This year Google produced 5 different packages for seq2seq:
seq2seq (claimed to be general purpose but
inactive)
nmt (active but supposed to be just
about NMT probably)
legacy_seq2seq
(clearly legacy)
contrib/seq2seq
(not complete probably)
tensor2tensor (similar purpose, also
active development)
Which package is actually worth to use for the implementation? It seems they are all different approaches but none of them stable enough.
I've had too a headache about some issue, which framework to choose? I want to implement OCR using Encoder-Decoder with attention. I've been trying to implement it using legacy_seq2seq (it was main library that time), but it was hard to understand all that process, for sure it should not be used any more.
https://github.com/google/seq2seq: for me it looks like trying to making a command line training script with not writing own code. If you want to learn Translation model, this should work but in other case it may not (like for my OCR), because there is not enough of documentation and too little number of users
https://github.com/tensorflow/tensor2tensor: this is very similar to above implementation but it is maintained and you can add more of own code for ex. reading own dataset. The basic usage is again Translation. But it also enable such task like Image Caption, which is nice. So if you want to try ready to use library and your problem is txt->txt or image->txt then you could try this. It should also work for OCR. I'm just not sure it there is enough documentation for each case (like using CNN at feature extractor)
https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/seq2seq: apart from above, this is just pure library, which can be useful when you want to create a seq2seq by yourself using TF. It have a function to add Attention, Sequence Loss etc. In my case I chose that option as then I have much more freedom of choosing the each step of framework. I can choose CNN architecture, RNN cell type, Bi or Uni RNN, type of decoder etc. But then you will need to spend some time to get familiar with all the idea behind it.
https://github.com/tensorflow/nmt : another translation framework, based on tf.contrib.seq2seq library
From my perspective you have two option:
If you want to check the idea very fast and be sure that you are using very efficient code, use tensor2tensor library. It should help you to get early results or even very good final model.
If you want to make a research, not being sure how exactly the pipeline should look like or want to learn about idea of seq2seq, use library from tf.contrib.seq2seq.
Related
I'm new to the Machine-Learning (AI) technology. I'm developing a messenger app for Android/IOs where I would like to recommend the users based on the texts/word/conversation a product from a relative small product portfolio.
Example 1:
In case the user of the messenger writes a sentence including the words "vine", "dinner", "date" the AI should recommend a bottle of vine to the user.
Example 2:
In case the user of the app writes that he has drunk a good coffee this morning, the AI should recommend a mug to the user.
Example 3:
In case the user writes something about a cute boy she met last day, the AI should recommend a "teddy bear" to the user.
I'm a Software Developer since almost 20 year with experience in the development of C/C++/Java based application (Android and IOs apps) as well as some experience in Google Cloud Platform. The ML/AI technology is completely new to me. Okay, I know the basics (input data is needed to train the ML/AI system etc.), but I wonder If there is already a framework which could help me to develop such a system which solves the above described uses-case.
I would appreciate it, if you could give me some hints where and how to start.
Thank you and regards
It is definitely possible to implement such an application, in case you want to do it in Google Cloud you will need some understanding of Tensorflow.
First of all, I recommend to you to do the Machine Learning Crash Course, for a good introduction to Machine Learning and to start to familiarize yourself with TensorFlow. Afterwards I recommend to take a look into Tensorflow tutorials which will give you a more practical introduction to Tensorflow, and include various examples on building/training/testing models.
Once you are famirialized with Tensorflow, you can jump into learning how to run jobs in the Machine Learning engine, you can start by following the quickstart. The documentation includes detailed guides on how to use the ml-engine, plus multiple samples and tutorials.
Since I believe that your application would fall into the Recommender System type, here you can see an example model, in Google Cloud ML Engine, on how to recommend items to users based on his previous searches. In your case, you would have to build a model in order to recommend items to users based on his previous words in the sentence.
The second option, in case you don't want to go through the hassle of building a new model from scratch, would be to use the Google Cloud Natural Language API, which you can understand as pre-trained models using Google (incredibly big) data. In your case, I believe that the Content Classifying API would help you achieve what your application intends to do, however, the outputs (which you can see here) are limited to what the model was trained to do, and might not be specific enough for your application, however it is an easy solution and you can still profit of this API in order to extract labels/information and send it as input to another model.
I hope that these links provide you with some foundations on what is possible to do with Tensorflow in the ML Engine, and are useful to you.
Just a general question here, no reproducible example but thought this might be the right place anyway since its very software specific.
I am building a model which I want to convert to .tflite. It relies on tf.hub.text_embedding_collumn() for feature generation. When I convert to .tflite will this be captured such that the resulting model will take raw text as input rather than a sparse vector representation?
Would be good to know just generally before I invest too much time in this approach. Thanks in advance!
