Piero Molino
posted to
uber/ludwig
Contributing to Ludwig - New Developer@desikan95 thank you really much for your availability! Really appreciated. Regarding data soruces, in the recent v0.3 version of Ludwig we added many new supported formats already, and are still working on adding even more and improve the preprocessing ... |
Piero Molino
posted to
uber/ludwig
Contributing to Ludwig - New Developerthank you really much for your interest and your willingness to get involved!I believe the best way to get started without the need to get all the nitty gritty details of Ludwig internals is helping out with tests. It's a great way to gradually get acqua... |
Piero Molino
posted to
uber/ludwig
Predict the sequence of labels for sentences in documents.Hi Aris, there could be more than one way to approach this problem.In my opnion the most traightforward way would be to split the abstract in sentences and feeding each sentence as input with the label as output.This may end up working fine, but does no... |
Piero Molino
posted to
uber/ludwig
Can't get Ludwig to work in a pure Python (non Bash) configuration - Any pointers on how to generate the config file?Hi Charlie, |
Piero Molino
posted to
uber/ludwig
Reproduce COTA using LudwingHey Lucas,funny enough I'm the person giving that talk :)And actually COTA was the first model developed with Ludwig, so definitely yes, you can reproduce exactly that architecture in Ludwig.In your model definition you would need to have the inp... |
Piero Molino
posted to
uber/ludwig
Can we implement Ludwig for time forecasting classification ?Hi Sutirtha,a couple things: you are getting a few erors when loading the data, so I'm not really sure in which order you are running the cells and what actually is the problem. if train is not none this should work without problems.Also, the output seems ... |
Piero Molino
posted to
uber/ludwig
Can we implement Ludwig for time forecasting classification ?Hi Shyam,Ludwig is a toolbox for deep learning models. You can obtain something similar to arima using a specific combiner after a timeseries input feature with a passthrough encoder, but that's not really the intent of the library. If you want to use arim... |
Piero Molino
posted to
uber/ludwig
Can we implement Ludwig for time forecasting classification ?Hi Sutirtha,yes you can definitely do time series classification with Ludwig.Assuming your 621 columns are numbers at different times, you'll have to combine them in a single column with space delimiters. Like three columns with values 4, 2, 1 will become ... |
Piero Molino
posted to
uber/ludwig
Unable to work with Ludwig. NameError: name 'ludwig' is not definedHi, the message means that Ludwig is not available in your environment. Pl... |
Piero Molino
posted to
uber/ludwig
How to finish Ludwig instalationPython 3.8 has only very recently been supported for TF2, TF1 still needs python 3.7. |
Piero Molino
posted to
uber/ludwig
How to finish Ludwig instalationWhich version of python are you using?It may be that some packages are not available with some versions of python.Anyway this isn't really a problem with Ludwig, but with TensorFlow.Let's try to figure out if it has to do with the specifics of your install... |
Piero Molino
posted to
uber/ludwig
Sequence or sequence-to-sequence prediction with Ludwig?Hi Jari, glad to hear things are working! For me to understan... |
Piero Molino
posted to
uber/ludwig
Sequence or sequence-to-sequence prediction with Ludwig?Hi Jari, a couple things here:
|
Piero Molino
posted to
uber/ludwig
Sequence or sequence-to-sequence prediction with Ludwig?Please post what you want to achieve, you tried and what errors you got, otherwise it is difficult for anyone to try to help. |
Piero Molino
posted to
uber/ludwig
AttributeError: type object 'Callable' has no attribute '_abc_registry' in python 3.7That's great news :) Let me know if there are other problems. |
Piero Molino
posted to
uber/ludwig
AttributeError: type object 'Callable' has no attribute '_abc_registry' in python 3.7As you are using python 3.7, typing is not needed. You should be ok by just removing it from the virtualenv before creating the neuropod. |
Piero Molino
posted to
uber/ludwig
AttributeError: type object 'Callable' has no attribute '_abc_registry' in python 3.7Hi Peng, this looks like a problem with the After looking at the alexa repo you linked, in their case they were explicitly having as a dependency, which is not the case in Lu... |
Piero Molino
posted to
uber/ludwig
What is a good starting number for confidence_penaltyHi SJF,I’ll try to improve the doc on that. Anyway, the intuition is that the more penalty you add, the more you expect your predictions to be entropic and less sharp. This may be useful when you have noisy labels you don’t trust too much.As per the spec... |
Piero Molino
posted to
uber/ludwig
Displaying the architecture of networkyou can use the tensorboard for that, just point it to the model/log directory |
Piero Molino
posted to
uber/ludwig
Export model as SavedModelThe JSON file contains all the mappings (both classes and text) that are needed ;) |
Piero Molino
posted to
uber/ludwig
Automated Feature selectionI think the main problem with this is the fact that at the moment there is a 1:1 mapping between input columns and placeholders in tf, if one adds some process that would map from one input to potentially several inputs, that would require some work. Anyw... |
Piero Molino
posted to
uber/ludwig
Export model as SavedModelGot it, will take a closer look then. |
Piero Molino
posted to
uber/ludwig
Export model as SavedModelReading the example, this part:
|
Piero Molino
posted to
uber/ludwig
Export model as SavedModelHi Jad, thank you for asking about this. I'm not familiar with that interface to be honest, i have to do some digging myself to figura out what one should do in order to make make it work.My concern by the way is always the same: preprocessing and postproc... |
Piero Molino
posted to
uber/ludwig
How to add embedding layer to vectorize text?Ludwig already vectorizes your text and looks up embeddings and does everything for you. You can specify pretrained embeddings too. Please look at the sequential encoders for more details. |