Radek

@radekosmulski

I ❤️ ML / DL ideas - I tweet about them / write about them / implement them. Self-taught RoR developer by trade.

যোগদান করেছেন এপ্রিল ২০১৪

মিডিয়া

  1. ৫ জুলাই
    -কে উত্তর দিচ্ছেন

    Thank you very much again for noticing this Sylvain 🙂New version pushed. This is what the learning rate and the momentum look like now:

  2. ৫ জুলাই

    Fastest way to train on CIFAR10 - now available on a PC near you! 🙂 This is a 🔋 included docker setup featuring recent work by & (training with AdamW and the 1 cycle policy). Very excited by the development!

  3. ৫ জুন

    A great into to pipelines! Learning this is one of my mini-projects. Gives you superpowers when working with structured data and is a very nice way to reason about calculations in general. Did you know sklearn had FunctionTransformer and Imputer? 👌🙂

  4. ৪ জুন
    -কে উত্তর দিচ্ছেন

    This is from the first lecture of the Computational Linear Algebra course:

  5. ৩১ মে

    But enough of making statements based on perceptions! Time to look at some data 🙂 Here is model performance on the val set. Not indicative of arch performance in general but carries some info on the ability to train said models using the tools I used on a single 1080ti

    এই থ্রেডটি দেখান
  6. ৩১ মে

    1yr ago I gave up on ML. I didn't know what to learn nor how After a 5 mths break I decided to give ML one last try. If it would not work out I would need to let it go to not continue to waste my time - maybe I am unable to learn this I then signed up for the course

    এই থ্রেডটি দেখান
  7. ১৮ মে

    Just how fast is a 1080ti? Training on cifar10 to 94% accuracy on a p2.8xlarge takes 4 min 10 sec (30%) longer than locally on a 1080ti! On a p2.xlarge that's nearly 1hr. The hyperparams have been tweaked for squeezing out every ounce of performance out of 1080ti but still...

    এই থ্রেডটি দেখান
  8. ১৭ মে

    `ssh -A` so good and yet I didn't know about it until recently! Effectively allows you to take your identity with you to the machines you ssh into. Committing to github / bitbucket without having to generate / add key on remote machine? No problem!

  9. ১৫ মে

    seemed like a good moment to fly the banner 🙂 (this is from the iMaterialist Challenge (Fashion) at FGVC5 competition that is still under way)

  10. ২ মে

    And this is GPU utilization.

    এই থ্রেডটি দেখান
  11. ২ মে

    A couple of pictures from the training. This is the groundbreaking 1cycle policy by Leslie Smith implemented beautifully in by . You can read more about it on his blog here: .

    এই থ্রেডটি দেখান
  12. ২ মে

    Train on cifar10 to over 94% accuracy on a single 1080ti while having a ☕️? Why not 🙂 train time < 13 min 30 sec, 20 epochs, lr = 1.5, bs = 128 (this is essentially DAWNbench submission with minor tweaks for running locally)

    এই থ্রেডটি দেখান
  13. ২২ এপ্রিল

    I know this has been done a trillion of times before and is not very complicated... but this is fun and wanted to share! (CAM is covered at the end of v2 lesson 7 and is a nice intro to FCNs and using hooks in )

  14. ২০ এপ্রিল
    উত্তর দিচ্ছেনReplying to এবং অন্য

    added an SSD to the comparison

  15. ১৯ এপ্রিল

    NVME vs HDD: training on 10k train, 5k val, single epoch (no opportunity for caching on val to kick in), small arch, files a subset of 76GB dataset, highly optimized dataloader cc

  16. ১৪ এপ্রিল

    I finally understand why git. Great talk to watch if you have been using git for a while but are still relatively new. Has also other great thoughts. My favorite one was that speed doesn't only mean we can do smth faster, but that it changes how we do it.

  17. ১১ এপ্রিল

    nvmes are an amazing piece of tech! random reads are so important for many applications - so looking forward to exploring the difference they can make for ML Below what iotop reports when reading from the hdd and the nvme

    এই থ্রেডটি দেখান
  18. ১১ এপ্রিল

    How long does it take to read 1 mln (76 GB) worth of jpegs? A lot depends on the drive (below comparison of reading from a hdd and an nvme)

    এই থ্রেডটি দেখান
  19. ১০ এপ্রিল

    You can now make submissions directly from a notebook with ease 🤗🎉

  20. ১০ এপ্রিল
    -কে উত্তর দিচ্ছেন

    Outstanding work! :) I can barely keep up with all the things being added to the library given the pace nowadays BTW since not too long ago the black border is also supported

লোড হতে বেশ কিছুক্ষণ সময় নিচ্ছে।

টুইটার তার ক্ষমতার বাইরে চলে গেছে বা কোনো সাময়িক সমস্যার সম্মুখীন হয়েছে আবার চেষ্টা করুন বা আরও তথ্যের জন্য টুইটারের স্থিতি দেখুন।

    আপনিও পছন্দ করতে পারেন

    ·