2024,江端さんの忘備録

「人に頼ることができて、はじめて一人前の社会人」という話は良くききますし、私もそれ自体に疑義を申し立てるつもりはありません。

It is often said that “only when you can rely on others can you become a full-fledged member of society,” I have no intention of questioning that statement.

最近、『ChatGPTを使うコツは、仕事を人に頼む時と同じ』ということが分かってきました。

でもね、

However, 

『自分でやれば1週間』

"If I do it by myself, it takes a week."

『他の人に一から教えると1ヶ月 + T.T(テクニカルトランスファー)時間』

"If I teach someone else from scratch, it will take a month + T.T. (technical transfer) time."

という場合、人に頼む、という選択肢があると思いますか? (しかも、納期とフォローも容赦なくやってくる)。

Do you think there is such an option as “asking someone to do it for me?” (And the deadlines and follow-up come relentlessly).

-----

実際に、私が編み出した、GISシミュレーション技術は、誰も継承してくれません。

No one will inherit the GIS simulation technology that I have developed.

いや、分かりますよ。だって、恐しく面倒で難しくて、そもそも、汎用性に欠ける属人性の高い他人の技術を、一体、どこの誰が学ぼうと思います? 私だって嫌ですよ。そんな技術の取得なんぞに時間を費やすのは。

Yes, I understand. Who in the world would want to learn someone else's technology that is so tedious, difficult, and, to begin with, lacking in versatility? Even I don't want to. I don't want to spend my time acquiring such technology.

-----

こんな感じで、高度に面倒くさい専門性の高い技術は、誰にも継承されず、失われていくんです。

Like this, highly tedious and specialized skills are not passed on to anyone and are lost.

エンジニアの世界には『人に頼む』という前提が『成立しない』仕事というものがあるんですよ。

In engineering, there are some jobs for which the premise of “asking others for help” is invalid.

でも、それは仕方がないことだと思っています。

I am sorry, but it cannot help that.

そういう技術は、私と一緒に墓の中に埋葬される運命です。

Such technology is destined to be buried in the grave with me.

ともあれ、まあ、私としては、「『人に頼むことができて、はじめて一人前の社会人』が成立しないフィールドがある」、ということだけは、皆さんに覚えておいて頂きたいのです。

Anyway, for my part, I would like everyone to remember that there are fields where it is not possible to be a “full-fledged member of society only when you can ask others for help.

2024,江端さんの忘備録

先日、皇室の方々の学問・研究について、個人的な戯言(ざれごと)を記載させていただきました。

The other day, I described my ramblings about the study and research of the people of the Imperial Family.

「そうだねえ。皇室の方が『戦術核の研究』されていた、なんてことになれば・・・うん、世界が動く」

嫁さんは『皇室の方々は、先端技術や戦争の研究はされるべきではない』と言っています。

My wife says, 'Imperial family members should not be studying advanced technology or warfare.

しかし「『学問の自由』は絶対である」と考える私としては、『それはダメだろう』と思うのです。

But as someone who believes that “academic freedom” is absolute, I think, 'That's not good enough.

-----

嫁さん:「皇室の方々が、そういう方向の研究には向かないようにする方がいい」

Wife: “It's better to ensure that the imperial family members don't turn to research in that direction.”

江端:「皇室の血脈が、そのような研究に向いていないことを、DNAレベルで調べる、ということを言っている?」

Ebata: “Are you saying that the imperial lineage is not suited for such a study at the DNA level?”

嫁さん:「いや、皇室の方が、そういう方向の研究には向かないように変えていく、ということ」

Wife: “No, I mean that the imperial family will make changes so that research will not be directed in that direction.”

江端:「(世論または政治的な同調)圧力で?」

Ebata: “(Public opinion or political sympathy) pressure?”

嫁さん:「いや、技術で」

Wife: “No, by technology.”

-----

嫁さんは、よく分かっていないようですが、『実に恐しいこと』を言っているのです。

My wife doesn't seem to understand what she is saying, but she is saying something 'horrifying.

その技術を深く考えていけば、究極的には『DNAレベルの遺伝操作』を、皇室関係者の方々に施す、という解に至ります。

If we consider the technology in depth, we will ultimately arrive at the “genetic manipulation at the DNA level” solution for people related to the Imperial Family.

これは「不敬」などというレベルを遥かに越える、人類の倫理・人道上の大問題です。

This is a major ethical and humanitarian issue for humanity that goes far beyond the level of “disrespect.

-----

まあ、こんな技術開発は不可能だ、ということは分かってはいるんですけど。

Well, I know that it is impossible to develop such technology.

DNAの構造(性格を操作する塩基配列制御)や、ちょっとした数学とITの知識(組み合わせ爆発)等の知識があれば、簡単に分かることです。

It's easy to figure out with some knowledge of DNA structure (sequence control to manipulate personality), a little math and IT knowledge (combinatorial explosion), etc.

そういうえば、そういうことを、大声で叫んでいた人、結構な数いたなぁ ―― 新型コロナのワクチン摂取の頃に。

Quite a few people were shouting that sort of thing out loud -- around the time of the new coronavirus vaccine intake.

もちろん、私は、『祈祷で感染を防ぐ』とか叫んでいたカルトと同様の取り扱いをしていましたが。

Of course, I handled them in the same way as the cults that were shouting, 'Prayer prevents infection' and so on.

(↑クリックでコラムに飛びます)

(↑click to jump to the column)

 

2024,江端さんの忘備録

我が家には玄関と庭に、24時間連続稼動のカメラを設置していて、動態状態を撮影し、それをログ(ラズパイ)に保管しています。(ちなみに使用しているカメラは私がジャンクとして拾ってきたものです)

We have cameras that run continuously 24 hours a day on our front porch and in our yard. They capture dynamic conditions and store them in a Raspberry Log. (By the way, the camera I am using is one I picked up as junk.)

(↑クリックすると、コラムに飛びます)

(↑click to jump to the column)

我が家も長女が家を出て、来年は次女も就職で家を出るかもしれません。

Our oldest daughter has left home, and our second daughter may leave next year for a job.

つまり、来年から私たち夫婦の生活となり、遠くない未来に一人暮しになるはずです。

This means that we will be living together next year and should be living alone in the not-too-distant future.

その前に対策をしておくべきか、と考えております。

I should take action before that happens.

