Thanks so much!
@radi http://forums.fast.ai/t/how-to-scrape-the-web-for-images/7446/15 may help for downloading images.
Ok here is my first attempt Hammers vs Screw Drivers …
GitHub: Lesson 1 HW Hammer vs Screw Driver
- train folder = 47 pics of each category
- valid folder = 11 pics of each category
- played with the Learning Rate
-
Learning Rate is just right … good accuracy of 91%:
-
Learning Rate is too small …accuracy stagnates at 54%:
-
Learning Rate is too big … accuracy is bad at 41% and the loss just explodes!!!
-
No idea why “learn.sched.plot()” is linear:
-
Finally …
-
Some interesting results:
- Most correct screw driver despite the disconnected handle …
- Obvious …
- No idea why …
Here are some of the ancillary things I used/learnt:
-
Images by web scrapping: https://github.com/hardikvasa/google-images-download
** ran from Windows cmd prompt, no need to call Python prompt, ran without the dollar sign, did pip install
** unless specified, it downloads the pics to the ‘Downloads’ folder -
Image folder structure for Paperscape cloud machine: How to use your own Dataset for Lesson 1
-
Considered using PuTTY to transfer files to Paperscape cloud machine: https://it.cornell.edu/managed-servers/transfer-files-using-putty
** but used Jupyter Notebook in Chrome browser to upload the zipped folder but could not unzip inside the browser
** went back to Paperscape console to unzip -
Change PATH in the Jupyter notebook code from the cats vs dogs example to what ever you chose
** there were couple of other locations where the phrase cats/dogs had to be renamed to your classes -
Password for Paperscape cloud machine could not be copy pasted, I have to type it every time
-
If you cannot access the Jupyter Notebook in the browser then check if your network provider is blocking port 8888
-
If you frequently stop and start Jupyter Notebook then the default port 8888 can become unavailable and Paperspace machine will start opening Jupyter Notebook with subsequent ports like 8889 etc
Thanks
Update to the Most Uncertain screw driver:
@jeremy may have answered why this last screw driver has such an ambiguous score of 0.48. According to his Lesson 2 DL 2018 (https://www.youtube.com/watch?v=JNxcznsrRb8), the software is written in such a way that the test set pictures are cropped to square shape, so the middle of this picture is not that obvious. It can be overcome by data augmentation, which I did not play with in my 1st homework. Thanks @jeremy for such an awesome tutorial
Github link to this please.