As a chess player, "60 minute blitz" sounds very wrong.
Deep Learning with PyTorch: A 60 Minute Blitz [video]
51–60 of 62 posts
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#52Ugh its so easy compared to what i've been wrangling in tensorflow.
Keep in mind that tutorials will always make it look easy compared to debugging actual production code. If you look through tensorflow tutorials, they also look very easy, especially with TF2. That said, I've experimented with pytorch and I agree that it is really nice to work with. Disclaimer: I work at Google and do use tensorflow, though I don't work on the tensorflow team.
PyTorch is 10x easier to debug than even TF2, and it's been that way all along. TF2 is no easier to debug than the previous releases if you're not using eager mode (which most people don't), and even in eager mode it sometimes errors out in ways that do not offer any suggestion as to _which op_ caused the error. This is nuts. Modern architectures have hundreds, sometimes thousands of ops. It basically boils down to flying blind and guessing and can easy take days of trial and error to figure out each issue. Plus, every time you start a TF program it just sort of sits there for a minute or so before it starts doing anything. This severely hampers productivity when debugging.
To all the folks who are just starting out: just go with PyTorch. It's downright intuitive compared to anything Google has been able to put out so far.
Disclosure: ex-Googler. Used TF while there (and DistBelief before it). Gave it up as soon as PyTorch came out. Couldn't be happier.
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#53Does no one build their own ml algos anymore? I don't understand the need for pytorch and tensor flow. I honestly thought tensor flow was nothing but a teaching thing for undergrads
Do you also write your own automatic differentiation tools? Using libraries like TF and PyTorch makes sense if you use neural networks because they provide automatic differentiation (who wants to write out their gradients by hand?) and standard neural network components. Edit: If your algorithm is not using neural networks, then libraries like TF may or may not be a good fit, it depends on the algorithm. Writing cust…
People do write their own AD tools... in a day, sometimes!
http://blog.rogerluo.me/2018/10/23/write-an-ad-in-one-day/
http://blog.rogerluo.me/2019/07/27/yassad/
Although the endpoint is likely to be a better understanding of the choices made by a mature implementation, and of the work involved in fixing up edge cases.
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#54For anyone who's interested in learning PyTorch, here's the best video course I was able to find: https://www.youtube.com/playlist?list=PLZbbT5o_s2xrfNyHZsM6u... They explain things incredibly well, videos are easy to understand, engaging, and to the point. Highly recommend it to everyone! I've also heard that Udacity has some good courses, but I can't vouch for those yet.
Do you have any more recommendations?
I'm an undergrad student, and I'm nervous about picking between Tensorflow+Keras over PyTorch.
It looks like many more companies are hiring for TensorFlow, and there's a wealth of information out there on learning ML with it. In addition, it just got the 2.0 update.
But, PyTorch is preferred nearly every single time when I see the discussion come up on HN and Google searches. I'm having a hard time deciding what to dedicate my time to.
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#55For anyone who's interested in learning PyTorch, here's the best video course I was able to find: https://www.youtube.com/playlist?list=PLZbbT5o_s2xrfNyHZsM6u... They explain things incredibly well, videos are easy to understand, engaging, and to the point. Highly recommend it to everyone! I've also heard that Udacity has some good courses, but I can't vouch for those yet.
Do you have any more recommendations? I'm an undergrad student, and I'm nervous about picking between Tensorflow+Keras over PyTorch. It looks like many more companies are hiring for TensorFlow, and there's a wealth of information out there on learning ML with it. In addition, it just got the 2.0 update. But, PyTorch is preferred nearly every single time when I see the discussion come up on HN and Google searches. I'm…
My 2c: learn the methods deeply, pick up the frameworks as needed. Knowing PyTorch or TF well won't make you a good data scientist or statistician.
YMMV
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#56For anyone who's interested in learning PyTorch, here's the best video course I was able to find: https://www.youtube.com/playlist?list=PLZbbT5o_s2xrfNyHZsM6u... They explain things incredibly well, videos are easy to understand, engaging, and to the point. Highly recommend it to everyone! I've also heard that Udacity has some good courses, but I can't vouch for those yet.
Do you have any more recommendations? I'm an undergrad student, and I'm nervous about picking between Tensorflow+Keras over PyTorch. It looks like many more companies are hiring for TensorFlow, and there's a wealth of information out there on learning ML with it. In addition, it just got the 2.0 update. But, PyTorch is preferred nearly every single time when I see the discussion come up on HN and Google searches. I'm…
Abstract from the tools. They come and go. You will need to adopt a new one every other year.
Instead, make sure to understand the math and the concepts, and then it‘s easy to translate that to an implementation.
One way of doing this (though not sufficient) is to learn both tools.
Right now the pull is away from TF (increasingly convoluted API and lots of deprecations) and towards pytorch (more support from the research community and increasing performance in production).
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#57Are you looking for a " rel="nofollow">https://www.simplycleaver.com/games/"> Best arcade games ? Snake Beats is your answer! It has great music and graphics, try now!
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#58I posted this link but now the title has somehow changed. I do not know what is the policy on HN. But the title saying "[video]" might give a wrong impression that this points to a one hour long video. The link points to a tutorial which embeds an entirely optional two minute video that introduces the main content contained in five web pages.
Wow, thanks, I was planning to not even click the link because, well, 60 minute video.
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#59For anyone who's interested in learning PyTorch, here's the best video course I was able to find: https://www.youtube.com/playlist?list=PLZbbT5o_s2xrfNyHZsM6u... They explain things incredibly well, videos are easy to understand, engaging, and to the point. Highly recommend it to everyone! I've also heard that Udacity has some good courses, but I can't vouch for those yet.
Do you have any more recommendations? I'm an undergrad student, and I'm nervous about picking between Tensorflow+Keras over PyTorch. It looks like many more companies are hiring for TensorFlow, and there's a wealth of information out there on learning ML with it. In addition, it just got the 2.0 update. But, PyTorch is preferred nearly every single time when I see the discussion come up on HN and Google searches. I'm…
I'll recommend fastai course [1].
At the end of the course you will be able to implement almost any ML state of the art solution (classification, regression and Computer vision).
Sounds too good to be true? Jeremy have that effect, The other day in a podcast they told him Saint.
It's free btw.
Re: Deep Learning with PyTorch: A 60 Minute Blitz [video]
#60Earlier quoted context omitted.
When you hear autoregressive model, think “predicting a sequence”. These are good for text to speech since you can say “given some text, generate a spectrogram.” GPT-2 is probably the most impressive example of autoregressive techniques (I think). GANs, and especially stylegan, are good for generating high quality images up to 1024x1024. These take about 5 weeks to train and $1k of GCE credits. The dataset size is ar…
I found a strange bifurcation recently while collecting papers on a sub-topic of this question.. China-based authors quoting other China-based authors extensively, in English with math, of course. Meanwhile, the US and Western EU seem like "it" , in other words, all the papers referenced seem like the ones you would reference..etc self-consistant.
One of the incredibly unfortunate things about science out of China. It may or may not be trustworthy, as in the data may be just straight false. I'm not surprised that you saw that split, I'd be leary of quoting/referencing a potentially false paper myself.