仮に強盗に襲われたとしても、山のように証拠映像を残しておけるようにしておこうと思います。

If I were to be robbed, I would try to keep a mountain of video evidence.

部屋の中にカメラを設置するのは抵抗がありますので、階段の天井に設置しておくか、と思っています(PoEによって、恐しく配線がラクになりました)。

I am uncomfortable installing a camera in a room, so I am considering installing it in the staircase ceiling (PoE makes wiring more manageable, I'm afraid).

サーバも、ラズパイから、クラウド(Amazon LightSail)で管理する方向で考えています。

I am also considering managing the server from Raspi to the cloud (Amazon LightSail).

-----

カメラ、といえば、私、色々な因縁があります。

Speaking of cameras, I have a lot of history.

長女から、「ついに"権力の犬"に成り下がったか」という感じで、問い詰められました。

実は、この話、警察から、カメラ設置の依頼を受けたのです。

This story is about a request from the police to install cameras.

多分、私は自宅の回りにカメラを設置しまくっていたので、『この家は、カメラ設置に対する心理的抵抗が低い』と思われたと思います(まあ、実際にその通りなのですが)。

Perhaps because I had installed cameras all around my house, people thought, 'This house has low psychological resistance to camera installation' (well, that's true).

まあ、我が家から提供したものは「電源」と、カメラを配置するための庭の一部です。映像転送装置をチラっと見たのですが、基本的な構成は私が作っているものと同じで、「警察も予算が苦しいんだなぁ」と、思ったものです。

Well, what we provided from our home was the “power supply” and part of the yard to place the cameras. I had a glimpse of the video transmission system, and the basic configuration is the same as what I am building, and I thought to myself, “I guess the police are struggling with their budget too.

「この警察からの依頼は、合法なのか?」 とも思いましたが、深く考えるのを止めました。『面白そう』という興味の方が勝りました。

I thought, “Is this request from the police legitimate?” But I decided not to think about it too much. I was more interested in the 'fun' aspect of it.

おそらく、容疑者の毎日の行動パターンを把握するためだったのだろう、と推認しています。

I surmise that it was probably to understand the suspect's daily behavior patterns.

犯罪者の皆さんは、私のような「権力の犬(の犬)」が、少なからず存在することを覚悟して下さい ―― というか、『犯罪者なら定住なんぞするな』と説教したくなります。

Criminals, please be prepared that there are more than a few “dogs(s) of power” like me. Or, as I would like to preach, “If you are a criminal, don't settle down.”

-----

今、私の視界には、実験用の5台のカメラがあります。

I now have five experimental cameras in my field of view.

江端家システムのセキュリティを破って、カメラのロックを外せれれば、私の部屋の中は覗き放題です ―― 私の部屋の中を見て何か楽しいことがあるのかは、私には分かりませんが、少なくとも私に恥をかかせることはできるでしょう。

If you can break the security of the Ebata family system and unlock the cameras, you can peek inside my room all you want -- I don't know if there is anything fun in looking inside my room, but at least you can embarrass me.

-----

私は『自分の家だけは、強盗に入られない』などという都合のよいことは考えていません。

I don't think, 'Only my house is burglar-proof.

高齢者宅はいつだって、強盗のターゲットです。

Elderly homes are always a target for burglars.

ただ、たとえ殺害されようとも、「ただでは殺られん」という気合はあります。

However, even if I am murdered, I am determined not to be killed easily.

ちなみに、我が家では、カメラだけでなく、殴打する武器(バット)なども、直ぐに取り出せる状態になっています。

Incidentally, in our house, not only cameras but also weapons (bats) for beating are ready to be taken out immediately.

強盗に金庫を開けるように言われたら、私は素直に開けます ―― が、金庫の中には、犯人を殺傷できる武器も入っています。

If a robber asks me to open a safe, I open it honestly -- but the safe also contains a weapon that can kill or injure the criminal.

という訳で ―― この平和な時代にあっても、「武装」という概念を持ち続けているシニアが存在していることを、覚えておいて下さいね。

-----

親や子どもの見守りシステムから、自分のための見守りシステムへのシフト ―― これが、歳をとる、ということなのだなぁ、としみじみと実感しています。

I realize with sincerity that growing old means shifting from a system of looking out for parents and children to a system of looking out for oneself.

2024,江端さんの忘備録

(この話は、米国在住の2000-2002当時の話になることを、ご了承下さい)

(This story is from 2000-2002, when I lived in the U.S.)

マヨネーズは、アメリカ合衆国発祥の調味料ではありますが、アメリカのマネヨーズと日本のマヨネーズは、まったく違います。

Although mayonnaise is a condiment that originated in the United States, American mayonnaise and Japanese mayonnaise are pretty different.

はっきりいって、米国のマヨネーズは不味い。

To be clear, mayonnaise in the U.S. tastes terrible.

「味の嗜好が違う」という問題なのかもしれませんが、我が家では、米国のマヨネーズは食していませんでした。

Perhaps it's a matter of “different taste preferences,” but our family never ate U.S. mayonnaise.

甘さ:アメリカのマヨネーズは、日本のマヨネーズに比べて甘みが強い傾向がある。この甘さが、日本人の味覚に違和感を与えることがあるらしい。

Sweetness: American mayonnaise tends to be sweeter than Japanese mayonnaise. This sweetness is said to be sometimes uncomfortable to the Japanese palate.

酸味:日本のマヨネーズ(特にキユーピー製)は酢の酸味が強く、卵黄を多く使っているため、濃厚でクリーミーな味わいが特徴。一方、アメリカのマヨネーズは酸味が控えめで、ライトな味付けになっている

Acidity: Japanese mayonnaise (mainly made by Kewpie) has an intense sourness from vinegar and a thick, creamy taste due to the high use of egg yolks. On the other hand, American mayonnaise is less acidic and has a lighter flavor

食感:アメリカのマヨネーズは軽いテクスチャのものが多く、日本のマヨネーズのようなコクを期待すると物足りなさを感じる。

Texture: Many American mayonnaise products have a light texture, and if you expect the richness of Japanese mayonnaise, you will find it lacking.

ともあれ、当時、我が家では、マヨネーズは、嫁さんの実家から空輸して貰う貴重品でした。

Mayonnaise was a precious commodity in my family, flown in from my wife's parents' house.

