This shows you the differences between two versions of the page.
| Both sides previous revision Previous revision Next revision | Previous revision | ||
|
cs601r_w2020:lab2 [2020/01/10 17:53] wingated |
cs601r_w2020:lab2 [2021/06/30 23:42] (current) |
||
|---|---|---|---|
| Line 13: | Line 13: | ||
| Your notebook will be graded on the following: | Your notebook will be graded on the following: | ||
| - | * 40% Part 1: Clearly displayed 10 bars (one for baseline, one for each tweak independently) | + | * 35% Part 1: Clearly displayed 10 bars (one for baseline, one for each tweak independently) |
| + | * 5% Part 1: Small writeup of conclusions from independent tweaks | ||
| * 25% Part 2: Clear explanation of your tweaking strategy | * 25% Part 2: Clear explanation of your tweaking strategy | ||
| * 25% Part 2: Actually run your tweaking strategy and show the results | * 25% Part 2: Actually run your tweaking strategy and show the results | ||
| Line 63: | Line 64: | ||
| Some of these tweaks require additional parameters. You should either leave them at their default values, or think of some reasonable way to set them. | Some of these tweaks require additional parameters. You should either leave them at their default values, or think of some reasonable way to set them. | ||
| + | |||
| + | Note: pytorch does not (AFAIK) natively implement label smoothing. In the interests of focusing on hyperparameter searching, **you may verbatim copy any internet code you like to help implement label smoothing.** | ||
| ---- | ---- | ||
| Line 73: | Line 76: | ||
| This lab should be pretty straightforward, with the right script -- you should be able to iterate over tweaks and run your classifier in a tidy loop. Ideally, you'll code it up, let it run, and come back in a few hours to find the results! | This lab should be pretty straightforward, with the right script -- you should be able to iterate over tweaks and run your classifier in a tidy loop. Ideally, you'll code it up, let it run, and come back in a few hours to find the results! | ||
| - | If you find yourself cutting-and-pasting, you might want to rethink your strategy! | + | If you find yourself cutting-and-pasting, you might want to rethink your strategy. |