Merge branch 'master' of github.com:fastai/courses

deeplearning1/nbs/imagenet_batchnorm.ipynb

@@ -1,5 +1,12 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "This notebook explains how to add batch normalization to VGG.  The code shown here is implemented in [vgg_bn.py](https://github.com/fastai/courses/blob/master/deeplearning1/nbs/vgg16bn.py), and there is a version of ``vgg_ft`` (our fine tuning function) with batch norm called ``vgg_ft_bn`` in [utils.py](https://github.com/fastai/courses/blob/master/deeplearning1/nbs/utils.py)."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -1089,6 +1096,15 @@
     "conv_model.save_weights(path+'models/inet_224squash_bn.h5')"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "The code shown here is implemented in [vgg_bn.py](https://github.com/fastai/courses/blob/master/deeplearning1/nbs/vgg16bn.py), and there is a version of ``vgg_ft`` (our fine tuning function) with batch norm called ``vgg_ft_bn`` in [utils.py](https://github.com/fastai/courses/blob/master/deeplearning1/nbs/utils.py)."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -1100,6 +1116,7 @@
   }
  ],
  "metadata": {
+  "anaconda-cloud": {},
   "kernelspec": {
    "display_name": "Python [default]",
    "language": "python",

deeplearning1/nbs/lesson7.ipynb

@@ -11,7 +11,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "In this notebook we're going to investigate a range of different architectures for the [Kaggle fisheries competition](https://www.kaggle.com/c/the-nature-conservancy-fisheries-monitoring/)."
+    "In this notebook we're going to investigate a range of different architectures for the [Kaggle fisheries competition](https://www.kaggle.com/c/the-nature-conservancy-fisheries-monitoring/).  The video states that vgg.py and ``vgg_ft()`` from utils.py have been updated to include VGG with batch normalization, but this is not the case.  We've instead created a new file [vgg_bn.py](https://github.com/fastai/courses/blob/master/deeplearning1/nbs/vgg16bn.py) and an additional method ``vgg_ft_bn()`` (which is already in utils.py) which we use in this notebook."
    ]
   },
   {
@@ -236,7 +236,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We start with our usual VGG approach."
+    "We start with our usual VGG approach.  We will be using VGG with batch normalization.  We explained how to add batch normalization to VGG in the [imagenet_batchnorm notebook](https://github.com/fastai/courses/blob/master/deeplearning1/nbs/imagenet_batchnorm.ipynb).  VGG with batch normalization is implemented in [vgg_bn.py](https://github.com/fastai/courses/blob/master/deeplearning1/nbs/vgg16bn.py), and there is a version of ``vgg_ft`` (our fine tuning function) with batch norm called ``vgg_ft_bn`` in [utils.py](https://github.com/fastai/courses/blob/master/deeplearning1/nbs/utils.py)."
    ]
   },
   {