Alex Chandler

Members
  • Content Count

    12
  • Joined

  • Last visited

About Alex Chandler

  • Rank
    Junior Member

Recent Profile Visitors

The recent visitors block is disabled and is not being shown to other users.

  1. This cello is interesting but very undescriptive. Is it a fake Pierre Sylvester or just an unverifiable instrument? Also what do y'all think about the asking price? https://tarisio.com/auctions/auction/lot/?csid=2199289856&cpid=3657482240&filter_key=
  2. I am releasing a large database of instruments including maker name, year built, price sold, date sold. Below is a link to the database. Due to the uncompressed data taking 40 gigabytes of storage, I will only be releasing the database without image data at this time. My goal is to increase knowledge of the violin trade through the eyesight of statistics. If one would like to provide critique or help in the project, below are desired questions regarding the database. 1. Accuracy: What information is wrong? Are there any systematic errors in the database? Is the price sold data accurate? 2. Generality: Where does the database fail in representing the entire violin trade (trade and contemporary instruments for example)? 3. Future work: What can be done with this database? What unanswered question is the violin trade ? 4. Accessibility: What is the best way to increase sharing this information? What method of sharing leads to the largest number of people being able to benefit from my data collection? Who is interested in having photo data and what is the preferred method for large file transfers? 5. Thought?
  3. Absolutely. Computers are not very good at this, and for many reasons. The machine learning side of my project is just a small project, and I hope it is not found as the most important part, because I am the first to acknowledge that trained humans will be 10 times more accurate. My goal is to make a program that is better than the untrained eye, to be better than the person who has no idea what they are doing. On a side note, I hear you make spectacular instruments and look forward to playing one of your cellos one day.
  4. Hey Brad. I'd say for about 15 percent of the instruments I only have one photo. For 10 percent I only have two. And for 75 percent I have at least three photos. Most instruments are RGB although maybe 20 percent are black and white.
  5. My database is amazing. It is the best database. The most tremendous database. And I am the most humble amateur instrument enthusiast in the history of amateur instrument enthusiasts. For legal and ethical reasons, I will not share how I created it, but I will share at least parts of the database to let others benefit from it. I have 2,000 unique violin makers with 40,000 HD photos, and 8,400 data points of maker name, instrument age, instrument location, and HD photos. The problem, if one, lies in my machine learning code, which although many seem to have a strong, intellectual, opinion on, no one has seemed to actually look at even though it is public on my github. Attached below is a snippet of my database. And feel free to share your instrument database. I can add it to mine, as long as it, as you so wisely pointed out does not call for the extermination of humanity. 1. By whose definitions? By the definition of price. The model does a good job at classifying instruments under and over 10,000 dollars. 2. Sure you're not just sorting images at this point? I am sorting images, by price. I'm not done. The code has not been reviewed. When I'm confident about my work, I will make another post. 3. But how do they sound? Unfortunately, looking at a database does not allow one to actually hear an instrument. That requires owning the instrument, and currently, I do not own 10,000 instruments.
  6. One thing that is actually super easy to make is a stringed instrument classifier. There are hundreds of public databases for car and cat photos, and I would label each such point as not stringed instrument. That could avoid labeling toilet paper or a rubber duck as a expensive instrument.
  7. Very cool book, and thank you for letting me know about these sources of information. I may try to do so later in my life. Unfortunately, the summer is running out of days and writing any code to convert a book into a database would take 100+ hours and be an absolute pain in the ass. Big kudos though to Donald Cohen for writing it. I can appreciate the time it took to create such a database. I think you pretty much summed it up perfectly at the end. The source of appreciation for such a database will not be money.
  8. It’s impossible for it to fully work. But I have 2,000 unique makers, 15,000 instruments, 40,000 plus photos now all labeled to price. With an image generator, I have converted those photos into a 100,000 plus photos for the convolutional neural network. It’s not anywhere close to being perfect. The more epochs, the higher “accuracy” but also the higher overfitting. It should be able to tell garbage from anything not garbage. But yes you are right. It’s not meant to replace a Luthier because it can’t replace one. I see its purpose for someone who is not at all an expert. Years ago when I first looked at buying a cello, I found a nice cello on Ebay made 17th century by "Hannibal". I knew very little about the violin market, and thought that I had found a diamond in the rough. Only after reverse image searching it did I realize this was 100% a scam. My algorithm, once complete, could serve a spam identification service for stringed instruments. When another “fine Italian Cello 17th century” is listed at 2,000 dollars on Ebay, a model with multiple inputs (text and photos) could flag this.
  9. One reason I haven't sent the code out is because I haven't tested it for things like that. Maybe there is a high correlation between black and white photos and high quality instruments (leading to me mistakenly thinking my algorithm works). Perhaps my algorithm is only looking at varnish and not any damage like a sound post crack. Skepticism in this part of my project is fully justified. If it does not work, well I will have a little toy to show people like that Silicon Valley clip above. I still think the bigger part of my project is inflation statistics. I can't seem to figure out why most violas appreciate less (aside from it being a limited dataset), as seen here: https://violinsarecool.wordpress.com/home/violin-inflation-statistics/
  10. Good idea. What kind of format for the database would be the most accessible to a wide audience? Perhaps, a CSV file?
  11. The website is unfinished, full of typos, I am sure, and still changing.. But yes I should say the tool is rather imperfect in its nature. The same could be said of some cellos in the Testore school that sell of obscene amounts but look crappy. I could boost accuracy by create a price prediction model including multiple inputs like maker name and age, like seen here for real estate (https://www.pyimagesearch.com/2019/02/04/keras-multiple-inputs-and-mixed-data/). I am more interested in what one could do with a database of this size. I have made an interactive map where one can pick a range of years and see where the instruments of that time are on a map of a country or geographic region.
  12. I have a database of around 10,000 instruments containing maker name, instrument type, location made, year built, year sold, price sold, and photos of the instrument. I have so far calculated the inflation rate for instruments of different type, value, and age from auction data of instruments that have been publicly sold multiple times. My interests are twofold: one is to integrate statistics into the history of the violin trade. The other is to apply to a branch of computer science to predict the price of instruments based on only a photo of the instrument. The process of creating such a database was excruciating. I may release it later after I am done testing it for its accuracy. My unfinished website can be viewed here: instrumentappraiser.com . The end website should predict the quality of an instrument solely based off photos. It will never be perfect, but could serve as a spam identifier or have some other unknown purpose. A couple interesting graphs and charts can be viewed here. https://violinsarecool.wordpress.com/home/history-of-violin-trade/ https://violinsarecool.wordpress.com/home/violin-inflation-statistics/ My questions are the following: if one was to have a database of the entire violin trade, what would one do with it? What are unanswered questions in the violin trade that could be solved with data? Does anyone else have interest in helping me in this project. Attached below is a compressed file of what I have accomplished so far. snippets.zip