Currently I don't imagine this would work, as we do not support enough string ops to implement that. One approach would be to do this handling through a custom op, but implementing this custom op would require domain knowledge and mitigate the ease-of-use advance of using tf hub in the first place.
There is some interest in defining a set of hub operators that are verified to work well with tflite, but this is not yet ready.
I'm looking into designing a software platform that will aid linguists and anthropologists in their study of previously unstudied languages. Statistics show that around 1,000 languages exist that have never been studied by a person outside of their respective speaker groups.
My goal is to utilize TensorFlow to make a platform that will allow linguists to study and document these languages more efficiently, and to help them create written systems for the ones that don't have a written system already. One of their current methods of accomplishing such a task is three-fold: 1) Record a native speaker conversing in the language, 2) Listening to that recording and trying to transcribe it into the IPA, 3) From the phonetics, analyzing the phonemics and phonotactics of the language to eventually create a written system for the speaker.
My proposed platform would cut that research time down from a minimum of a year to a maximum of six months. Before I start, I have some questions...
What would be required to train TensorFlow to transcribe live audio into the IPA? Has this already been done? and if so, how would I utilize a previous solution for this project? Is a project like this even possible with TensorFlow? if not, what would you recommend using instead?
My apologies for the magnitude of this question. I don't have much experience in the realm of machine learning, as I am just beginning the research process for this project. Any help is appreciated!
I guess I will take a first shot at answering this. Since the question is pretty general, my answer will have to be pretty general as well.
What would be required. At the very least you would have to have a large dataset of pre-transcribed data. Ideally a large amount of spoken language audio mapped to characters in the phonetic alphabet, so the system could learn the sound of individual characters rather than whole transcribed words. If such a dataset doesn't exist, a less granular dataset could be used, mapping single words to their transcriptions. Then you would need a model, that is the actual neural network architecture implemented in code. And lastly you would need some computing resources. This is not something you can train casually, you would either have to buy some time in a cloud based machine learning framework (like Google Cloud ML) or build a fairly expensive machine to train at home.
Has this been done? I don't know. I don't think so. There have been published papers reporting various degrees of success at training systems to transcribe speech. Here is one, for example, http://deeplearning.stanford.edu/lexfree/lexfree.pdf It seems that since the alphabet you want to transcribe to is specifically designed to capture the way words sound rather than just write down the words you might have more success at training such a model.
Is it possible with TensorFlow. Yes, most likely. TensorFlow is well suited for implementing most modern deep learning architectures. Unless you end up designing some really weird and very original model for this purpose, TensorFlow should work just fine.
Edit: after some thought in part 1, you would have to use a dataset mapping spoken words to their transcriptions, since I expect that the same sound pronounced separately would be different from when the same sound is used in a word.
This has actually been done, albeit in PyTorch, by a group at CMU: https://github.com/xinjli/allosaurus
I have been playing around with building some deep learning models in Python and now I have a couple of outcomes I would like to be able to show friends and family.
Unfortunately(?), most of my friends and family aren't really up to the task of installing any of the advanced frameworks that are more or less necessary to have when creating these networks, so I can't just send them my scripts in the present state and hope to have them run.
But then again, I have already created the nets, and just using the finished product is considerably less demanding than making it. We don't need advanced graph compilers or GPU compute powers for the show and tell. We just need the ability to make a few matrix multiplications.
"Just" being a weasel word, regrettably. What I would like to do is convert the the whole model (connectivity,functions and parameters) to a model expressed in e.g. regular Numpy (which, though not part of standard library, is both much easier to install and easier to bundle reliably with a script)
I fail to find any ready solutions to do this. (I find it difficult to pick specific keywords on it for a search engine). But it seems to me that I can't be the first guy who wants to use a ready-made deep learning model on a lower-spec machine operated by people who aren't necessarily inclined to spend months learning how to set the parameters in an artificial neural network.
Are there established ways of transferring a model from e.g. Theano to Numpy?
I'm not necessarily requesting those specific libraries. The main point is I want to go from a GPU-capable framework in the creation phase to one that is trivial to install or bundle in the usage phase, to alleviate or eliminate the threshold the dependencies create for users without extensive technical experience.
An interesting option for you would be to deploy your project to heroku, like explained on this page:
https://github.com/sugyan/tensorflow-mnist
Has anyone seen any work done on this? I'd think this would be a reasonably common use-case. Train model in python, export the graph and map to a sequence of eigen instructions?
I don't believe anything like this is available, but it is definitely something that would be useful. There are some obstacles to overcome though:
Not all operations are implemented by Eigen.
We'd need to know how to generate code for all operations we want to support.
The glue code to allocate buffers and schedule work can get pretty gnarly.
It's still a good idea though, and it might get more attention posted as a feature request on https://github.com/tensorflow/tensorflow/issues/