-----

「ツナマヨネーズおにぎり」に人気があることからも、マヨネーズと御飯は、非常に相性が良いです。

Mayonnaise and rice go very well together, as evidenced by the popularity of “tuna mayonnaise onigiri.

「ツナマヨネーズおにぎり」が登場したのは、1990年代の初頭とされています。コンビニエンスストアの中でも特に セブン-イレブン が1991年に発売したのが最初と言われています。

Tuna mayonnaise onigiri” first appeared in the early 1990s. Among convenience stores, Seven-Eleven is said to have been the first to market the product in 1991.

当時、ツナ缶とマヨネーズという組み合わせは、すでに家庭料理やサンドイッチの具材として広く親しまれていましたが、発売当初、「ツナマヨネーズおにぎり」は忌避されていたと記憶しています。

At the time, the combination of canned tuna and mayonnaise was already widely popular in home cooking and sandwiches. Still, I remember that “tuna mayonnaise onigiri” was avoided when it was first released.

「マヨネーズとごはん」というのは、何かのタブーのような取り扱いだったように思います。

It seems to me that “mayonnaise and rice” was treated as a taboo.

もちろん、当時も「マヨネーズかけごはん」という食し方も確かにあったのですが、これは「きわもの」扱いされていたと思います。合えて言うなら「貧困状態を表わすメタファ」のような感じでしょうか。

Of course, there was also a way of eating “mayonnaise on rice” then, but I think it was treated as “something extreme. If I had to put it another way, I would say it was like a metaphor for poverty.

ただ、論理的に考えると「卵かけごはん」は日本人のソウルフードと言えるのに、「マヨネーズかけごはん」が忌避される、というのは、変な話ではあります。特に、「ツナマヨネーズおにぎり」が人気商品であることを鑑みると、さらに変だと思います。

However, logically speaking, it is strange that “Gohan with egg” can be called the soul food of the Japanese, while “Gohan with mayonnaise” is anathema. It is even stranger, especially because “tuna mayonnaise onigiri” is popular.

ちなみに、私は、マヨネーズかけごはんは「ダメ」。冷やし中華麺にマヨネーズは「必須」。唐揚げにマヨネーズは「可」です。手巻き寿司にマヨネーズは「OK」です。

By the way, I am a “no-no” for rice with mayonnaise. Mayonnaise on chilled Chinese noodles is a “must. Mayonnaise on fried chicken is “yes.” Mayonnaise on hand-rolled sushi is “OK.

ばっきりいって、一貫性がありません。

It is not consistent.

まあ、こういう説明不能な嗜好というものが、経験とか文化の一側面であると思います。

Well, these unexplainable preferences are an aspect of experience and culture.

それに理屈をつけることはできるのですが、あまり意義のない行為なのだとは思います。

We can reason with that, but I don't think it is a very significant act.

-----

以前、「私はカニバリズム(Cannibalism)もO.K.」てなことを書きましたが ―― 『人肉であっても、唐揚げにして、マヨネーズかければ、食べられるかにしれないな』とか思っています。

I once wrote, “I am OK with cannibalism,” but now I am thinking, “Even if it is human flesh, I can eat it if I deep-fry it and put mayonnaise on it.

ですから、仮に、私がどこかの国で、切り取った人間の肉で饗応されたとしても『ちゃんと食べ切る』自信があります。

2024,江端さんの技術メモ

Windowsのmsys2でもmsys64でもUbuntu22.04でもdockerでも、VMAF機能尽きのffmpegが上手くいかなくて困っています。

g:\home\ebata\vmafに

FROM ubuntu:22.04

# 必要なパッケージのインストール
RUN apt-get update && apt-get install -y \
    wget build-essential yasm pkg-config libtool autoconf automake cmake git \
    libx264-dev libx265-dev meson ninja-build nasm python3-pip && \
    apt-get clean

# VMAFのビルドとインストール
RUN git clone https://github.com/Netflix/vmaf.git /vmaf && \
    cd /vmaf/libvmaf && \
    meson setup build --buildtype release && \
    ninja -C build && \
    ninja -C build install && \
    ldconfig

# FFmpegのビルドとインストール
RUN git clone https://git.ffmpeg.org/ffmpeg.git /ffmpeg && \
    cd /ffmpeg && \
    ./configure --enable-gpl --enable-libx264 --enable-libx265 --enable-libvmaf && \
    make && make install

# 実行用のディレクトリを作成
RUN mkdir /workspace
WORKDIR /workspace

で、

docker build -t custom-ffmpeg-vmaf .

をやっても、かならず、こんなエラーが出てきて、これが、どうしても消せない。

G:\home\ebata\vmaf>docker run --rm -it -v G:\download:/workspace ffmpeg-vmaf ffmpeg -i /workspace/104014_1280x720.mp4 -i /workspace/104014_1280x720.mp4 -lavfi libvmaf="model=/workspace/vmaf_v0.6.1.json" -f null -
ffmpeg version N-118070-g17e4746687 Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 11 (Ubuntu 11.4.0-1ubuntu1~22.04)
configuration: --enable-gpl --enable-libx264 --enable-libx265 --enable-libvmaf
libavutil 59. 51.100 / 59. 51.100
libavcodec 61. 27.101 / 61. 27.101
libavformat 61. 9.101 / 61. 9.101
libavdevice 61. 4.100 / 61. 4.100
libavfilter 10. 6.101 / 10. 6.101
libswscale 8. 12.100 / 8. 12.100
libswresample 5. 4.100 / 5. 4.100
libpostproc 58. 4.100 / 58. 4.100
[Parsed_libvmaf_0 @ 0x55f5cc0b97c0] could not parse model config: /workspace/vmaf_v0.6.1.json
[AVFilterGraph @ 0x55f5cc0b91c0] Error initializing filters
Error : Invalid argument


2日間かけたのですが、疲れ果てたので、闘うのを止めました。

で、代替手段です。

■ブラウザのサービスを使う方法

VMAF on Browser

■VMAFを組み込んだffmpegのバイナリダウンロード
https://www.gyan.dev/ffmpeg/builds/
https://www.gyan.dev/ffmpeg/builds/#git-master-builds

ダウンロードして展開した場所の内部で(パスが通っていない)ffmpegを実行

G:\download\ffmpeg-2024-12-11-git-a518b5540d-full_build\bin>ffmpeg -i input.mp4 -i reference.mp4 -lavfi libvmaf -f null -

