spatial-transformer-network - A Tensorflow Implementation of Spatial Transformer Networks

  •        32

This is a Tensorflow implementation of Spatial Transformer Networks by Max Jaderberg, Karen Simonyan, Andrew Zisserman and Koray Kavukcuoglu, accompanying by two-part blog tutorial series. Spatial Transformer Networks (STN) is a differentiable module that can be inserted anywhere in ConvNet architecture to increase its geometric invariance. It effectively gives the network the ability to spatially transform feature maps at no extra data or supervision cost.

https://github.com/kevinzakka/spatial-transformer-network

Tags
Implementation
License
Platform

   




Related Projects

gvnn - gvnn: Geometric Vision with Neural Networks

  •    Lua

gvnn is primarily intended for self-supervised learning using low-level vision. It is inspired by the Spatial Transformer Networks (STN) paper that appeared in NIPS in 2015 and its open source code made available by Maxime Oquab. The code is self contained i.e. the original implementation of STN by Maxime is also within the repository. STs were mainly limited to applying only 2D transformations to the input. We added a new set of transformations often needed for manipulating data in 3D geometric computer vision. These include the 3D counterparts of what were used in original STN together with a lot more new transformations and different M-estimators.

transformer - A TensorFlow Implementation of the Transformer: Attention Is All You Need

  •    Python

I tried to implement the idea in Attention Is All You Need. They authors claimed that their model, the Transformer, outperformed the state-of-the-art one in machine translation with only attention, no CNNs, no RNNs. How cool it is! At the end of the paper, they promise they will make their code available soon, but apparently it is not so yet. I have two goals with this project. One is I wanted to have a full understanding of the paper. Often it's hard for me to have a good grasp before writing some code for it. Another is to share my code with people who are interested in this model before the official code is unveiled. I got a BLEU score of 17.14. (Recollect I trained with a small dataset, limited vocabulary) Some of the evaluation results are as follows. Details are available in the results folder.

attention_is_all_you_need - Transformer of "Attention Is All You Need" (Vaswani et al

  •    Jupyter

Chainer-based Python implementation of Transformer, an attention-based seq2seq model without convolution and recurrence. If you want to see the architecture, please see net.py. See "Attention Is All You Need", Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, arxiv, 2017.

SPP_net - SPP_net : Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

  •    Matlab

This is a re-implementation of the object detection algorithm described in the ECCV 2014 paper "Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition". This re-implementation should reproduce the object detection results reported in the paper up to some statistical variance. The models used in the paper are trained/fine-tuned using cuda-convnet, while the model attached with this code is trained/fine-tuned using Caffe, for the ease of code release. The implementation of image classification training/testing has not been included, but the network configuration files can be found directly in this code.


g2p-seq2seq - G2P with Tensorflow

  •    Python

The tool does Grapheme-to-Phoneme (G2P) conversion using transformer model from tensor2tensor toolkit [1]. A lot of approaches in sequence modeling and transduction problems use recurrent neural networks. But, transformer model architecture eschews recurrence and instead relies entirely on an attention mechanism to draw global dependencies between input and output [2]. This implementation is based on python TensorFlow, which allows an efficient training on both CPU and GPU.

PostGIS - Spatial and Geographic objects for PostgreSQL

  •    C

PostGIS is a spatial database extender for PostgreSQL object-relational database. It adds support for geographic objects allowing location queries to be run in SQL. PostGIS adds extra types (geometry, geography, raster and others) to the PostgreSQL database. It also adds functions, operators, and index enhancements that apply to these spatial types.

pytorch-openai-transformer-lm - A PyTorch implementation of OpenAI's finetuned transformer language model with a script to import the weights pre-trained by OpenAI

  •    Python

This is a PyTorch implementation of the TensorFlow code provided with OpenAI's paper "Improving Language Understanding by Generative Pre-Training" by Alec Radford, Karthik Narasimhan, Tim Salimans and Ilya Sutskever. This implementation comprises a script to load in the PyTorch model the weights pre-trained by the authors with the TensorFlow implementation.

JCS - Conflates spatial datasets

  •    Java

The JCS Conflation Suite is an API and set of interactive tools which perform conflation on spatial datasets.

class-transformer - Proper decorator-based transformation / serialization / deserialization of plain javascript objects to class constructors

  •    TypeScript

Its ES6 and Typescript era. Nowadays you are working with classes and constructor objects more then ever. Class-transformer allows you to transform plain object to some instance of class and versa. Also it allows to serialize / deserialize object based on criteria. This tool is super useful on both frontend and backend. Example how to use with angular 2 in plunker. Source code is available here.

MicroCity

  •    Lua

MicroCity is a framework for spatial analysis and simulation. It is lightweight, fast, portable, extendable and user friendly. Users can easily operate large GIS and Grid data and perform Spatial, Fractal, Network analysis and simulation.

Tensorflow-Tutorial - Tensorflow tutorial from basic to hard

  •    Python

In these tutorials, we will build our first Neural Network and try to build some advanced Neural Network architectures developed recent years. All methods mentioned below have their video and text tutorial in Chinese. Visit 莫烦 Python for more.

osmnx - OSMnx: Python for street networks

  •    Python

Retrieve, construct, analyze, and visualize street networks from OpenStreetMap: full overview. You can just as easily download and work with building footprints, elevation data, street bearings/orientations, and network routing.

SpatiaLite - Spatial SQL

  •    C

SpatiaLite is an open source library intended to extend the SQLite core to support fully fledged Spatial SQL capabilities. SQLite is intrinsically simple and lightweight, It is a single lightweight library implementing the full SQL engine. SpatiaLite is smoothly integrated into SQLite to provide a complete and powerful Spatial DBMS (mostly OGC-SFS compliant). Using SQLite + SpatiaLite you can effectively deploy an alternative open source Spatial DBMS roughly equivalent to PostgreSQL + PostGIS.

bi-att-flow - Bi-directional Attention Flow (BiDAF) network is a multi-stage hierarchical process that represents context at different levels of granularity and uses a bi-directional attention flow mechanism to achieve a query-aware context representation without early summarization

  •    Python

The model has ~2.5M parameters. The model was trained with NVidia Titan X (Pascal Architecture, 2016). The model requires at least 12GB of GPU RAM. If your GPU RAM is smaller than 12GB, you can either decrease batch size (performance might degrade), or you can use multi GPU (see below). The training converges at ~18k steps, and it took ~4s per step (i.e. ~20 hours). You can still omit them, but training will be much slower.

class-transformer - Proper decorator-based transformation / serialization / deserialization of plain javascript objects to class constructors

  •    TypeScript

Proper decorator-based transformation / serialization / deserialization of plain javascript objects to class constructors

MoTMoT

  •    Java

MoTMoT is a MOdel driven, Template based, MOdel Transformer, capable of generating model transformation code from visual transformation specifications.

pix2pix-tensorflow - TensorFlow implementation of "Image-to-Image Translation Using Conditional Adversarial Networks"

  •    Python

TensorFlow implementation of Image-to-Image Translation Using Conditional Adversarial Networks that learns a mapping from input images to output images. Note: To avoid the fast convergence of D (discriminator) network, G (generator) network is updated twice for each D network update, which differs from original paper but same as DCGAN-tensorflow, which this project based on.





We have large collection of open source products. Follow the tags from Tag Cloud >>


Open source products are scattered around the web. Please provide information about the open source projects you own / you use. Add Projects.