Merge pull request #53 from paganpasta/dev

Dev
paganpasta · Sep 3, 2022 · acc222c · acc222c
2 parents 47d3fb9 + edcbb6c
commit acc222c
Show file tree

Hide file tree

Showing 6 changed files with 8 additions and 45 deletions.
diff --git a/README.md b/README.md
@@ -1,6 +1,6 @@
 # Eqxvision
 [![PyPI](https://img.shields.io/pypi/v/eqxvision?style=flat-square)](https://pypi.org/project/eqxvision/) 
-[![Github](https://img.shields.io/badge/Documentation-link-yellowgreen)](https://eqxvision.readthedocs.io/en/latest/)
+[![Github](https://img.shields.io/badge/Documentation-link-yellowgreen?style=flat-square)](https://eqxvision.readthedocs.io/en/latest/)
 [![GitHub Release Date](https://img.shields.io/github/release-date/paganpasta/eqxvision?style=flat-square)](/~https://github.com/paganpasta/eqxvision/releases) 
 [![GitHub](https://img.shields.io/github/license/paganpasta/eqxvision?style=flat-square)](/~https://github.com/paganpasta/eqxvision/blob/main/LICENSE.md)
 

diff --git a/docs/getting_started/Adversarial_Attack.ipynb b/docs/getting_started/Adversarial_Attack.ipynb
@@ -18,18 +18,6 @@
   }
  },
  "cells": [
-  {
-   "cell_type": "markdown",
-   "source": [
-    "<a href=\"https://colab.research.google.com/github/paganpasta/eqxvision/blob/tutorial%2Fadv/Adversarial_Attack.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
-   ],
-   "metadata": {
-    "collapsed": false,
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   }
-  },
   {
    "cell_type": "markdown",
    "source": [

diff --git a/docs/getting_started/Self-Attention Maps.ipynb b/docs/getting_started/Self-Attention Maps.ipynb
@@ -21,19 +21,6 @@
   "gpuClass": "standard"
  },
  "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "view-in-github",
-    "colab_type": "text",
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   },
-   "source": [
-    "<a href=\"https://colab.research.google.com/github/paganpasta/eqxvision/blob/documentation%2Fgetting_started%2Fself-attention/docs/getting_started/vit_attention.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
-   ]
-  },
   {
    "cell_type": "markdown",
    "source": [

diff --git a/docs/getting_started/Transfer_Learning.ipynb b/docs/getting_started/Transfer_Learning.ipynb
@@ -709,19 +709,6 @@
   }
  },
  "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "view-in-github",
-    "colab_type": "text",
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   },
-   "source": [
-    "<a href=\"https://colab.research.google.com/github/paganpasta/eqxvision/blob/documentation%2Fgetting_started%2Fself-attention/docs/getting_started/Transfer_Learning.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
-   ]
-  },
   {
    "cell_type": "markdown",
    "source": [

diff --git a/docs/index.md b/docs/index.md
@@ -42,12 +42,13 @@ pip install eqxvision
 ## Get Started!
 
 Start with any one of these easy to follow [tutorials](getting_started/Transfer_Learning.ipynb). 
-       
+
 ## Tips
-- Use `@equinox.jit_filter` instead of `@jax.jit`
-- Use `jax.{v,p}map` with `axis_name='batch'` for all models
-- Don't forget to switch to `inference` mode for evaluations
-- Wrap the model for `Optax` initialisation with `eqx.filter(net, eqx.is_array)`.
+- Better to use `@equinox.filter_jit` instead of `@jax.jit`.
+- Use `jax.{v,p}map` with `axis_name='batch'` when using models that use batch normalisation.
+- Don't forget to switch to `inference` mode for evaluations. (`model = eqx.tree_inference(model)`)
+- Initialise Optax optimisers as `optim.init(eqx.filter(net, eqx.is_array))`. ([See here.](https://docs.kidger.site/equinox/faq/#optax-is-throwing-an-error))
+
 
 
 

diff --git a/eqxvision/__init__.py b/eqxvision/__init__.py
@@ -1,4 +1,4 @@
 r"""Root package info."""
-__version__ = "0.1.11"
+__version__ = "0.1.12"
 
 from . import layers, models, utils