 Dec 23, 2022
A repo to show how to use custom dataset to train s2anet, and change backbone to resnext101

A repo to show how to use custom dataset to train s2anet, and change backbone to resnext101

jedibobo 3 Dec 28, 2022
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding

Vision Longformer This project provides the source code for the vision longformer paper. Multi-Scale Vision Longformer: A New Vision Transformer for H

Microsoft 209 Dec 30, 2022
"MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction" (CVPRW 2022) & (Winner of NTIRE 2022 Challenge on Spectral Reconstruction from RGB)

MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction (CVPRW 2022) Yuanhao Cai, Jing Lin, Zudi Lin, Haoqian Wang, Yulun Z

Yuanhao Cai 274 Jan 05, 2023
BEGAN in PyTorch

BEGAN in PyTorch This project is still in progress. If you are looking for the working code, use BEGAN-tensorflow. Requirements Python 2.7 Pillow tqdm

Taehoon Kim 260 Dec 07, 2022
Finetuner allows one to tune the weights of any deep neural network for better embeddings on search tasks

Finetuner allows one to tune the weights of any deep neural network for better embeddings on search tasks

Jina AI 794 Dec 31, 2022
PyTorch implementation of Deep HDR Imaging via A Non-Local Network (TIP 2020).

NHDRRNet-PyTorch This is the PyTorch implementation of Deep HDR Imaging via A Non-Local Network (TIP 2020). 0. Differences between Original Paper and

Yutong Zhang 1 Mar 01, 2022
Official code for the paper: Deep Graph Matching under Quadratic Constraint (CVPR 2021)

QC-DGM This is the official PyTorch implementation and models for our CVPR 2021 paper: Deep Graph Matching under Quadratic Constraint. It also contain

Quankai Gao 55 Nov 14, 2022
Unofficial PyTorch implementation of Fastformer based on paper "Fastformer: Additive Attention Can Be All You Need"."

Fastformer-PyTorch Unofficial PyTorch implementation of Fastformer based on paper Fastformer: Additive Attention Can Be All You Need. Usage : import t

Hong-Jia Chen 126 Dec 06, 2022
SegNet-Basic with Keras

SegNet-Basic: What is Segnet? Deep Convolutional Encoder-Decoder Architecture for Semantic Pixel-wise Image Segmentation Segnet = (Encoder + Decoder)

Yad Konrad 81 Jun 30, 2022
ChebLieNet, a spectral graph neural network turned equivariant by Riemannian geometry on Lie groups.

ChebLieNet: Invariant spectral graph NNs turned equivariant by Riemannian geometry on Lie groups Hugo Aguettaz, Erik J. Bekkers, Michaël Defferrard We

haguettaz 12 Dec 10, 2022
ML-Decoder: Scalable and Versatile Classification Head

ML-Decoder: Scalable and Versatile Classification Head Paper Official PyTorch Implementation Tal Ridnik, Gilad Sharir, Avi Ben-Cohen, Emanuel Ben-Baru

189 Jan 04, 2023
OpenDILab RL Kubernetes Custom Resource and Operator Lib

DI Orchestrator DI Orchestrator is designed to manage DI (Decision Intelligence) jobs using Kubernetes Custom Resource and Operator. Prerequisites A w

OpenDILab 205 Dec 29, 2022
Updated for TTS(CE) = Also Known as TTN V3. The code requires the first server to be 'ttn' protocol.

Updated Updated for TTS(CE) = Also Known as TTN V3. The code requires the first server to be 'ttn' protocol. Introduction This balenaCloud (previously

Remko 1 Oct 17, 2021
Save-restricted-v-3 - Save restricted content Bot For telegram

Save restricted content Bot Contact: Telegram A stable telegram bot to get restr

DEVANSH 11 Dec 21, 2022
Code accompanying the paper Shared Independent Component Analysis for Multi-subject Neuroimaging

ShICA Code accompanying the paper Shared Independent Component Analysis for Multi-subject Neuroimaging Install Move into the ShICA directory cd ShICA

8 Nov 07, 2022