I’m starting a monthly update for Clojure MXNet. The goal is to share the progress and exciting things that are happening in the project and our community. Here’s some highlights for the month of March. Shipped Under the shipped heading, the 1.4.0 release of MXNet has been released, along with the Clojure MXNet Jars. There have been improvements to the JVM memory management and an Image API addition. You can see the full list of changes here ...
Object detection just landed in MXNet thanks to the work of contributors Kedar Bellare and Nicolas Modrzyk. Kedar ported over the infer package to Clojure, making inference and prediction much easier for users and Nicolas integrated in his Origami OpenCV library into the the examples to make the visualizations happen. We’ll walk through the main steps to use the infer object detection which include creating the detector with a model and then loading the image and running the inference on it. ...
It’s holiday time and that means parties and getting together with friends. Bringing a baked good or dessert to a gathering is a time honored tradition. But what if this year, you could take it to the next level? Everyone brings actual food. But with the help of Deep Learning, you can bring something completely different - you can bring the image of baked good! I’m not talking about just any old image that someone captured with a camera or created with a pen and paper. I’m talking about the computer itself creating. This image would be never before seen, totally unique, and crafted by the creative process of the machine. ...
This is an introduction to the high level Clojure API for deep learning library MXNet. The module API provides an intermediate and high-level interface for performing computation with neural networks in MXNet. To follow along with this documentation, you can use this namespace to with the needed requires: (ns docs.module (:require [clojure.java.io :as io] [clojure.java.shell :refer [sh]] [org.apache.clojure-mxnet.eval-metric :as eval-metric] [org.apache.clojure-mxnet.io :as mx-io] [org.apache.clojure-mxnet.module :as m] [org.apache.clojure-mxnet.symbol :as sym] [org.apache.clojure-mxnet.ndarray :as ndarray])) Prepare the Data In this example, we are going to use the MNIST data set. If you have cloned the MXNet repo and cd contrib/clojure-package, we can run some helper scripts to download the data for us. ...
I’m delighted to share the news that the Clojure package for MXNet has now joined the main Apache MXNet project. A big thank you to the efforts of everyone involved to make this possible. Having it as part of the main project is a great place for growth and collaboration that will benefit both MXNet and the Clojure community. Invitation to Join and Contribute The Clojure package has been brought in as a contrib clojure-package. It is still very new and will go through a period of feedback, stabilization, and improvement before it graduates out of contrib. ...
This is the beginning of a series of blog posts to get to know the Apache MXNet Deep Learning project and the new Clojure language binding clojure-package MXNet is a first class, modern deep learning library that AWS has officially picked as its chosen library. It supports multiple languages on a first class basis and is incubating as an Apache project. The motivation for creating a Clojure package is to be able to open the deep learning library to the Clojure ecosystem and build bridges for future development and innovation for the community. It provides all the needed tools including low level and high level apis, dynamic graphs, and things like GAN and natural language support. ...
I wrote a blog post a while back about using a Clojure machine learning library called Cortex to do the Kaggle Cats and Dogs classification challenge. I wanted to revisit it for a few reasons. The first one is that the Cortex library has progressed and improved considerably over the last year. It’s still not at version 1.0, but it my eyes, it’s really starting to shine. The second reason is that they recently published an example of using the RESNET50 model, (I’ll explain later on), to do fine-tuning or transfer learning. The third reason, is that there is a great new plugin for leiningen the supports using Jupyter notebooks with Clojure projects. These notebooks are a great way of doing walkthroughs and tutorials. ...
Update: Cortex has moved along since I first wrote this blog post, so if you are looking to run the examples, please go and clone the Cortex repo and look for the cats and dogs code in the examples directory. There is an awesome new Clojure-first machine learning library called Cortex that was open sourced recently. I’ve been exploring it lately and wanted to share my discoveries so far in this post. In our exploration, we are going to tackle one of the classic classification problems of the internet. How do you tell the difference between a cat and dog pic? ...
Clojure.spec is a new library for Clojure that enables you to write specifications for your program. In an earlier post, I showed off some of it’s power to generate test data from your specifications. It’s a pretty cool feature. Given some clojure.spec code, you can generate sample data for you based off of the specifications. But what if you could write a program that would generate your clojure.spec program based off of data so that you could generate more test data? ...
Clojure.spec is an exciting, new core library for Clojure. It enables pragmatic specifications for functions and brings a new level of robustness to building software in Clojure, along with unexpected side benefits. One of which is the ability to write specifications that generate Dr. Seuss inspired rhymes. In this blog post, we’ll take a tour of writing specifications for a clojure function, as well as the power of data generation. First, some inspirational words: ...