Update to FluxTraining.jl v0.2.0 interfaces (#134)

* Revamp learning rate finder

* Move notebook files

* update  `finetune!` and notebooks

* Add weight decay to `fitonecycle!`

* Add some docstrings

Author: lorenzoh

.gitignore

@@ -3,4 +3,4 @@ test/Manifest.toml
 docs/Manifest.toml
 development/**
 Manifest.toml
-docs/**/*.jld2
+**/*.jld2

Project.toml

@@ -45,7 +45,7 @@ FilePathsBase = "0.9"
 FileTrees = "0.3"
 FixedPointNumbers = "0.8"
 Flux = "0.12"
-FluxTraining = "0.1, 0.2"
+FluxTraining = "0.2"
 JLD2 = "0.4"
 LearnBase = "0.3"
 MLDataPattern = "0.5"

docs/background/datapipelines.md

@@ -26,7 +26,7 @@ using DataLoaders: batchviewcollated
 using FastAI
 using FastAI.Datasets
 
-data = loadtaskdata(datasetpath("imagenette2-320"), ImageClasssification)
+data = loadtaskdata(datasetpath("imagenette2-320"), ImageClassification)
 method = ImageClassification(Datasets.getclassesclassification("imagenette2-320"), (224, 224))
 
 # maps data processing over `data`
@@ -68,7 +68,7 @@ using FastAI
 using FastAI.Datasets
 using FluxTraining: fitbatchphase!
 
-data = loadtaskdata(datasetpath("imagenette2-320"), ImageClasssification)
+data = loadtaskdata(datasetpath("imagenette2-320"), ImageClassification)
 method = ImageClassification(Datasets.getclassesclassification("imagenette2-320"), (224, 224))
 
 learner = methodlearner(method, data, xresnet18())
@@ -100,7 +100,7 @@ using FastAI.Datasets
 
 # Since loading times can vary per observation, we'll average the measurements over multiple observations
 N = 10
-data = datasubset(shuffleobs(loadtaskdata(datasetpath("imagenette2"), ImageClasssification), 1:N))
+data = datasubset(shuffleobs(loadtaskdata(datasetpath("imagenette2"), ImageClassification), 1:N))
 method = ImageClassification(Datasets.getclassesclassification("imagenette2-320"), (224, 224))
 
 # Time it takes to load an `(image, class)` observation
@@ -132,13 +132,13 @@ If the data loading is still slowing down training, you'll probably have to spee
 For many computer vision tasks, you will resize and crop images to a specific size during training for GPU performance reasons. If the images themselves are large, loading them from disk itself can take some time. If your dataset consists of 1920x1080 resolution images but you're resizing them to 256x256 during training, you're wasting a lot of time loading the large images. *Presizing* means saving resized versions of each image to disk once, and then loading these smaller versions during training. We can see the performance difference using ImageNette since it comes in 3 sizes: original, 360px and 180px.
 
 ```julia
-data_orig = loadtaskdata(datasetpath("imagenette2"), ImageClasssification)
+data_orig = loadtaskdata(datasetpath("imagenette2"), ImageClassification)
 @time eachobsparallel(data_orig, buffered = false)
 
-data_320px = loadtaskdata(datasetpath("imagenette2-320"), ImageClasssification)
+data_320px = loadtaskdata(datasetpath("imagenette2-320"), ImageClassification)
 @time eachobsparallel(data_320px, buffered = false)
 
-data_160px = loadtaskdata(datasetpath("imagenette2-160"), ImageClasssification)
+data_160px = loadtaskdata(datasetpath("imagenette2-160"), ImageClassification)
 @time eachobsparallel(data_160px, buffered = false)
 ```
 