実行結果は以下の通り(欲しいのは以下の赤字のところだけ) # 今回は同じファイルを使って比較しただけ

G:\download\ffmpeg-2024-12-11-git-a518b5540d-full_build\bin>ffmpeg -i input.mp4 -i reference.mp4 -lavfi libvmaf -f null -
ffmpeg version 2024-12-11-git-a518b5540d-full_build-www.gyan.dev Copyright (c) 2000-2024 the FFmpeg developers
built with gcc 14.2.0 (Rev1, Built by MSYS2 project)
configuration: --enable-gpl --enable-version3 --enable-static --disable-w32threads --disable-autodetect --enable-fontconfig --enable-iconv --enable-gnutls --enable-libxml2 --enable-gmp --enable-bzlib --enable-lzma --enable-libsnappy --enable-zlib --enable-librist --enable-libsrt --enable-libssh --enable-libzmq --enable-avisynth --enable-libbluray --enable-libcaca --enable-sdl2 --enable-libaribb24 --enable-libaribcaption --enable-libdav1d --enable-libdavs2 --enable-libopenjpeg --enable-libquirc --enable-libuavs3d --enable-libxevd --enable-libzvbi --enable-libqrencode --enable-librav1e --enable-libsvtav1 --enable-libvvenc --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxavs2 --enable-libxeve --enable-libxvid --enable-libaom --enable-libjxl --enable-libvpx --enable-mediafoundation --enable-libass --enable-frei0r --enable-libfreetype --enable-libfribidi --enable-libharfbuzz --enable-liblensfun --enable-libvidstab --enable-libvmaf --enable-libzimg --enable-amf --enable-cuda-llvm --enable-cuvid --enable-dxva2 --enable-d3d11va --enable-d3d12va --enable-ffnvcodec --enable-libvpl --enable-nvdec --enable-nvenc --enable-vaapi --enable-libshaderc --enable-vulkan --enable-libplacebo --enable-opencl --enable-libcdio --enable-libgme --enable-libmodplug --enable-libopenmpt --enable-libopencore-amrwb --enable-libmp3lame --enable-libshine --enable-libtheora --enable-libtwolame --enable-libvo-amrwbenc --enable-libcodec2 --enable-libilbc --enable-libgsm --enable-liblc3 --enable-libopencore-amrnb --enable-libopus --enable-libspeex --enable-libvorbis --enable-ladspa --enable-libbs2b --enable-libflite --enable-libmysofa --enable-librubberband --enable-libsoxr --enable-chromaprint
libavutil 59. 49.100 / 59. 49.100
libavcodec 61. 26.100 / 61. 26.100
libavformat 61. 9.100 / 61. 9.100
libavdevice 61. 4.100 / 61. 4.100
libavfilter 10. 6.101 / 10. 6.101
libswscale 8. 12.100 / 8. 12.100
libswresample 5. 4.100 / 5. 4.100
libpostproc 58. 4.100 / 58. 4.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'input.mp4':
Metadata:
major_brand : mp42
minor_version : 0
compatible_brands: mp41isom
creation_time : 2024-02-14T12:54:44.000000Z
Duration: 00:00:30.46, start: 0.000000, bitrate: 2228 kb/s
Stream #0:0[0x1](und): Video: h264 (Constrained Baseline) (avc1 / 0x31637661), yuv420p(progressive), 722x444 [SAR 1:1 DAR 361:222], 2032 kb/s, 29.97 fps, 29.97 tbr, 29970 tbn (default)
Metadata:
creation_time : 2024-02-14T12:54:44.000000Z
handler_name : VideoHandler
vendor_id : [0][0][0][0]
encoder : AVC Coding
Stream #0:1[0x2](und): Audio: aac (LC) (mp4a / 0x6134706D), 48000 Hz, stereo, fltp, 195 kb/s (default)
Metadata:
creation_time : 2024-02-14T12:54:44.000000Z
handler_name : SoundHandler
vendor_id : [0][0][0][0]
Input #1, mov,mp4,m4a,3gp,3g2,mj2, from 'reference.mp4':
Metadata:
major_brand : mp42
minor_version : 0
compatible_brands: mp41isom
creation_time : 2024-02-14T12:54:44.000000Z
Duration: 00:00:30.46, start: 0.000000, bitrate: 2228 kb/s
Stream #1:0[0x1](und): Video: h264 (Constrained Baseline) (avc1 / 0x31637661), yuv420p(progressive), 722x444 [SAR 1:1 DAR 361:222], 2032 kb/s, 29.97 fps, 29.97 tbr, 29970 tbn (default)
Metadata:
creation_time : 2024-02-14T12:54:44.000000Z
handler_name : VideoHandler
vendor_id : [0][0][0][0]
encoder : AVC Coding
Stream #1:1[0x2](und): Audio: aac (LC) (mp4a / 0x6134706D), 48000 Hz, stereo, fltp, 195 kb/s (default)
Metadata:
creation_time : 2024-02-14T12:54:44.000000Z
handler_name : SoundHandler
vendor_id : [0][0][0][0]
Stream mapping:
Stream #0:0 (h264) -> libvmaf
Stream #1:0 (h264) -> libvmaf
libvmaf:default -> Stream #0:0 (wrapped_avframe)
Stream #0:1 -> #0:1 (aac (native) -> pcm_s16le (native))
Press [q] to stop, [?] for help
Output #0, null, to 'pipe:':
Metadata:
major_brand : mp42
minor_version : 0
compatible_brands: mp41isom
encoder : Lavf61.9.100
Stream #0:0: Video: wrapped_avframe, yuv420p(progressive), 722x444 [SAR 1:1 DAR 361:222], q=2-31, 200 kb/s, 29.97 fps, 29.97 tbn
Metadata:
encoder : Lavc61.26.100 wrapped_avframe
Stream #0:1(und): Audio: pcm_s16le, 48000 Hz, stereo, s16, 1536 kb/s (default)
Metadata:
encoder : Lavc61.26.100 pcm_s16le
creation_time : 2024-02-14T12:54:44.000000Z
handler_name : SoundHandler
vendor_id : [0][0][0][0]
[Parsed_libvmaf_0 @ 00000226c63e6640] VMAF score: 99.992967e=N/A speed=1.57x
[out#0/null @ 00000226c61d1ac0] video:392KiB audio:5616KiB subtitle:0KiB other streams:0KiB global headers:0KiB muxing overhead: unknown
frame= 913 fps= 47 q=-0.0 Lsize=N/A time=00:00:29.95 bitrate=N/A speed=1.55x

