Mnist github version <> version in week 6 video

MTAU · December 28, 2017, 1:19am

Week 6 video shows a section in the mnist.ipynb notebook “Pseudo-labeling”.

The github repo version of mnist does not include the code shown in the video.

fastai/courses/blob/master/deeplearning1/nbs/mnist.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using gpu device 2: GeForce GTX TITAN X (CNMeM is enabled with initial size: 90.0% of memory, cuDNN 4007)\n"
     ]
    }
   ],
   "source": [
    "from theano.sandbox import cuda\n",
    "cuda.use('gpu2')"

This file has been truncated. show original

The lesson7 notebook does include a “Pseudo-labeling” section.

github.com

fastai/courses/blob/master/deeplearning1/nbs/lesson7.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fisheries competition"
   ]
  },
  {
   "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/).  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."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {

This file has been truncated. show original

is there another github repo I should be referring to?