top of page

What I've been through in a year / 私が1年間で経験してきたこと


My name is Takumi Owada, and I have been working at Orange Tech Lab as an intern.

While I was doing research as a graduate student in image processing, I had a chance to work with President Miyazaki, who is the president of the company, and I was able to intern with him. Over the past year, I have learned not only about Deep Learning, but also about quantum computers and many other things, which have given me a lot of strength for my future working life. I would like to talk about some of the experiences I gained.

At the beginning of my internship, I had only a sketch of the theory behind Deep Learning, and I had never actually run a network before, let alone understood what kind of networks were hot right now. As a beginner, I was introduced to a variety of object detectors, given detailed instructions on how to operate them, and provided with an environment where I could run them. My main activity was to improve the accuracy of Re-ID and tracking using DeepCC, a method of MTMCT. To achieve this goal, I conducted a survey of papers and open source research, but I had the most difficulty in conducting follow-up experiments. It was the end of the year when I finally got it working in vanilla, with unfamiliar MATLAB, and a storm of errors in installing the version specified gcc. Originally, I was going to apply the experimental data held in the Orange Tech Lab to DeepCC, but I had to give up halfway through the project due to a series of errors. It was very frustrating that it took so long to build the environment, but I am glad that I was able to deepen my knowledge of Deep Learning and error handling.

As part of my MTMCT research, I was also asked to accompany MTMCT to CVPR, one of the largest conferences in the world. It was my first international conference, my first time to go abroad, and it was a great experience for me to learn not only about the latest research on MTMCT, but also about the research I am doing as a graduate student. I would like to thank Dr. Tashiro and Dr. Nishida for taking care of me during this process.

During this internship, I had the opportunity to learn about quantum computers apart from Deep Learning. I was interested in what makes quantum computers different from the computers we are dealing with now and how they are implemented, so I participated in more than a dozen independent seminars that lasted about two hours. My impressions of the seminars were that they were completely different from what I had imagined from what I had seen and heard in the news, and that it was difficult for me to understand enough to explain to others, even though I had participated in the seminars many times. Through this experience, I was able to look at the news related to quantum computers with a certain degree of calmness. I would like to thank Mr. Asakura and Mr. A.Miyazaki for giving me the opportunity to learn about quantum computers, which will become a hot word in the future.

The Orange Tech Lab has given me a lot of things. I will continue to work in the IT industry in the future, so I would like to use the experience I gained to push forward. I would like to express my great appreciation to President Miyazaki for giving me the opportunity to be an intern, and to everyone involved in Orange Tech Lab for giving me the opportunity to grow.

Translated with (free version)


私は画像処理系の大学院生として研究を行っていた傍ら、社長である宮崎社長との間にご縁が生まれ、インターンをさせていただく運びになりました。この1年でDeep Learningの知識だけでなく、量子コンピュータやその他多くのことについて学ばせていただき、これからの私の社会人人生に多くの力を与えてくれました。これから私が得られた経験についてお話ししたいと思います。

インターン開始当初はDeep Learningに関して理論のさわりしか把握しておらず、どのようなネットワークが今アツいのか把握していることはおろか、実際に動作させたこともありませんでした。そのような初心者の私に、様々な物体検出器の紹介とその動作方法について丁寧に指導いただき、また動かせる環境を提供していただきました。私の主な活動はMTMCTの一手法であるDeepCCを用いてRe-IDとtrackingの精度向上を目指すことでした。この目的を達成するために論文調査やオープンソースの調査を行ったのですが、追実験を行うことに一番苦労しました。使い慣れないMATLAB、version指定されているgccをインストールするのにもエラーの嵐で、ようやくバニラで動いたのは年末でした。本来であれば、オレンジテクラボで保有している実験データをDeepCCに適用するまで行うはずでしたが、こちらもエラーの連続で道半ばにして断念することになりました。環境構築で手間取ったことは大変悔しいですが、Deep Learningに関する知識、エラー対処について理解を深めることが出来たのは良かったです。


このインターン期間中、Deep Learningとは別に量子コンピュータについて勉強する機会がありました。我々が今取り扱っているコンピュータと何が異なるのか、どのような実装をしているのかに興味があり、2時間ほどの自主ゼミに十数回参加しました。参加した感想としては、自分が今までニュースで見聞きして想像してたものとは全然異なるということと、何回もゼミに参加してる割には、人に説明できるほど理解できず難しかったということでした。この経験で、ある程度量子コンピュータ関連のニュースを冷静に見ることが出来ました。今後、ホットワードになっていく量子コンピュータについて知ることが出来た機会を下さった朝倉様、宮崎様に感謝申し上げます。


bottom of page