で、この評価の見方は以下の通りです。


1. [Parsed_libvmaf_0 @ 000001f6e343da40] VMAF score: 97.465053

  • [Parsed_libvmaf_0 @ ...]
    libvmafフィルタが処理を行ったことを示しています。
  • VMAF score: 97.465053
    最終的なVMAFスコアが97.465です。この値は、評価対象の動画(input.mp4)と参照動画(reference.mp4)の視覚的な品質の差異を数値化したものです。スコアは通常 0〜100 の範囲で表され、高いスコア(90以上)は非常に高品質であることを意味します。

2. e=N/A speed=0.299x

  • e=N/A
    現在のところ特定のエンコードステータスがありません(通常は気にしなくて大丈夫です)。
  • speed=0.299x
    処理速度を示しています。speed=0.299xは、処理がリアルタイムの29.9%の速度で進行したことを意味します。この低速さは、VMAF計算が非常に計算集約的であるためです。

3. [out#0/null @ 000001f6e1dc98c0] video:754KiB ... muxing overhead: unknown

  • video:754KiB
    出力された動画データの合計サイズが754KiBであることを示します。
  • audio:0KiB subtitle:0KiB other streams:0KiB
    音声、字幕、その他のストリームが含まれていないことを示します(VMAF評価ではこれらは不要)。
  • global headers:0KiB
    グローバルヘッダーのデータサイズも0KiBであることを示します。
  • muxing overhead: unknown
    出力ファイルのオーバーヘッド(余分なデータ量)が計算されていないことを示しています。nullフォーマットを使用しているため、通常は無視して問題ありません。

4. frame= 1755 fps= 18 q=-0.0 Lsize=N/A time=00:00:29.27 bitrate=N/A speed=0.299x

  • frame=1755
    VMAF計算の対象となったフレーム数です。1755フレームが処理されました。
  • fps=18
    平均で1秒間に18フレームが処理されたことを示します。
  • q=-0.0
    映像の品質パラメータで、VMAF評価では特に重要ではありません。
  • Lsize=N/A
    出力ファイルの総サイズ(nullフォーマットなので未計算)。
  • time=00:00:29.27
    処理された動画の総時間が29.27秒であることを示します。
  • bitrate=N/A
    ビットレートが計算されていないことを示します(評価中なので未計算)。
  • speed=0.299x
    処理速度がリアルタイムの約30%であることを再度示しています。

 

■VMAFについての評価方法や読み方については、以下が詳しいです。

【Netflixでも使ってる!】 映像品質評価ライブラリVMAFを使ったエンコードパラメータの決定方法の紹介

未分類

VMAF(Video Multi-Method Assessment Fusion)は、動画の品質を評価するための指標で、主にFFmpegなどのツールを使用してローカル環境で計算されます。しかし、オンラインでVMAFスコアを計算できるサービスも存在します。

例えば、「VMAF-on-browser」は、ブラウザ上でVMAFスコアを計算できるオンラインツールです。このツールを使用すると、ソフトウェアのインストールや設定を行わずに、手軽に動画の品質評価が可能です。

使用方法:

  1. ウェブサイトにアクセス:
  2. 動画ファイルのアップロード:
    • 「Reference Video」と「Distorted Video」の欄に、それぞれ元の動画ファイルと品質を評価したい動画ファイルを選択します。
    • 対応する動画形式は、mp4、webm、mkvなどです。
  3. VMAFモデルの選択:
    • 「VMAF Model」のドロップダウンメニューから、使用したいVMAFモデルを選択します。
    • 一般的にはデフォルトのモデルで問題ありませんが、特定の用途に応じて他のモデルを選択することも可能です。
  4. 計算の実行:
    • すべての設定が完了したら、「Compute VMAF」ボタンをクリックします。
    • 計算が開始され、完了するとVMAFスコアが表示されます。

注意点:

  • アップロードする動画ファイルのサイズや長さによって、計算時間が変動します。
  • ブラウザの性能やインターネット接続状況によっては、処理が遅くなる場合があります。
  • プライバシーや機密性の高い動画をアップロードする際は、セキュリティに十分注意してください。

このオンラインツールを活用することで、ローカル環境での設定やインストール作業を省略し、迅速に動画の品質評価を行うことができます。

 

 

2024,江端さんの忘備録

長女の結婚式の前に、散々私が言ってきたことがあります。

Before my eldest daughter's wedding, I had told her at length.

私:「『お父さん、お母さん。これまで育ててくれてありがとう。(以下省略)』という、あの例のスピーチ(または録音)やらをやらかしかしたりしたら、結婚式そのものを台無しにしてやるから、覚悟しておけよ」

Me: If you do anything like a speech or recording of “'Father and mother. Thank you for your .....", I'll ruin the wedding, so be prepared.

長女:「そんなに嫌?」

Eldest: “You don't like it that much?”

私:「虫酸が走るくらい、嫌」

Me: “I hate it so much it makes me sick.

長女:「なにが、そんなに嫌?」

Eldest: “Why, you don't like it that much?”

私:「『お涙頂戴』の陳腐な予定調和の役に、この私が組込まれるのが不快の極み。こんな役割は、私の人生の自己否定と言っても過言ではないレベルで、嫌」

Me: “I am extremely uncomfortable with the fact that I am being paired with a clichéd, scheduled role in a ‘sob story.’ I hate this kind of role on a level that is not too much to say that it is a self-denial of my life.”

長女:「ちなみに『台無し』って、どういう風に」

Eldest: “By the way, how do you mean ‘ruined’?”

私:「そうだなぁ。私なら、『不快な表情をして、会場の表門からから立ち去って、ドアを叩き閉める』とか、『娘の感謝とはこの程度のものでであったのかと知って、ガッカリしました』とかのスピーチをかます。判っていると思うが、私は"本気"だ」

Me: “Well, I guess. 'With an uncomfortable look, walk away from the front gate of the venue, and slam the door shut' and I will say, "I'm disappointed to learn that this is the extent of my daughter's gratitude,” or some such speech.".You know I'm serious.

