And if you want to just load generic pre-trained classifiers for a variety of tasks, ml5js (which uses TensorFlow.js under the hood) seems promising!
> Training a model in the browser is the least practical use for tensorflow.js
Unless you want to do some type of federated training in real time without sending private information to the servers (very unusual case in my opinion)
The most practical use not mentioned here is probably to import existing trained models/weights. I can see it being useful for anything that you want to run in real-time (e.g., webcams apps like https://github.com/ModelDepot/tfjs-yolo-tiny) and can't pay a round-trip cost to server.
Training a model in the browser is the least practical use for tensorflow.js IMO (unless maybe you want to hijack people's browsers to help with training or something).
wow! that is an amazingly well done video!
Interesting video except I found the vocal fry to be distracting.
thanks for sharing!! :)
A nice introductory presentation about deep learning using tensorflow.js:
A lot of problems boil down to optimizing a cost function. This function could be the error in recognizing cat pictures or the likelihood of recommending a movie to a user.
What people want is an easy way to express these functions so that a computer can optimize it for them. Tensorflow allows people to do just that, it lets you represent your mathematical equation in a way that can be analyzed and optimized by a computer.
It does it by exposing various mathematical operations that it understands. As long as you can express your mathematical function using these operations then Tensorflow knows how to compute it efficiently and you can use its optimizer to find the optimal inputs.
comes in handy for a lot of problems.
Tensorflow tries to fit the free parameters (usually millions of parameters) of a function y=f(x). The fitting algorithm gets usually thousands or millions of examples of how the output y for a given input x has to look like.
For example, x can be tens of thousands of images of cats and dogs, and y can be 1 for a dog and 0 for a cat.
The goal for the fitting algorithm is to find parameters that describe the concept of a cat and a dog so that it can
can generalize and categorize general images of cats and dogs. A bad fit would be if the network just memorized the example images.
If I understand it correctly:
- Tensorflow is the best tool to make the grunt work necessary to calibrate the parameters of fitting algorithms.
- Models of fitting algorithms are human proposed and where the ML 'art' is. Seems to be kind of reverse engineering.
Accurate, although in most cases, the art is not in choosing the algorithm (often a regular feed-forward, covolutional or recurrent neural network) but the hyperparameters (regularization, number of layers, units, etc.) and sometimes the way the data is fed (augment the dataset with distortions? sample negative examples randomly? etc.)
Tensorflow is the best tool
It is one of many competing tools, which is “best” depends ironically on many variables. CNTK is a rival for example.
It's a high-performance-computing framework that allows you to specify matrix and vector math expressions in terms of a graph structure. In exchange, you get automatic derivative calculation, and a somewhat easier ability to distribute complicated calculations across processors.
HN people are mainly interested in it because it's one of the major frameworks for creating neural networks. Also because Google.
- Privacy. You can make predictions locally, or send embeddings back to a server without the raw data ever leaving a client.
- Interactivity / education tooling. See tensorflow playground for an excellent example.
- No servers for applications. Making predictions in TensorFlow on a server can be expensive in the long run. Hosting static weights on a server is much much cheaper.
Right. So this is "we don't want to use another language". Acknowledged.
"Privacy. You can make predictions locally, or send embeddings back to a server without the raw data ever leaving a client."
If calling out to a binary is a security problem for you, you have bigger problems than choice of language. Also, of course, you don't need tensorflow to convert your top-secret data into an input vector that you can send somewhere (seriously: it does not help with this problem).
Your third and fourth points -- flexibility and interactivity -- are indeed why people use Python vs C++ (even though it's more difficult and painful to get decent performance out of TF with that approach). So again, this boils down to "I don't want to use Python and I'd prefer to use JS instead."
"No servers for applications. Making predictions in TensorFlow on a server can be expensive in the long run. Hosting static weights on a server is much much cheaper."
You're contradicting yourself with this point. Servers are expensive so hosting static weights on a server is cheaper? I have no idea what this means.
> So this is "we don't want to use another language".
Yup, which is a perfectly valid reason.
> If calling out to a binary is a security problem for you
You miss the point. The security problem is sending the raw data from the client to the server.
> So again, this boils down to "I don't want to use Python and I'd prefer to use JS instead."
Which once again, is a perfectly valid reason
> Servers are expensive so hosting static weights on a server is cheaper?
No, CPU/GPU intensive tasks on a server is expensive but storing a few static weights is cheap.
"You miss the point. The security problem is sending the raw data from the client to the server."
So don't do that. If you can run tensorflow on your device, you can call out to a local process.
If you want to use JS to do everything, fine. But that's not a good reason. It's just a reason.
> So don't do that. If you can run tensorflow on your device, you can call out to a local process.
Not from a webapp (without jumping through a dozen other hoops.) With tensorflow.js, you can do (for example) pose estimation, or face detection, or audio recognition, right in the browser without sending data to a remote server.
> But that's not a good reason. It's just a reason.
Yes, of course it's a reason. The point is that it can be a good reason in many cases.
So now we're down to "I want to run a neural network exclusively in the browser" as the primary reason you'd want to use this.
OK, fine. That's a niche use-case for a domain where scale and performance matter so much that we're building specialized hardware to support it. For 99.99% of developers, they would be better advised to find another way to solve their problem using more conventional tools.
How can you run Python tensorflow locally? We're talking about web apps here.
Try to understand what is at play here. It's not all about raw performance, there are many more important things to consider that GP explained extensively.
I think you're conflating privacy and security. Serving the
model on the client side means that the server is never aware of who put the inputs in.
Also he isn't contradicting himself, serving static data off a CDN or server is a lot easier and a lot less expensive than having a cluster setup to do inference.
Noob question: Can anybody tell in a few sentences of plain english what is tensorflow, how it works and why seems to be so relevant?
You can probably export your Keras model, load it in tensorflow.js, and train it. Makes more sense than transpiling.
Thanks! Do you by chance know if it is practical to convert huge .h5 Keras models to TF.js layers model? (~1GB). I have some state-of-art computer vision models and it would be great if they could be used in a browser with a WebCam, if they can fit into memory and be performant for inferencing.
Mobile has similar constraints as web (but to a lesser extent) so you will find more resources there.
Look into quantizing the weights (e.g., reduce from 32bit per parameter to 8 bits) to reduce model size: https://www.tensorflow.org/mobile/optimizing#model_size
Fixed it, thanks!
I think your step 4 code is messed up though?
I was going to upvote you ‘til I read the last line
haha take my upvote sir. i'm looking forward to new breed of websites that abuse our browsers unknowingly. First mining crypto, now we will have people using thousands(millions) of web browsers as part of some elaborate compute cluster that runs some 'AI' deep learning crap to try and optimize branding/click rates etc.
You were so busy figuring out if you could, you didn't stop to wonder if you should…
Joking aside this is super cool