To me it seems the real goal of hyping these things so heavily is to increase their cloud revenues.
TensorFlow, Keras and deep learning, without a PhD
101–110 of 156 posts
Re: TensorFlow, Keras and deep learning, without a PhD
#102Mandatory plug: do consider using PyTorch instead. It's far easier to pick up and work with. Easy things are easy, hard things are possible.
For what it's worth, I've found Pytorch to be much more rigid than TF. Maybe I just haven't found the easy way to do things. For example here's a function that applies an N×N box filter to all but the first 2 dimensions of a tensor (apologies to mobile users):
def boxfilter(image, N=3):
shape = image.shape
image = tf.reshape(image, [1, shape[0], shape[1], -1])
C = image.shape[-1]
conv = tf.nn.conv2d(image, tf.eye(C, C, [N, N]), 1, "SAME")[0]
return tf.reshape(conv, shape) / (N * N)Re: TensorFlow, Keras and deep learning, without a PhD
#103I'm doing deep learning without a data science background. Some of my current results are: * https://vo.codes * https://trumped.com The voices need better data curation and longer training, but some speakers such as David Attenborough are quite good. I've also built a real time streaming voice conversion system. I want to generalize it better so that it can be an actual product. I think it could be a killer app for D…
Great work! (Though it seems to work only with words it knows) And don't worry, PhD requirements are overrated
Thanks!
There's a reason for the word omission: I'm using the CMUdict Grapheme -> Phoneme database. There are 140,000 entries, but it doesn't capture everything. I've had to add words like "pokemon" and "fortnite".
I'm looking for a model that handles arbitrary grapheme/word -> phoneme/polyphone transformation. I'm also interested in perhaps replacing Arpabet with IPA (using the existing arpabet database to construct it). This might work well for non-English languages.
Do you happen to know an existing model that does this?
So much work to do... :)
Re: TensorFlow, Keras and deep learning, without a PhD
#104I'm doing deep learning without a data science background. Some of my current results are: * https://vo.codes * https://trumped.com The voices need better data curation and longer training, but some speakers such as David Attenborough are quite good. I've also built a real time streaming voice conversion system. I want to generalize it better so that it can be an actual product. I think it could be a killer app for D…
Could you provide some examples of good work in the field of singing nets?
Check out r9y9 on Github. He's doing some amazing work in this area.
Re: TensorFlow, Keras and deep learning, without a PhD
#105I'm doing deep learning without a data science background. Some of my current results are: * https://vo.codes * https://trumped.com The voices need better data curation and longer training, but some speakers such as David Attenborough are quite good. I've also built a real time streaming voice conversion system. I want to generalize it better so that it can be an actual product. I think it could be a killer app for D…
Hi Brandon, nice work! Some questions to learn more if you don't mind - are you using Tacoton2 for the voice generation? If it's Tacotron2, are you using a base model before you train up new speakers, or is each speaker model trained from scratch? How long do you run the training for normally (for both cases), and what hardware are you running? You mentioned elsewhere you're renting the V100s, what services have you…
> are you using Tacoton2 for the voice generation?
Nope. glowtts. Tacotron2 has higher fidelity (it's a denser network), but it's really slow and expensive to run.
> are you using a base model before you train up new speakers
Absolutely! Transfer learning is essential to training on sparse or limited data, and it's incredibly effective.
> How long do you run the training for normally
> and what hardware are you running?
I think I explained this in my other answer? But if not, it's typically awhile. The best guiding light though is to frequently listen to the inference results. Are they improving? Watch the Tensorboard graphs to see what loss and attention look like and make sure you're actually learning.
> By the way, your Trumped.com is throwing some errors in the console so the site isn't working for me.
Oh no. I realize there are some bugs I left for iPhone (simply because I don't have one), and I really need to get those fixed. I'm not sure if this is your case or not. Perhaps the pods with the Trump model are also experiencing duress -- I'll need to investigate that too. I have yet to hook up monitoring (yikes).
Re: TensorFlow, Keras and deep learning, without a PhD
#106Earlier quoted context omitted.
