Skip Navigation

User banner

Charlie Fish

@ fishcharlie @eventfrontier.com

Posts
46
Comments
44
Joined
3 yr. ago

Software Engineer (iOS) 🖥📱, student pilot ✈️, HUGE Colorado Avalanche fan 🥅, entrepreneur (rrainn, Inc.) ⭐️ https://charlie.fish/

  • When building a home server, could a used/cheap PC do the job?

    Jump

  • It really depends on what you're trying to do. At the end of the day, the foundational components are pretty standard across the board. All machines have a CPU, motherboard, storage mechanism, etc. Oftentimes those actual servers have a form factor better suited for rack mounting. They often have more powerful components.

    But at the end of the day, the difference isn't as striking as most people not aware of this stuff think.

    I'd say considering this is your first experience, you should start with converting an old PC due to the lower price point, and then expand as needed. You'll learn a lot and get a lot of experience from starting there.

  • Netflix says its brief Apple TV app integration was a mistake

    Jump

  • This is not a “mistake”. This clearly proves they have Apple TV app integration implemented (just turned off). And someone accidentally turned it on.

    But they have clearly put in effort and work into adding this functionality.

    New functionality doesn’t just happen by mistake.

  • Very inconsistent machine learning model training

    Jump

  • Got it. Thanks so much for your help!! Still a lot to learn here.

    Coming from a world of building software where things are very binary (it works or it doesn't), it's also really tough to judge how good is "good enough". There is a point of diminishing returns, and not sure at what point to say that it's good enough vs continuing to learn and improve it.

    Really appreciate your help here tho.

  • Very inconsistent machine learning model training

    Jump

  • So someone else suggested to reduce the learning rate. I tried that and at least to me it looks a lot more stable between runs. All the code is my original code (none of the suggestions you made) but I reduced the learning rate to 0.00001 instead of 0.0001.

    Not quite sure what that means exactly tho. Or if more adjustments are needed.

    As for the confusion matrix. I think the issue is the difference between smoothed values in TensorBoard vs the actual values. But I just ran it again with the previous values to verify. It does look like it matches up if you look at the actual value instead of the smoothed value.

  • Very inconsistent machine learning model training

    Jump

  • Sorry for the delayed reply. I really appreciate your help so far.

    Here is the raw link to the confusion matrix: https://eventfrontier.com/pictrs/image/1a2bc13e-378b-4920-b7f6-e5b337cd8c6f.webm

    I changed it to keras.layers.Conv2D(16, 10, strides=(5, 5), activation='relu'). Dense units still at 64.

    And in case the confusion matrix still doesn't work, here is a still image from the last run.

    EDIT: The wrong image was uploaded originally.

  • Very inconsistent machine learning model training

    Jump

  • Ok I changed the Conv2D layer to be 10x10. I also changed the dense units to 64. Here is just a single run of that with a Confusion Matrix.

    I don't really see a bias towards non-blurred images.

  • Very inconsistent machine learning model training

    Jump

  • So does the fact that they aren't converging near the same point indicate there is a problem with my architecture and model design?

  • Very inconsistent machine learning model training

    Jump

  • Got it. I'll try with some more values and see what that leads to.

    So does that mean my learning rate might be too high and it's overshooting the optimal solution sometimes based on those random weights?

  • Very inconsistent machine learning model training

    Jump

  • I think what you’re referring to with iterating through algorithms and such is called hyper parameter tuning. I think there is a tool called Keras Tuner you can use for this.

    However. I’m incredibly skeptical that will work in this situation because of how variable the results are between runs. I run it with the same input, same code, everything, and get wildly different results. So I think in order for that to be effective it needs to be fairly consistent between runs.

    I could be totally off base here tho. (I haven’t worked with this stuff a ton yet).

  • Very inconsistent machine learning model training

    Jump

  • Thanks so much for the reply!

    The convolution size seems a little small

    I changed this to 5 instead of 3, and hard to tell if that made much of an improvement. It still is pretty inconsistent between training runs.

    If it doesn’t I’d look into reducing the number of filters or the dense layer. Reducing the available space can force an overfitting network to figure out more general solutions

    I'll try reducing the dense layer from 128 to 64 next.

    Lastly, I bet someone else has either solved the same problem as an exercise or something similar and you could check out their network architecture to see if your solution is in the ballpark of something that works

    This is a great idea. I did a quick Google search and nothing stood out to start. But I'll dig deeper more.

    It's still super weird to me that with zero changes how variable it can be. I don't change anything, and one run it is consistently improving for a few epochs, the next run it's a lot less accurate to start and declines after the first epoch.

