Classifying Tesla cars

pbanavara · October 30, 2018, 2:33am

I just tried this for the sake of playing around. I was curious at how the Resnet34 model will perform given how similar the Model3 and ModelS cars are. I was quite surprised at the results :).
I ignored all the download errors related to content size and all that. Goes to show how robust the model is. I tried to increase the fit_cycle to 8 but started running into CUDA OOM errors. I am using GCP. Anyways great experience. One mistake I noticed is that I failed to change the learning rate interval. I tried to correct this but am landing with CUDA OOM errors. Will keep trying and share the results.

I reused the download_images.ipynb notebook but cleaned up a bit. My results:

github.com

pbanavara/course-v3/blob/master/nbs/dl1/tesla_classification.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "hide_input": false
   },
   "source": [
    "# Creating your own dataset from Google Images\n",
    "\n",
    "*by: Francisco Ingham and Jeremy Howard. Inspired by [Adrian Rosebrock](https://www.pyimagesearch.com/2017/12/04/how-to-create-a-deep-learning-dataset-using-google-images/)*"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "hide_input": true
   },
   "source": [
    "In this tutorial we will see how to easily create an image dataset through Google Images. **Note**: You will have to repeat these steps for any new category you want to Google (e.g once for dogs and once for cats)."

This file has been truncated. show original

jeremy · October 30, 2018, 2:37am

Thanks for sharing - perhaps better to post in the existing thread rather than creating a new one, otherwise it can get pretty cluttered here!:

pbanavara · October 30, 2018, 3:09am

Yep makes sense. I just posted on the Share your work thread. @jeremy can you please delete this topic ?