------

で、昨日、長女から、こんなものが届いていました。

So, yesterday, I received this from my eldest daughter.

―― あいつ(長女)、よく、分かっているじゃないか

"-- She (the eldest daughter) knows exactly what I want."

と、とても嬉しかったです。

I was delighted.

感謝は、明解な内容を、言葉を伴って、当事者間で行われて、残されるべきです(ちなみに、この感状は、ラミネートでラッピングされています)。

Thanks should be left with a clear statement, accompanied by words, and made between the parties (by the way, this letter of sentiment is wrapped in laminate).

上記は、以下の日記のことだと思います。

I believe the above refers to the following diary entries.

「結婚とは不幸になること」でいいんです。

―― 大人は自由だ。大人は楽しい。大人はパラダイスだ

若者に「世界は広い」といっても無駄 ―― ということを分っていない大人が、多すぎるように思えます。

-----

まあ、卒業証書、英検認定証、国際学会の論文賞や奨励賞の賞状、ましてや社内表彰なんぞよりも、長女の「感状」は、

Well, rather than a diploma, an Eiken certificate, a certificate for a paper award, or an encouragement award from an international conference, much less an in-house prize, my eldest daughter's “letter of commendation” -- made me much happier and prouder.

―― はるかに嬉しく、誇らしい気持ちになった

"I felt much happier and prouder."

ということは、ちゃんと残して、伝えておきたい、と思いました。

I wanted to leave this message with her and let her know that I was very proud of her.

-----

感謝とは、言葉にして、表現して、残して、その人に伝えて、はじめて「感謝」になるのです。

Gratitude becomes “gratitude” only when it is put into words, expressed, left behind, and conveyed to that person.

日本の生産性がずっと低下しているのは、この「Let me say "Thank you"」ができていないからだと、私は本気で思っています。

2024,江端さんの忘備録

私は「キャリアアップ」という言葉の意味は分かっているつもりなのですが、その意義については、私は、多分、理解できないまま生涯を終えるだろう、という諦観があります。

I think I know what “career advancement” means, but I have resigned myself to the fact that I will probably spend the rest of my life not understanding its significance.

キャリアなるものの主な"機能"を調べてみたのですが、「自己実現の手段」「社会的役割の提供」「経済的基盤の確立」などが挙げられるようです。

I looked up the main “functions” of a career, and it seems that it is a “means of self-realization,” “provision of social roles,” and “establishment of an economic foundation.

また、キャリアの"効果"では、「スキルと知識の拡張」「自信の向上」「人間関係の拡大」「柔軟性の向上」などが出てきます。

Career “benefits” include “expanded skills and knowledge,” “increased confidence,” “expanded relationships,” and “increased flexibility.

上記の内容を眺めながら、

While looking at the above,

―― 私には、どの項目もヒットしないなぁ

"None of the items hit the mark for me."

と思っています。

I am thinking.

そもそも、私は、「キャリアアップ」を目的として働いた記憶がないのです。

To begin with, I don't recall ever working for “career advancement.”

だから『私の人生、この歳にして、この様(ざま)』か ―― うん、ちょっと悔しいけど、納得しました。

So, “My life, at my age, is like this”—yes, it's frustrating, but I'm convinced.

-----

私はエンジニアですので、私の財産は「技術力」ということなります。

I am an engineer, so my asset is my “technical skills.”

ですが、私の場合、この「技術力」は、別にキャリアアップを目指したものではなく、「目の前の課題解決の手段」として模索してきた結果です。

In my case, however, this “technical skill” is not something I have been aiming for career advancement, but is the result of my search for a “means of solving the issues at hand.

つまり、「その場しのぎの努力」であり、そこには長期的ビジョンがありません。

In other words, it is a “stopgap effort” with no long-term vision.

これを最も分かりやすく説明するのであれば、"あれ"ですよ、あれ ―― 「一夜漬け」。

The easiest way to explain this is “that,” that -- “cram for the test.”

「なんとかしろ」と命令されて、「なんとかしてきたもの」が、私の「技術力」です。

I was ordered to “do something about it,” and “what I have managed to do” is my “technical ability.

そこには、「向上しよう」とか「出世しよう」とか、そういう前向きな志(こころざし)は、1mmもなかったですね(断言)。

There was not a single millimeter of positive aspiration to “improve,” “get ahead,” or anything like that (I assure you).

あえて言うなら「最大限、手を抜く為に、膨大な時間を費して勉強をして、システムやプログラムを作ってきた」という感じです。

I dare say that I have spent an enormous amount of time studying and creating systems and programs to cut corners to the greatest extent possible.

こういう振舞いは、コスト的には、全然ダメなのかもしれません。

This kind of behavior may not be cost-effective at all.

でも、「本当にそうかな?」 とも思いましたので、ChatGPTと会話してみました。

But I also wondered, “Is it?” I also wondered, so I had a conversation with ChatGPT.

-----

『キャリアアップをするコストとしないコストの比較をしてみてください。コストとはここでは時間、労力、金銭を、数値で語って下さい』

キャリアアップをする場合としない場合のコスト比較を具体的に示すため、以下の仮定を設定して試算します:

  1. 条件設定
    • 年齢:30歳、年収400万円の会社員
    • 勤務時間:年間2000時間(1日8時間・250日)
    • キャリアアップの具体的な取り組み:資格取得のための学習と転職
    • キャリアアップ後の年収:500万円
    • キャリアアップしない場合の年収:昇給率1%/年
  2. キャリアアップのコスト試算
    • 時間
      • 資格取得の学習時間:300時間(年間約6時間/週)
      • 転職活動:50時間(企業リサーチ、面接準備、移動など)
      • 合計:350時間/年
    • 労力
      • 学習負荷:業務外の勉強時間を確保する精神的・体力的コスト
      • 転職負荷:不安定な状態での精神的ストレス(数値化困難)
    • 金銭
      • 資格取得費用:20万円(講座費用、試験代など)
      • 転職に伴う一時的な収入減:30万円(転職準備中の失業期間の1ヶ月分)
      • 合計:50万円
  3. キャリアアップしない場合のコスト試算
    • 時間
      • キャリアアップ準備をしない分、年間350時間が自由時間として確保可能
    • 労力
      • 業務以外の負担なし(学習や転職活動がない)
    • 金銭
      • 年収の伸び率:1%/年(年収400万円懼10年後440万円)
  4. 比較表(10年後の累積)
項目 キャリアアップする場合 キャリアアップしない場合 差額
累積収入 約5000万円 約4400万円 +600万円
学習・転職時間 350時間・2年 = 700時間 0時間 -700時間
金銭コスト(資格・転職) 50万円 0円 -50万円
自由時間 約17200時間(2000-350・2) 約20000時間 -2800時間