docs/data_containers.md

@@ -18,7 +18,7 @@ using FastAI.Datasets: datasetpath, loadtaskdata
 
 NAME = "imagenette2-160"
 dir = datasetpath(NAME)
-data = loadtaskdata(dir, ImageClasssification)
+data = loadtaskdata(dir, ImageClassification)
 ```
 
 A data container is any type that holds observations of data and allows us to load them with `getobs` and query the number of observations with `nobs`:

docs/howto/augmentvision.md

@@ -10,7 +10,7 @@ using FastAI
 using CairoMakie; CairoMakie.activate!(type="png")
 
 dir = joinpath(datasetpath("dogscats"), "train")
-data = loadtaskdata(dir, ImageClasssification)
+data = loadtaskdata(dir, ImageClassification)
 classes = Datasets.getclassesclassification(dir)
 method = ImageClassification(classes, (100, 128))
 xs, ys = FastAI.makebatch(method, data, fill(4, 9))

docs/howto/logtensorboard.md

@@ -33,7 +33,7 @@ callbacks = [
     Metrics(accuracy)
 ]
 
-data = Datasets.loadtaskdata(Datasets.datasetpath("imagenette2-160"), ImageClasssification)
+data = Datasets.loadtaskdata(Datasets.datasetpath("imagenette2-160"), ImageClassification)
 method = ImageClassification(Datasets.getclassesclassification("imagenette2-160"), (160, 160))
 learner = methodlearner(method, data, Models.xresnet18(), callbacks...)
 fitonecycle!(learner, 5)

docs/interfaces.md

@@ -33,6 +33,7 @@ For visualizing observations and predictions using [Makie.jl](https://github.com
 - Required methods:
     - [`plotsample!`](#)
     - [`plotxy!`](#)
+    - [`plotprediction!`](#)
 - Enables use of:
     - [`plotsamples`](#)
     - [`plotbatch`](#)

docs/introduction.md

@@ -7,13 +7,13 @@
 using FastAI
 ```
 
-On the [quickstart page](quickstart.ipynb), we showed how to train models on common tasks in a few lines of code:
+On the [quickstart page](../notebooks/quickstart.ipynb), we showed how to train models on common tasks in a few lines of code:
 
 ```julia
 using FastAI
 
 path = datasetpath("imagenette2-160")
-dataset = loadtaskdata(path, ImageClasssification)
+dataset = loadtaskdata(path, ImageClassification)
 method = ImageClassification(Datasets.getclassesclassification("imagenette2-160"), (160, 160))
 dls = methoddataloaders(dataset, method, 16)
 model = methodmodel(method, Models.xresnet18())
@@ -28,7 +28,7 @@ Let's unpack each line.
 {cell=main}
 ```julia
 path = datasetpath("imagenette2-160")
-dataset = loadtaskdata(path, ImageClasssification)
+dataset = loadtaskdata(path, ImageClassification)
 ```
 
 These two lines download and load the [ImageNette](https://github.com/fastai/imagenette) image classification dataset, a small subset of ImageNet with 10 different classes. `dataset` is a [data container](data_containers.md) that can be used to load individual observations, here of images and the corresponding labels. We can use `getobs(dataset, i)` to load the `i`-th observation and `nobs` to find out how many observations there are.

docs/learning_methods.md

@@ -27,7 +27,7 @@ Before we get started, let's load up a [data container](data_containers.md) that
 using FastAI
 using FastAI.Datasets
 DATASET = "imagenette2-160"
-data = Datasets.loadtaskdata(Datasets.datasetpath(DATASET), ImageClasssification)
+data = Datasets.loadtaskdata(Datasets.datasetpath(DATASET), ImageClassification)
 image, class = getobs(data, 1)
 image
 ```

docs/methods/imageclassification.md

@@ -19,7 +19,7 @@ end
 using CairoMakie
 using FastAI
 dir = joinpath(datasetpath("dogscats"), "train")
-data = loadtaskdata(dir, ImageClasssification)
+data = loadtaskdata(dir, ImageClassification)
 samples = [getobs(data, i) for i in rand(1:nobs(data), 9)]
 classes = Datasets.getclassesclassification(dir)
 method = ImageClassification(classes, (128, 128))