documentation update (#2422)

* update docs

* update docs

* update docs

* fixes for mlp tutorial

* compat

* blitz update and model zoo page

Author: CarloLucibello

Project.toml

@@ -7,6 +7,8 @@ Adapt = "79e6a3ab-5dfb-504d-930d-738a2a938a0e"
 ChainRulesCore = "d360d2e6-b24c-11e9-a2a3-2a2ae2dbcce4"
 Compat = "34da2185-b29b-5c13-b0c7-acf172513d20"
 Functors = "d9f16b24-f501-4c13-a1f2-28368ffc5196"
+ImageCore = "a09fc81d-aa75-5fe9-8630-4744c3626534"
+ImageShow = "4e3cecfd-b093-5904-9786-8bbb286a6a31"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 MLUtils = "f1d291b0-491e-4a28-83b9-f70985020b54"
 MacroTools = "1914dd2f-81c6-5fcd-8719-6d5c9610ff09"
@@ -48,7 +50,7 @@ MacroTools = "0.5"
 Metal = "0.5, 1"
 NNlib = "0.9.1"
 OneHotArrays = "0.2.4"
-Optimisers = "0.3.2"
+Optimisers = "0.3.3"
 Preferences = "1"
 ProgressLogging = "0.1"
 Reexport = "1.0"
@@ -77,7 +79,4 @@ Tracker = "9f7883ad-71c0-57eb-9f7f-b5c9e6d3789c"
 cuDNN = "02a925ec-e4fe-4b08-9a7e-0d78e3d38ccd"
 
 [targets]
-test = ["Test", "Documenter", "IterTools", "LinearAlgebra", "FillArrays", 
-        "ComponentArrays", "BSON", "Pkg", "CUDA", "cuDNN", "Metal", "AMDGPU", 
-        "Enzyme", "FiniteDifferences", "Tracker"]
-
+test = ["Test", "Documenter", "IterTools", "LinearAlgebra", "FillArrays", "ComponentArrays", "BSON", "Pkg", "CUDA", "cuDNN", "Metal", "AMDGPU", "Enzyme", "FiniteDifferences", "Tracker"]

docs/Project.toml

@@ -16,4 +16,4 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 Zygote = "e88e6eb3-aa80-5325-afca-941959d7151f"
 
 [compat]
-Documenter = "0.27"
+Documenter = "1.3"

docs/make.jl

@@ -13,48 +13,48 @@ makedocs(
         # You could read this end-to-end, or skip to what you need.
         # Aim is to cover each new concept exactly once (but not list all variants).
         # Hard to invent further divisions which aren't more confusing than helpful?
-            "Quick Start" => "models/quickstart.md",
-            "Fitting a Line" => "models/overview.md",
-            "Gradients and Layers" => "models/basics.md",
-            "Training" => "training/training.md",
-            "Recurrence" => "models/recurrence.md",
-            "GPU Support" => "gpu.md",
-            "Saving & Loading" => "saving.md",
-            "Performance Tips" => "performance.md",
+            "Quick Start" => "guide/models/quickstart.md",
+            "Fitting a Line" => "guide/models/overview.md",
+            "Gradients and Layers" => "guide/models/basics.md",
+            "Custom Layers" => "guide/models/custom_layers.md",
+            "Training" => "guide/training/training.md",
+            "Recurrence" => "guide/models/recurrence.md",
+            "GPU Support" => "guide/gpu.md",
+            "Saving & Loading" => "guide/saving.md",
+            "Performance Tips" => "guide/performance.md",
         ],
         "Ecosystem" => "ecosystem.md",
         "Reference" => [
         # This essentially collects docstrings, with a bit of introduction.
-            "Built-in Layers" => "models/layers.md",
-            "Activation Functions" => "models/activation.md",
-            "Weight Initialisation" => "utilities.md",
-            "Loss Functions" => "models/losses.md",
-            "Training API" => "training/reference.md",
-            "Optimisation Rules" => "training/optimisers.md",
-            "Shape Inference" => "outputsize.md",
-            "Flat vs. Nested" => "destructure.md",
-            "Callback Helpers" => "training/callbacks.md",
-            "Gradients -- Zygote.jl" => "training/zygote.md",
-            "Batching Data -- MLUtils.jl" => "data/mlutils.md",
-            "OneHotArrays.jl" => "data/onehot.md",
-            "Low-level Operations -- NNlib.jl" => "models/nnlib.md",
-            "Nested Structures -- Functors.jl" => "models/functors.md",
+            "Built-in Layers" => "reference/models/layers.md",
+            "Activation Functions" => "reference/models/activation.md",
+            "Weight Initialisation" => "reference/utilities.md",
+            "Loss Functions" => "reference/models/losses.md",
+            "Training API" => "reference/training/reference.md",
+            "Optimisation Rules" => "reference/training/optimisers.md",
+            "Shape Inference" => "reference/outputsize.md",
+            "Flat vs. Nested" => "reference/destructure.md",
+            "Callback Helpers" => "reference/training/callbacks.md",
+            "Gradients -- Zygote.jl" => "reference/training/zygote.md",
+            "Batching Data -- MLUtils.jl" => "reference/data/mlutils.md",
+            "OneHotArrays.jl" => "reference/data/onehot.md",
+            "Low-level Operations -- NNlib.jl" => "reference/models/nnlib.md",
+            "Nested Structures -- Functors.jl" => "reference/models/functors.md",
          ],
         "Tutorials" => [
         # These walk you through various tasks. It's fine if they overlap quite a lot.
         # All the website tutorials can move here, perhaps much of the model zoo too?
         # Or perhaps those should just be trashed, model zoo versions are newer & more useful.
             "Linear Regression" => "tutorials/linear_regression.md",
             "Logistic Regression" => "tutorials/logistic_regression.md",
+            "Model Zoo" => "tutorials/model_zoo.md",
             #=
-            "Julia & Flux: 60 Minute Blitz" => "tutorials/2020-09-15-deep-learning-flux.md",
-            "Multi-layer Perceptron" => "tutorials/2021-01-26-mlp.md",
+            # "Multi-layer Perceptron" => "tutorials/mlp.md",
+            # "Julia & Flux: 60 Minute Blitz" => "tutorials/blitz.md",
             "Simple ConvNet" => "tutorials/2021-02-07-convnet.md",
             "Generative Adversarial Net" => "tutorials/2021-10-14-vanilla-gan.md",
             "Deep Convolutional GAN" => "tutorials/2021-10-08-dcgan-mnist.md",
             =#
-            # Not really sure where this belongs... some in Fluxperimental, aim to delete?
-            "Custom Layers" => "models/advanced.md",  # TODO move freezing to Training
         ],
     ],
     format = Documenter.HTML(
@@ -63,19 +63,10 @@ makedocs(
         assets = ["assets/flux.css"],
         prettyurls = get(ENV, "CI", nothing) == "true"
     ),
-    doctest = false, 
-    # linkcheck = true,
-    checkdocs = :exports,
-    # strict = true,
-    # strict = [
-    #     :cross_references,
-    #     :missing_docs,
-    #     :doctest,
-    #     :linkcheck,
-    #     :parse_error,
-    #     :example_block,
-    #     :autodocs_block, :docs_block, :eval_block, :example_block, :footnote, :meta_block, :setup_block
-    # ],
+    doctest = false,   # done later
+    checkdocs = :none, # :exports # Do not check if all functions appear in the docs
+                                  # since it considers all packages
+    warnonly = [:cross_references]
 )
 