Oh yes, I don't think advanced math is required in any way. However, there is a difference in that researchers who have worked with these models for many years (often including having done some of the math) have a very good intuitive understanding of these models. Once you have that, it's fine to be driven by gut feeling. Just like many engineers are driven by gut feeling that come from tacit knowledge through experi…
It sounds like what you’re complaining about is some people who put papers on arxiv and deceivingly claim to be experts. And kind of implying that these blog posts are to blame, so the blog posts should be retracted due to those dishonest academic people? You’re making a very confusing point.
Not confusing. He's saying that watching Judge Judy for a week doesn't make you a lawyer. And when hiring, be careful because lots of people who claim to be experts are far from it.
Re: TensorFlow, Keras and deep learning, without a PhD
#107Earlier quoted context omitted.
I have self taught this material and have been working professionally in the field for some years now. It was primarily driven by the need to solve problems for autonomous systems I was creating. When I am asked how to do it I give the progression I followed. First have preferably a CS background but at least Calc 1&2, Linear Algebra, and University statistics, then: 1. Read "Artificial Intelligence A Modern Approach…
Thanks for sharing your learning path and congrats to your success. There are so many great resources out there that it's possible for anyone to become an expert. Unfortunately, people like you who are willing to put in the hard work seem to be the minority. All of your success is well-deserved and props to you. Just like you said, most gravitate towards the easy-to-understand videos and blogs instead of confronting…
> Did you feel that your specific problem put everything you were learning into context and made it easier to stay motivated?
Absolutely, having focus on finding better solutions to a single problem for multiple years certainly helped putting everything into context and staying motivated. That is the biggest problem I think, really learning this stuff like is needed to in order to solve new problems takes years of investment and just can't be done in a week or a month. Pretty hard to stay focused on something for that long without a goal and support of some sort.
The way that having the specific long term problem to solve really helped was always having that thread spinning in the back of my mind thinking about how something new could be applied to solve part of it and possibly trying it out. Also thinking about if certain approaches could even be practical at all.
I suppose that is probably fairly similar to grad school though.
Re: TensorFlow, Keras and deep learning, without a PhD
#108I'm doing deep learning without a data science background. Some of my current results are: * https://vo.codes * https://trumped.com The voices need better data curation and longer training, but some speakers such as David Attenborough are quite good. I've also built a real time streaming voice conversion system. I want to generalize it better so that it can be an actual product. I think it could be a killer app for D…
very nice work!
Re: TensorFlow, Keras and deep learning, without a PhD
#109Mandatory plug: do consider using PyTorch instead. It's far easier to pick up and work with. Easy things are easy, hard things are possible.
For what it's worth, I've found Pytorch to be much more rigid than TF. Maybe I just haven't found the easy way to do things. For example here's a function that applies an N×N box filter to all but the first 2 dimensions of a tensor (apologies to mobile users): def boxfilter(image, N=3): shape = image.shape image = tf.reshape(image, [1, shape[0], shape[1], -1]) C = image.shape[-1] conv = tf.nn.conv2d(image, tf.eye(C,…
You can almost 1:1 translate this by swapping "tf" and "torch". No need to use nn.Conv2d -- there's a functional API for all these layers:
https://pytorch.org/docs/master/nn.functional.html#conv2d
Torch doesn't have "same" padding, so you have to manually calculate the correct padding value for your input/output shapes.
Re: TensorFlow, Keras and deep learning, without a PhD
#110Earlier quoted context omitted.
I have self taught this material and have been working professionally in the field for some years now. It was primarily driven by the need to solve problems for autonomous systems I was creating. When I am asked how to do it I give the progression I followed. First have preferably a CS background but at least Calc 1&2, Linear Algebra, and University statistics, then: 1. Read "Artificial Intelligence A Modern Approach…
Thanks for sharing your learning path and congrats to your success. There are so many great resources out there that it's possible for anyone to become an expert. Unfortunately, people like you who are willing to put in the hard work seem to be the minority. All of your success is well-deserved and props to you. Just like you said, most gravitate towards the easy-to-understand videos and blogs instead of confronting…
> I wonder if your success also had something to do with the fact that you had a specific problem you were trying to solve.
As a side note, and I've found that this is one of the best ways to learn. Find a hard but obtainable problem and work towards it gathering all the knowledge you need along the way. What works for me is breaking down a project into a bunch of mini projects and so it becomes a lot easier to track progress and specify what I need to learn. That way even if you don't finish the project there's still a clear distinction of what you learned and can do.
I'm highly in favor of project oriented learning.