Published in Towards Data Science·Aug 11, 2021Adapting to changes of data by building MLOps pipeline in Vertex AIThis post shows how to build a machine learning pipeline for object detection tasks. The objective is to demonstrate how to realize MLOps to prepare data drift situations using Vertex AI’s AutoML and Cloud Function. — Motivation I have a three year old daughter, and I realized that her face is continuously changing so dramatically month by month. Google photo is already doing an excellent job to recognize faces by tracking changes in people’s faces. However, I figured that I could go even further like classifying pictures…Mlops13 min readMlops13 min read
Published in Google Developer Experts·May 11, 2021MLOps: Big Picture in GCPTwitter has become the most important platform for various people to get recent news since famous theorist, practitioners, etc. in your interest are continuously posting what they have found, built, and more. I believe I am not the only one who retweets whenever I encounter interesting tweets. I tell myself…Machine Learning14 min readMachine Learning14 min read
Published in Towards Data Science·Jul 26, 2018YOLOv2 to detect your own objects using DarkflowThe previous story before this one shows the most basic usage about Darkflow which is one of the implementation of YOLOv2 object detection model. This story introduces the basic steps for object detection on your custom dataset. As an example, I did it myself for soccer ball detection. In brief…Object Detection5 min readObject Detection5 min read
Published in Towards Data Science·Jul 2, 2018YOLOv2 object detection using DarkflowThis story introduces how object detection can be done. It will be helpful if you plan to build an application which benefits from object detection. YOLOv2 algorithm is used behind the scene. However, I have used open source implementation, “Darkflow”, so you don’t need to worry about the detail. You…Deep Learning4 min readDeep Learning4 min read
Published in Towards Data Science·Jun 12, 2018Transfer Learning in Tensorflow (VGG19 on CIFAR-10): Part 2This is the second part of the Transfer Learning in Tensorflow (VGG19 on CIFAR-10). The first part can be found here. The previous article has given descriptions about ‘Transfer Learning’, ‘Choice of Model’, ‘Choice of the Model Implementation’, ‘Know How to Create the Model’, and ‘Know About the Last Layer’. …Deep Learning4 min readDeep Learning4 min read
Published in Towards Data Science·Jun 7, 2018Transfer Learning in Tensorflow (VGG19 on CIFAR-10): Part 1Introduction The part2 of this story can be found here. This story presents how to train CIFAR-10 dataset with the pretrained VGG19 model. I will be using the VGG19 included in tensornets. The primary goals of this article are to understand the concept of transfer learning and what steps should be…Deep Learning6 min readDeep Learning6 min read
Published in Towards Data Science·May 2, 2018Seq2Seq model in TensorFlowIn this project, I am going to build language translation model called seq2seq model or encoder-decoder model in TensorFlow. The objective of the model is translating English sentences to French sentences. I am going to show the detailed steps, and they will answer to the questions likehow to define encoder…Machine Translation9 min readMachine Translation9 min read
Published in Towards Data Science·Apr 17, 2018CIFAR-10 Image Classification in TensorFlowIn this story, I am going to classify images from the CIFAR-10 dataset. This story covers preprocessing the image and training/prediction the convolutional neural networks model. Some of the code and description of this notebook is borrowed by this repo provided by Udacity, but this story provides richer descriptions. …Deep Learning15 min readDeep Learning15 min read
Mar 29, 2018EN-FR Machine Translation with Various RNN Models in Google CoLab (1)Within two parts of articles, I am going to implement deep learning model for English to French machine translation. The training data-set is borrowed from Udacity AI-ND (AI Nanodegree) program’s repository. Along the journey, I am going to use Google CoLab which gives cloud based jupyter notebook like environment. The…Google Colab8 min readGoogle Colab8 min read
Published in ITNEXT·Mar 26, 2018Comparable and Comparator in JAVAClick here to share this article on LinkedIn » We encounter lots of situations to create our own classes (custom classes) when building programs to solve particular problems. For instance, A class representing a news article to hold information while crawling news websites can be an example. No matter what…Programming5 min readProgramming5 min read
