31–40 of 62 posts
Does 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
can we see some of the "ml algos" you've built? in particular your autodiff engine
Is there a drop in replacement for TensorBoard? It’s probably the biggest thing keeping me using tensorflow. Ideally the api of the pytorch equivalent would be about the same too. I answered my own comment before posting it. But in case it’s helpful to anyone else, I’ll put the answer here: yes, TensorBoardX. Looks like it’s very easy to use: https://tensorboardx.readthedocs.io/en/latest/tutorial.html Anyone have tho…
One thing I've noticed is that it's quite hard to have vibrant discussions about DL because it is all either so simple or it is dauntingly complicated/unpredictable. Mostly my DL conversations end up being about frameworks. Anyone else experience this? Also the number of DL submissions on HN seems surprisingly low given the applicability of the technology.
These are “hands on” in the sense that you can replicate the results just by pasting in the same code. It’s kind of like a tutorial notebook in essay form.
Speaking of tutorial notebooks, pbaylies’ stylegan-encoder is quite good and you can run it on colab: https://colab.research.google.com/github/pbaylies/stylegan-e...
(Set runtime to GPU up in the menu.)
https://github.com/pbaylies/stylegan-encoder
In my experience the best place to have informal ai discussions is Twitter. The community is shockingly helpful. Follow @jonathanfly, @roadrunning01, @pbaylies and whoever pops up in the stuff they post. Roadrunning in particular posts tweets of the form “here’s some research; here’s the code” often with an interactive notebook.
Anyone know somewhere that has a good overview of the various ML and DL model types and what they are good for? I've been looking for a survey paper or book or just a glossary of ML.
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…
Anyone know somewhere that has a good overview of the various ML and DL model types and what they are good for? I've been looking for a survey paper or book or just a glossary of ML.
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…
The whole advantage of GaN is it does NOT need an explicit distance metric for comparing images--instead the discriminator effectively learns the metric in order to improve its ability to distinguish real images from generated/fake ones. Arguably this is the whole advantage of GaNs.
So to argue that IMLE can solve mode collapse is a false equivalency.
Ugh its so easy compared to what i've been wrangling in tensorflow.
Earlier quoted context omitted.
Do you write your own crypto libraries too?
>Do you write your own crypto libraries too? Some people do. It's a good challenge.[0] [0] https://cryptopals.com/
I had a lesson in writing crypto once, when I made what I thought was a good enough secret mixing procedure to encode some data I wanted to email outside of a company that didn’t allow web access. (Long time ago, circa 2000). It all looked undecipherable and I sent most of the data before I discovered that strings of binary zero were leaking my secret key. Oops, pretty stupid.
For 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.
Anyone know somewhere that has a good overview of the various ML and DL model types and what they are good for? I've been looking for a survey paper or book or just a glossary of ML.
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…