Share your work here ✅

radek · October 23, 2018, 4:16pm

I put together a Kaggle competition starter pack for a competition that is currently under way - Quick, Draw! There are still six more weeks before it finishes so that is plenty of time to play around.

You can find the starter pack on github here.

The competition has a lot of good things going for it. First of all, there do not seem to be any issues with the data. It is also one of the unusual competitions where you can let your imagination run wild - many, many different models can be useful here, potentially including RNNs. Given the submission format it should also be really easy to come up with some interesting way to ensemble the data - might be a fun thing to work on in a group.

If you have any starter code or competition related questions - please go to the thread on Kaggle forums and let’s please discuss it there. This way others who might have a similar question could also benefit. Same goes for sharing code - if there is any competition related code you would like to share, please do it in the open - sharing privately is against competition rules.

Enjoy and beware - these competitions can be addictive

PS. I have not made any references to class materials as to not share links before MOOC launch. The training notebook is based line for line on the lesson 1 lecture nb. Hope Jeremy will forgive me for the lack of proper attribution this time around.

jeremy · October 23, 2018, 5:12pm

Thanks for mentioning that! I think it would be nice to say “this code is based on code from a fast.ai MOOC that will be publicly available in Jan 2019” or something.

Blanche · October 24, 2018, 9:23am

Is getting 99,9% accuracy on MNIST any good?
I’ve played a bit with first notebook and got that after some experiments accuracy. From what I’ve found this seems to be better than paper results: https://rodrigob.github.io/are_we_there_yet/build/classification_datasets_results.html

hkristen · October 24, 2018, 10:58am

Hi everybody!

While watching lesson 1 of the new course I was wondering where to get a big forest/nature related dataset to build an image classifier on, as this is the domain I am coming from.

I finally found the ImageCLEF Plant Identification Challenge 2013 which provides a already labeld training dataset containing images of 250 plant species on 10485 images (25GB). Most of the images are showing leafs but there also images of flowers, fruit, stem & the entire plant.

For the classifier I used the images with a uniform background (category=SheetAsBAckground) which only contain leaves: 4921 samples and 124 classes.

I started with training a pretrained resnet34 and already got the error rate down to ~3% after 17 epochs. Interestingly fine tuning didn´t help to improve accuracy/loss drastically.

What to do next:

Train network for category=NaturalBackground
Maybe exclude classes with samples < 10?

Below you can find a GIST of the notebook I used. I am looking forward to your feedback on what I can improve or what else could be done with this dataset

gist.github.com

https://gist.github.com/hkristen/696d5111692c25c9ae0d6949501e9215

lesson1-imageclef2013_plant_leaf_types.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%reload_ext autoreload\n",
    "%autoreload 2\n",

This file has been truncated. show original

Cheers,
Harald

devforfu · October 24, 2018, 11:15am

Note that Quick Draw competition goes in two versions: (1) simplified and (2) raw. And the later one includes approx. 66GB of data. So in case if you’re downloading the data, you’d better specify which version of the dataset you’re going to use:

kaggle competitions download quickdraw-doodle-recognition -p ~/data/doodle -f test_simplified.csv
kaggle competitions download quickdraw-doodle-recognition -p ~/data/doodle -f train_simplified.zip

poppingtonic · October 29, 2018, 8:24pm

I’ve made a notebook to classify food pictures from the food-101 dataset. Here’s the notebook in nbviewer, and here’s the repo if you want to see the other experiments I’ve been running. I built a French language model using v1, and also have another experiment with food-101.

Benoit_c · October 24, 2018, 12:58pm

Hello I’ve made a Notebook to classify airplaines, more info here : https://forums.fast.ai/t/lesson-1-beat-google-auto-ml-at-b747-vs-a380/27764

keyurparalkar · October 24, 2018, 2:42pm

I have written a synopsis of how to approach a given problem i.e. dataset and to get the end results. This is blog is at preliminary stage so suggestions are highly appreciated.
BLOG: https://medium.com/@keur.plkar/fast-ai-course-part1v3-e004bcc919d8

brismith · October 24, 2018, 3:15pm

I’ll do a broader write up on my blog as I progress - but my first attempt at differentiating downloaded images from Google (thanks @lindyrock for the tip) of American football, soccer, rugby, Australian rules football, ice hockey, field hockey, lacrosse, baseball, cricket, boxing, wrestling and athletics gave some fun results. A few hundred images of each, ResNet34 and just 4 cycles gave me 20% error rate. Initial observations - my data isn’t that clean - some search results weren’t what I was looking for (soccer/football - ice and field hockey) - so reviewing and cleaning datasets will help. Confusion matrix much as expected -

with the hockeys, wrestling/boxing and football/soccer most confused. Surprisingly rugby and Australian rules not as bad. A fun start!

fadhli · October 24, 2018, 3:20pm

Was looking at this competitions the other day. Thanks for sharing your work.

kai · October 24, 2018, 3:25pm

I wrote a fun little notebook to create an image classifier just with specifying keywords. It’s using the google image search to find images for those keywords and trains a classifier on those images:

Classify images with Keywords

I tried to advance the emerging field of classifying Hot Dogs by specifically adding “Corn Dogs” to the portfolio.

Maybe it’s time for the ImageDataBunch.from_google Method

Kaushikjais · October 24, 2018, 3:28pm

hey how did you added the dataset .

Kaushikjais · October 24, 2018, 3:37pm

in line 3 how did you add the food data . like in Lesson-1 notebook , jeremy has defined a url constant for pet dataset .

poppingtonic · October 24, 2018, 4:38pm

I had downloaded the data separately, but I’ll update the notebook with the constant.

Edit: Done

Kaushikjais · October 24, 2018, 4:39pm

have you put the data in a separate folder and just passed the path of that folder in line 3?

ritika26 · October 24, 2018, 4:45pm

@radek .Thank you for sharing your work. It is very helpful.

poppingtonic · October 24, 2018, 4:46pm

That folder is where I had downloaded it anyway, so the result will be the same, if my reading of the code is right.

Taka · October 24, 2018, 7:33pm

I really needed the script for removing corrupted images(pynoob ). Thanks!

kai · October 24, 2018, 7:56pm

You’re welcome

Taka · October 24, 2018, 7:57pm

btw, do you know of any shorter method?