分析

  • キャリアアップの金銭的リターン
    10年後の累積収入差は+600万円。ただし、初期費用の50万円を差し引いても、結果的には利益が大きい。
  • 時間コストの比較
    キャリアアップの学習や転職活動に費やす700時間を考慮すると、年間自由時間が減少。
  • 選択のポイント
    • キャリアアップは金銭的なリターンが大きいが、時間の余裕がなくなる。
    • 自由時間や精神的負担を優先する場合、キャリアアップしない方が得策。

詳細な計算や条件の調整も可能ですので、必要であればご指定ください。

To compare the costs of pursuing career advancement versus not pursuing it, the following assumptions and calculations are provided:


1. Assumptions

  • Age: 30 years old, current annual salary of ▼4,000,000
  • Working hours: 2,000 hours/year (8 hours/day ・ 250 days)
  • Career advancement activities: Studying for certification and job-hopping
  • Post-advancement annual salary: ▼5,000,000
  • Annual salary growth without advancement: 1%/year

2. Career Advancement Cost Estimates

  • Time
    • Study time for certification: 300 hours (approx. 6 hours/week for a year)
    • Job-hunting: 50 hours (researching companies, preparing for interviews, travel, etc.)
    • Total: 350 hours/year
  • Effort
    • Study burden: Physical and mental effort required to allocate study time outside of work
    • Job-hunting burden: Stress from job instability during the transition (hard to quantify)
  • Money
    • Certification costs: ▼200,000 (course fees, exam fees, etc.)
    • Temporary income loss during job transition: ▼300,000 (1 month of unemployment)
    • Total: ▼500,000

3. Costs of Not Pursuing Career Advancement

  • Time
    • No preparation for career advancement, freeing 350 hours/year for personal use
  • Effort
    • No additional workload outside regular job (no studying or job-hunting)
  • Money
    • Annual salary growth: 1%/year (▼4,000,000 懼 ▼4,400,000 after 10 years)

4. Comparison Table (Cumulative Over 10 Years)

Item Career Advancement No Career Advancement Difference
Cumulative Income Approx. ▼50,000,000 Approx. ▼44,000,000 +▼6,000,000
Study & Job-Hunting Time 350 hours ・ 2 years = 700 hours 0 hours -700 hours
Monetary Costs ▼500,000 ▼0 -▼500,000
Free Time Approx. 17,200 hours Approx. 20,000 hours -2,800 hours

5. Analysis

  • Monetary Return on Career Advancement
    The cumulative income difference after 10 years is +▼6,000,000. Even after deducting initial costs of ▼500,000, the financial gain is significant.
  • Comparison of Time Costs
    The time spent studying and job-hunting amounts to 700 hours, reducing annual free time.
  • Key Considerations
    • Career advancement offers substantial monetary returns but reduces available free time.
    • Not pursuing career advancement may be preferable if you prioritize free time and reduce mental burdens.

Further adjustments to the calculations or assumptions can be made upon request.

----

ほらね。

You see?

このChatGPTの回答は、ちょっと単純に過ぎますが、キャリアアップが、かならずしもコスト的にプラスになっているは限らない一例だとは思うのです。

This ChatGPT answer is a bit too simplistic, but it exemplifies how career advancement does not always cost positively.

-----

私は、キャリアップのためには時間を使わなかったけど、技術力の為には、膨大(というか莫大)な時間を費してきました。

I didn't spend much time on career advancement, but I have spent an enormous (and I mean huge) amount of time on technical skills.

この理由を問われると、正直答えには窮するんですが ―― 多分、「ある技術でモノを動かせるようにする = (ゲームの)ラスボスを倒す」と同じ感覚なのだと思います。

I am at a loss to answer why this is so -- perhaps it is the same feeling as “making things move with a certain technology = defeating the last boss (of a game).”

ただ「ラスボスを倒した"後"」も、取得した必殺技を使い続けることができる分、「技術には『若干トク』があるんじゃないかな」と思い込むことにしています。

However, I have decided to assume that there is a “slight advantage” to the technique because I can continue to use the special moves that I have acquired “after” defeating the last boss.

2024,江端さんの忘備録

皇族の皆様が行われている研究については、ニュースなどで興味深く拝見させて頂いております。

I have been watching the research conducted by the royal family in the news with great interest.

これまでの天皇陛下や皇室の方々が取り組んでこられた研究は、自然科学(植物や生物)関係が多いように思います。

It seems that most of the research that His Majesty the Emperor and members of the Imperial Family have engaged in so far has been related to the natural sciences (plants and organisms).

で、私が気にしているのは『その研究を"楽しく"行なわれているか?』ということです。

And my concern is, “Do they conduct the research with enjoying?

-----

私:「興味のある研究をやられているならいいんだけど、『皇族』を理由で、研究内容にある種の圧力が発生していないかを心配しているんだ」

Me: “I hope they are doing the research they are interested in, but I am concerned that they are not creating some sort of pressure on the content of their research because of the ‘royal family.’”

嫁さん:「どういうこと?」

Wife: “What do you mean?”

私:「例えば、ご本人が、"遺伝子工学"、"量子力学(量子コンピュータを含む)"、"核融合"、"同性生殖技術"、"廃炉(デブリ除去を含む)技術"、"戦術核"とかの研究を、ご希望されているにもかかわらず、それをやらせてもらえない、ということはないだろうか、と、まあ、余計な心配をしているんだよ」

Me: “For example, even though they would like to research ‘genetic engineering,’ ‘quantum mechanics (including quantum computers),’ ‘nuclear fusion,’ ‘same-sex reproduction technology,’ ‘decommissioning (including debris removal) technology,’ ‘tactical nuclear weapons,’ etc., I wonder if they would not be allowed to do so, well... I'm just worried about something else.”

