171–180 of 188 posts
Earlier quoted context omitted.
Why?
Anything created with free work should be free in return. Anything created by the public should be available for the public.
(serious request... I got a cluster, and something like a million pictures; but no GPUs or time for another side project...)
Earlier quoted context omitted.
Assuming from context you're CTO of Facebook, the facebook.com/schrep link in your profile isn't working: This page isn't available. The link you followed may be broken, or the page may have been removed.
The link only works if you are logged in, otherwise it says the page not found, which is wrong message because it makes you think it doesn't exists even if you login.
my overall feeling as someone that wants to start getting into visual recognition is that there are a bunch of great libraries/ecosystems to choose from and all of them have pros and cons, but i honestly don't want to make the wrong decision and end up being stuck later on. Anyone here has any advise on what i should use to have a camera(rpi) recognize most common objects and then add a layer where we can teach speci…
unless I'm mistaken, this is the very first lesson of the fast.ai course.
That's also covered eventually in fast.ai, but not until the second course if memory serves.
Can someone with GPUs and love in their hearts, bundle this with trained models in a Docker container? (serious request... I got a cluster, and something like a million pictures; but no GPUs or time for another side project...)
Follow me on Twitter, and I’ll post it there when it’s finished. Same username as here.
* edit: I've put a pull request in that builds the Dockerfile for the GPU for now: https://github.com/facebookresearch/Detectron/pull/15
Earlier quoted context omitted.
It was the same when this was about words from old books. I always had to fill in letters the average person would have thought it to be, not what it actually was (e.g. the letter "f" for what really was an "s" in gothic type). Nowadays it's much easier, you can click anything that looks vaguely the same (e.g. boxy things for cars, ads for traffic signs, traffic signs for store fronts etc.). The fact that it's so eas…
I actually like poisoning them. Not to be malicious but I feel manipulated into training their software for free. "Oh you wanted to sign up for that web forum? Sorry, but you have to do some free work for us first" And if you think that it's somehow good because it's mutually beneficial to train AI to better the future of humanity, don't. That is what their marketing department wants you to think.
Earlier quoted context omitted.
That’s impressive work. Still don’t think we have reached human level for all the categories of things we see in images. But you are correct that my comment about 1k categories is not true for many production systems.
Definitely not close to having things work for all categories. As you scale up to more categories ambiguity and specificity becomes an issue. Clarifai has a nice demo of their model which has >10K classes, https://clarifai.com/demo , the top predictions are usually correct but not always the most relevant. I only linked to the xception paper because it mentions JFT. It's not state of the art for large scale recogniti…
Earlier quoted context omitted.
FWIW we have some similar R-CNN models using this codebase running in the FB apps on iOS/Android with Caffe2 - with some neat bells and whistles (eg full execution of the compute graph on the device GPU where available via Metal/OpenGL). I’ll look into adding a mobile tutorial for Detectron if you’re interested.
That would be awesome. But - is a tutorial enough? From what I gather from the readme the custom ops have cuda implementations and no CPU ones, which you'd like to have as a fallback on mobile (even if metal/opengl implementations exist), or am I wrong?
Earlier quoted context omitted.
That would be awesome. But - is a tutorial enough? From what I gather from the readme the custom ops have cuda implementations and no CPU ones, which you'd like to have as a fallback on mobile (even if metal/opengl implementations exist), or am I wrong?
They exist and are (nearly all) open-sourced for CPU & Metal (I wrote some of them).