  • Machine Learning | Artificial Intelligence @lemmy.world
    Charlie Fish @eventfrontier.com

    Very inconsistent machine learning model training

  • Instance owners, how did you get your server online?

    Jump

  • That’s attached to the instance? Do you have a screenshot maybe?

  • Instance owners, how did you get your server online?

    Jump

  • What is the error that you get?

  • Ubiquiti @lemmy.ml
    Charlie Fish @eventfrontier.com

    Ubiquiti Black Friday Deals

    store.ui.com /us/en/black-friday

  • Does my instance federate with communities, or does my user?

    Jump

  • Yes. It just will fill your feed with a bunch of things you might not care about. But admin vs non admin doesn’t matter in the context of what I said.

  • Does my instance federate with communities, or does my user?

    Jump

  • Your instance is the one that federates. However it starts with a user subscribing to that content. Your instance won’t federate normally without user interaction.

    Normally the solution for the second part is relays. But that isn’t something Lemmy supports currently. This issue is very common with smaller instances. It isn’t as big of a deal with bigger instances since users are more likely to have subscribed to more communities that will automatically be federated to your instance. You could experiment with creating a user and subscribing to a bunch of communities so they get federated to your instance.

  • Deleted

    Permanently Deleted

    Jump

  • It’s not really any different than hosting any other service.

  • Removed

    Do people actually use Mastodon for something else than posting cats and hiking photos?

    Jump

  • I was lucky to get in in the early days when posting Mastodon handles on Twitter was common so was able to easily migrate. But this is a problem with ActivityPub right now I feel like. Discovery algorithms can be awful in the timeline, but so useful for finding people/communities to follow.

  • Eve Energy smart plugs transmit Energy information via Matter

    Jump

  • Yep just saw that too after I researched it a bit more. What is strange is I don't remember Eve Energy having a firmware update since then. Makes me wonder if they had it ready to go in previous firmware versions based on internal specs they saw? Or maybe I just forgot about a firmware update I did.

  • Major League Baseball @lemmy.ml
    Charlie Fish @eventfrontier.com

    Hurricane-stricken Tampa Bay Rays to play 2025 season at Yankees' spring training field in Tampa

    apnews.com /article/tropicana-roof-rays-yankees-hurricane-milton-112a238a23b1223b9222effcb26b8911

  • Eve Energy smart plugs transmit Energy information via Matter

    Jump

  • but as the Matter standard doesn't yet support energy monitoring, users are limited to basic features like on and off and scheduling

    - from this link

    Granted the article is almost a year old. But I just didn't realize that Matter now supports energy monitoring. Somehow I just missed that news.

  • homeassistant @lemmy.world
    Charlie Fish @eventfrontier.com

    Eve Energy smart plugs transmit Energy information via Matter

  • Apple @lemmy.world
    Charlie Fish @eventfrontier.com

    Apple teams up with airlines for new ‘Share Item Location’ AirTags feature in iOS 18.2 - 9to5Mac

    9to5mac.com /2024/11/11/ios-18-2-share-item-location-airtags-feature/
  • Lemmy App Development @lemm.ee
    Charlie Fish @eventfrontier.com

    Best way to determine if a Lemmy server has a pictrs server?

  • Obtaining Certification ID's

    Jump

  • I'm not aware of any official Ubiquiti certifications. Maybe it was a 3rd party certification? Someone else might know more than I do tho.

  • Machine Learning | Artificial Intelligence @lemmy.world
    Charlie Fish @eventfrontier.com

    coremltools Error: ValueError: perm should have the same length as rank(x): 3 != 2

  • TensorFlow @eventfrontier.com
    Charlie Fish @eventfrontier.com

    coremltools Error: ValueError: perm should have the same length as rank(x): 3 != 2

  • Major League Baseball @lemmy.ml
    Charlie Fish @eventfrontier.com

    Soto already drawing interest from several clubs (report)

    www.mlb.com /news/juan-soto-rumors
  • Machine Learning | Artificial Intelligence @lemmy.world
    Charlie Fish @eventfrontier.com

    TensorFlow Lemmy Community

    eventfrontier.com /c/tensorflow
  • TensorFlow @eventfrontier.com
    Charlie Fish @eventfrontier.com

    Were there major performance improvements between 2.12.0 and 2.18.0?

  • Major League Baseball @lemmy.ml
    Charlie Fish @eventfrontier.com

    Dodgers are 2024 World Series Champions

  • Major League Baseball @lemmy.ml
    Charlie Fish @eventfrontier.com

    Dodgers take Game 2 as series shifts to NY