嫁さん:「それはなんというか、凄い"パワーワード"だね」

Wife: “They are kind of great ‘power words.’

私:「私は、天皇制の意義について私なりに理解したと思っているし、陛下を含めた皇室の方々の日々のご公務について、本当に感謝している。だからこそ、私たちのために、皇室の方々が『何かを諦めなければならない』のであれば、それは"よくないこと"だと思う」

Me: “I believe that I have understood the significance of the Emperor System in my way, and I am truly grateful for the daily official duties of the members of the Imperial Family, including His Majesty the Emperor. Therefore, if the members of the Imperial Family have to “give up something” for our sake, I think it is a “bad thing.

嫁さん:「で?」

Wife: “So?”

私:「とは言え、日本の皇室の方々が行っている研究分野は、国内のみならず、海外にも反響を与えるだろうとは思う。その研究内容は、国内の公的研究投資額への影響も必至だ」

Me: “Nevertheless, I believe that the field of research being conducted by the Japanese Imperial Family will have repercussions domestically and abroad. And that research will inevitably impact the amount of public research investment in Japan.”

嫁さん:「そうだねえ。皇室の方が『戦術核の研究』されていた、なんてことになれば・・・うん、世界が動く」

Wife: “Yes, that's right. If it comes out that the imperial family was 'studying tactical nuclear weapons,'... yeah, the world will move.”

私:「まあ研究者として生きるのであれば、発表してナンボなのは事実だけど、個人的には、研究なんぞ別に発表しなくてもいいと私は思っている。公に発表できなくとも、少なくとも、自分の好きな勉強が自由にできる環境だけは担保されていて欲しい、と心から願っている」

Me: “Well, it is true that if they are going to live as a researcher, they have to publish their research, but I do not think they have to publish your research. Even if they cannot publish publicly, I sincerely hope they can have an environment where they can freely study what they want.

嫁さん:「・・・」

Wife: “...”

私:「政府機関は、皇室の方々の『学問の自由』を守ってくれているのかな・・・」

Ebata: “I wonder if the government agencies are protecting the ‘academic freedom’ of the imperial people...”

-----

(シニアの)学問の徒の一人として、「学問の自由だけは絶対に守られるべきである」と、私は信じているんです。

As one of the (senior) academics, I believe that “only academic freedom should be protected.

ちなみに、戦術核は無理ですが、IT周辺の研究であれば、私は研究のお手伝いができると思います。

By the way, I can't help with tactical nuclei, but I can assist with IT research.

私は口も軽く、筆も軽いですが、その秘密は墓まで持っていくつもりです。

I am light of mouth and light of pen, but I will take that secret to my grave.

ですけど、やめた方がいいかな。

But I think you'd better not.

私、外国の諜報機関に拷問されたら、2秒で口を割る自信があります。

I am confident that if a foreign intelligence agency tortured me, I would crack in two seconds.

-----

ともあれ、宮内庁の人が『あの江端は、何下らないことを心配しとるんだ』と、せせら笑ってくれるようなら、それが一番いいです。

Anyway, it would be best if the people at the Imperial Household Agency would sneer at me and say, 'What a silly thing that Ebata is worrying about.

『計算とシステム評価から、敬愛に至る』

未分類

NHKの「解体キングダム」という番組がありますが、この番組構成と同じような形態で、人生の終りを計画・実行する「終活キングダム」を考えて下さい。

「終活キングダム」というテーマに基づく番組構成を提案します。この番組は、視聴者に終活(人生の終わりに向けた準備)についての具体的な手順やアイデアを提供することを目的とし、解体キングダムのようにプロジェクト形式で進行します。


番組タイトル

終活キングダム ~人生の最終章をデザインする~


番組構成

1. オープニングセグメント

  • 番組のテーマを簡潔に紹介。
  • 視聴者が抱える「終活」への不安や課題を映像やインタビューで紹介。
  • 「今日のプロジェクト」を発表。例えば、遺品整理、生前契約、デジタル遺産の管理、終活イベントの準備など。

2. プロジェクト開始

  • 番組ホスト(終活コンサルタントや専門家)が登場し、具体的なゴールを設定。
    • 例: 遺品を整理し家族に思い出を伝える、デジタルデータの整理とメッセージ作成など。
  • 専門家チーム(弁護士、遺品整理士、ライフコーチ、医療関係者)がプロジェクトをサポート。

3. ドキュメントパート

  • 実際のプロジェクト遂行の様子を追う。
  • プロジェクトの対象者(高齢者やその家族)が抱える感情的な葛藤や課題を描写。
  • 専門家が終活のアイデアや技術的なノウハウを提供。
    • 例: 家族とのコミュニケーション方法、効率的な整理術、法的手続きの解説。

4. エモーショナルセグメント

  • 家族や親しい人々との会話や手紙の準備など、感動的な場面を挿入。
  • 視聴者が共感できるように、実際の人生エピソードを共有。

5. プロジェクトの完成

  • 成果を視聴者に報告。
  • 例: 整理された家、メモリアルビデオ、生前葬の準備が整った様子などを紹介。
  • 対象者の感想や心の変化を語ってもらう。

6. エンディングセグメント

  • 番組を通じて得られた知識や視点を総括。
  • 視聴者に向けたメッセージとして、「今日から始められる終活リスト」を提供。
  • 次回予告: 他の終活テーマ(墓じまい、老後資金計画、友人へのメッセージ作成など)。

特徴

  • ビジュアル重視: 解体キングダムのようにビフォー・アフター形式を取り入れ、視覚的な変化を楽しめる構成。
  • 専門家の知識を凝縮: 終活のプロフェッショナルが分かりやすくアドバイス。
  • 心に響く物語性: 感動的な人間ドラマを通じて、終活への前向きな姿勢を啓発。
  • 参加型の要素: 視聴者が自分でも実践できる終活ワークシートを提供。

この番組を通じて、視聴者が人生の最終章を自分らしくデザインし、前向きな気持ちで終活に取り組むきっかけを提供します。


(江端感想)

うーん。この内容では、プロジェクトの評価項目(KPI)と、評価結果、およびフィードバックがないな。

「まだ、番組として検討の余地あり」と思いました。

# 自分の「死に方」にまで、点数を付けられではたまらん、と考える人は多いかとは思いますが、私、「終活」も、「技術」の一つだと思っていますので。