Share your work here ✅

mike.moloch · June 6, 2019, 7:36pm

I created a trash/recycling classifier and got the validation accuracy up to 94% … it’s not that good on random uploaded data but it’s pretty good. Next steps are to get more labelled data and experiment with augmentation of existing pics with background noise.

https://fasttrash.onrender.com/

paulsolomon · June 7, 2019, 6:17pm

For week 4 I wanted to have a go at some NLP. I have a fairly long whatsapp chat history with my wife so I decided to try and build a language model with it…

My notebook is here. It can be used to process and build a model from any whatsapp chat history. I took a very simple approach, just strung all the messages together for each day (~1000 total) and didn’t label by person. Despite the small amount of data (it runs very quickly), the text generated by the model was pretty good!

mindtrinket · June 10, 2019, 12:10pm

I recently got a bronze medal in Google’s Landmark Recognition Kaggle Competition. Read all about it here!

harikrishnanrajeev · June 10, 2019, 2:48pm

thank you for sharing the details. Congrats on your bronze medal. For multi GPU , where you using the distributed model (to_distributed). ?. Can you please share some details on the same. thanks

mindtrinket · June 10, 2019, 3:04pm

Thanks, I will post the code tomorrow (doing a little training before I upload it).

Literally as easy as:

learn.model = torch.nn.DataParallel(learn.model)

abhikjha · June 10, 2019, 3:27pm

what an article!! very nicely written!! Cant wait to see the codes now!! and congrats for your medal!!

dipam7 · June 12, 2019, 4:26am

Hey guys, I recently started writing for a new publication. My first article for them is about CNNs and Heatmaps. Fastai has really been a launchpad for my deep learning journey. Waiting for part 2

Best,
Dipam

NicolasVitale · June 12, 2019, 9:40pm

Starting to play after lesson 1 & 2 with an image classifier for ants.
Starting small as time is limited… by focusing on Lasius Niger, Messor Barbarus and Pheidole Pallidula.
I achieved 85% detection with a resnet50 without much finetuning for now.
Not extraordinary but very interesting

gist.github.com

https://gist.github.com/NicolasVitale/3ed78687ef53ab092bd01f3d3294b5a4

lesson2-download-ants.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "hide_input": false
   },
   "source": [
    "# Creating your own dataset from Google Images\n",
    "\n",

This file has been truncated. show original

oneironaut · June 13, 2019, 7:32am

I just finished the second post in my mini-series about automatic captcha solving. In the first part, I used a multi-label classification approach to show that CNN’s can be used to solve captchas.

In this new part, I’m using single-character classification to turn captcha solving into a standard classification task. The heatmap function in plot_top_losses produced some very nice visuals. In fact it was so useful, I consider moving the heatmap generation into it’s own function. That way we could use it to explain the models decision for arbitrary inputs.

nidaahmed · June 13, 2019, 9:33am

I’m getting the same error but even num_workers ad padding_mode is not fixing it.

utkb · June 13, 2019, 10:41am

Sorry, this is all I thought of when I read your first sentence… =P

33cvf8

NicolasVitale · June 13, 2019, 11:03am

Find it more interesting than bears or mosquitoes
I love ants!

mr0 · June 15, 2019, 1:29am

[Lesson 1, 2] Classifying Screenshots of 485 SNES games with 95.8% accuracy

I was able to use the techniques taught in 2019 lessons 1 and 2 to build a SNES game screenshot classifier.

It distinguishes between all 485 SNES games with remarkable accuracy!

error_rate
The screenshots it has difficulty on are screens with only text displayed (for example, game endings, etc).

To build the dataset, I downloaded LongPlays of the game from youtube, then used ffmpeg to extract ~150 screenshots from each video.

Links:
GitHub repository
Online Demo/Webapp of the model
Short Blogpost

I have not shared the dataset, because I’m not sure how to do so in a cost-effective manner (it’s 3.2 gigs of screenshots).

Edit: Changed 600 games to 485 games. I downloaded 600 videos, but only had 485 games to distinguish between after merging multiple videos for single games, and merging japanese/us/european titles to one per.

oneironaut · June 15, 2019, 6:11am

Wow, I love this!
600 classes is really a lot. And that method for generating the dataset is genius!

polegar · June 15, 2019, 1:04pm

Hello everyone,

I have made a responsive webapp to help me provide inputs to the different models that I train with fastai and mostly to have fun with my friends while using it .

For the moment you can interract with 4 trained models : image recognition (do not forget to read the discalmer ! ), sound detection, NLP and image reconstruction.

The hard part for the NLP model was to get enough data. Since facebook api needs autorisation to get all the post of a specific page (even a public one), I had to scroll A LOT on John Danaher’s facebook page, copy all the html, find a regexp to extract only the text and then clean it. But i’m pretty satisfied with the results since I only got 82975 words in total.

Image reconstruction is still in progress. Even though Henri.C and myself have made a lot of experimentations, the results are not always great. But the task seems to be a harder than we thought since nvidia is working on this https://www.nvidia.com/research/inpainting/masking .

Still, I’m pretty amazed with all the complex models that we can create with a formation of only 7 lessons !

Here you can find the git repos :
client side : https://github.com/Polegar22/fastai-feeder-pwa
server side : https://github.com/Polegar22/fastai-models-interactor

And I deployed it on : https://render.com/ which is really convenient !

Rajeev · June 16, 2019, 3:32am

I would love to see the top losses on this

noachr · June 17, 2019, 4:12am

Hello. I’d like to share my first ever blog post; I have written about implementing MixMatch in fastai.

MixMatch is a recent semi-supervised learning technique from Google research, and has pretty impressive results.

I’d like to thank Rachel Thomas for this very helpful blog on writing better posts.

heye0507 · June 17, 2019, 6:34pm

Hi all,
I finally finished replicate the 2018 lesson 8-9 of SSD model in fastai V1 style.
I hope this can bridge the gap between 2018 SSD and 2019 Retina Net (since in 2019 part-2 we still didn’t get chance to talk about Retina Net).
It follows everything in 2018 lesson 8-9. It was a great time to explore some lower level APIs of fastai
Here is working notebook,

github.com

heye0507/dl_related/blob/master/play_ground/SSD_dev.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from fastai.vision import *\n",
    "from fastai import *\n",
    "from fastai.callbacks import *"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {

This file has been truncated. show original

And I also wrote a bit about Object Detection API, construct bounding box in V1 style (-1,1) and interpret Loss function and display prediction.

senecamanu · June 18, 2019, 6:48am

Trained the stanford car dataset: https://ai.stanford.edu/~jkrause/cars/car_dataset.html and reached 93% with fast.ai. I’m quite pleased with the result! Here’s the code: https://github.com/senecamanu/stanford-car-sm

oneironaut · June 23, 2019, 8:57am

I finally finished my mini-series about solving captchas!

In this final part I improve the solution from the second part by not using 5 single models but instead modelling the whole captcha solving in a single model.
After some failed modelling attempts I found one that works really well.

I’m exited to now tackle the next challenge! (whatever that may be)