 doctest(Flux) # only test Flux modules

docs/src/tutorials/2021-02-07-convnet.md renamed to docs/old_tutorials/2021-02-07-convnet.md

@@ -109,7 +109,7 @@ dcgan_init(shape...) = randn(Float32, shape) * 0.02f0
 ```julia
 function Generator(latent_dim)
     Chain(
-        Dense(latent_dim, 7*7*256, bias=false),
+        Dense(latent_dim  => 7*7*256, bias=false),
         BatchNorm(7*7*256, relu),
 
         x -> reshape(x, 7, 7, 256, :),

docs/src/tutorials/2021-10-08-dcgan-mnist.md renamed to docs/old_tutorials/2021-10-08-dcgan-mnist.md

@@ -96,13 +96,13 @@ calling the model in a gradient context. As a final non-linearity, we use the
 `sigmoid` activation function.
 
 ```julia
-discriminator = Chain(Dense(n_features, 1024, x -> leakyrelu(x, 0.2f0)),
+discriminator = Chain(Dense(n_features => 1024, x -> leakyrelu(x, 0.2f0)),
                         Dropout(0.3),
-                        Dense(1024, 512, x -> leakyrelu(x, 0.2f0)),
+                        Dense(1024 => 512, x -> leakyrelu(x, 0.2f0)),
                         Dropout(0.3),
-                        Dense(512, 256, x -> leakyrelu(x, 0.2f0)),
+                        Dense(512 => 256, x -> leakyrelu(x, 0.2f0)),
                         Dropout(0.3),
-                        Dense(256, 1, sigmoid)) |> gpu
+                        Dense(256 => 1, sigmoid)) |> gpu
 ```
 
 Let's define the generator in a similar fashion. This network maps a latent
@@ -113,9 +113,9 @@ the training data onto.
 
 ```julia
 generator = Chain(Dense(latent_dim, 256, x -> leakyrelu(x, 0.2f0)),
-                    Dense(256, 512, x -> leakyrelu(x, 0.2f0)),
-                    Dense(512, 1024, x -> leakyrelu(x, 0.2f0)),
-                    Dense(1024, n_features, tanh)) |> gpu
+                    Dense(256 => 512, x -> leakyrelu(x, 0.2f0)),
+                    Dense(512 => 1024, x -> leakyrelu(x, 0.2f0)),
+                    Dense(1024 => n_features, tanh)) |> gpu
 ```