FastAI.jl
FastAI.jl copied to clipboard
FluxML
Repository of best practices for deep learning in Julia, inspired by fastai
I have added the code for a basic RNN Model for the task of time series classification. ```Julia > data, blocks = load(datarecipes()["ecg5000"]); > task = TSClassificationSingle(blocks, data); > model...
Hi, this code from `https://fluxml.ai/FastAI.jl/dev/documents/notebooks/quickstart.ipynb` fails with the latest FastAI.jl release: ```julia using FastAI data, blocks = loaddataset("imagenette2-320", (Image, Label)) task = ImageClassificationSingle(blocks, size=(256, 256)) learner = tasklearner(task, data, callbacks=[ToGPU(),...
Can do the following: ```julia lm = FastText.LanguageModel(true) classifier = FastText.TextClassifier(lm) FastText.train_classifier!(classifier) # Would throw an error as I haven't fully enabled the model to work with FastAI's data container....
How can collaborative filtering (with probabilistic matrix factorization) be implemented with FastAI.jl? Are there any snippets of this or plans to add it soon? I haven't seen examples of this...
Sometimes encodings need to be able to take into account batch information, as in a sequence learning task where samples in a batch should be padded to the length of...
I would sub-type [`MLUtils.AbstractDataContainer`](https://github.com/JuliaML/MLUtils.jl/blob/387b371287d00ce7e40a1be092db0dc4ad624b58/src/observation.jl#L75) to get some sensible defaults like `Base.iterate` defined on top of the MLUtils.jl interface.
CI fails on Windows at the moment due to file permission errors that occur when downloading datadeps. See for example this run: https://github.com/FluxML/FastAI.jl/runs/6899007003?check_suite_focus=true
Add simple character and word level tokenizers that conform to the LearnBase.jl `getobs`/`nobs` interfaces.
In addition to existing feature registries, FastAI.jl will be getting a model registry. The model registry should allow - domain and third-party packages to add additional models when loaded; -...
This adds interface tests to various interfaces in FastAI.jl. This allows - giving user-friendly error messages by performing checks in high-level functions - giving help when implementing an interface, and...