|
Loss and Accuracy Figures.
|
|
May-17-2020, 04:16 PM
Anyone can help me understand the following figures?
https://drive.google.com/open?id=1YZmVh7...sB9-cTelVT https://drive.google.com/open?id=1ztRU82...rS5OoWJ7WC Thank you
May-18-2020, 03:21 AM
Please don't use links, rather post code here using bbcode tags.
May-20-2020, 06:55 PM
That didn't exactly work either, but -
In general, the loss decreases and accuracy increases as you run more cycles in your model (sometimes called epochs). The down side of this is that you can "overfit" your model so it is really really good at predicting the data in your training set, but when tested on other data the results start getting worse. From your graphs you appear to have hit the "sweet spot", where the accuracy and loss in the test sets have flattened out, before they start getting worse. Make sense? |
|
|
| Possibly Related Threads… | |||||
| Thread | Author | Replies | Views | Last Post | |
| LSTM Model accuracy caps and I can't improve it | celinafregoso99 | 1 | 1,983 |
Dec-19-2020, 01:29 PM Last Post: jefsummers |
|
| matplotlib.pyplot functions create new figures instead of applying to the current one | karkas | 2 | 2,093 |
Jul-09-2020, 08:32 AM Last Post: karkas |
|
| Increasing validation accuracy on a CNN | hobbyist | 4 | 4,130 |
Jun-23-2020, 01:15 PM Last Post: hussainmujtaba |
|
| Best Accuracy From Loop. | AhmadMWaddah | 4 | 2,444 |
Mar-17-2020, 10:25 PM Last Post: stullis |
|
| How to create matplotlib subplots from figures | vitaly | 3 | 3,119 |
Mar-02-2020, 12:58 AM Last Post: scidam |
|
| Why is my train and test accuracy so low? | python420 | 0 | 2,051 |
Dec-08-2019, 08:51 PM Last Post: python420 |
|
| Low accuracy for fake news detection model | shivani | 1 | 2,338 |
Oct-10-2019, 12:09 PM Last Post: animeshagrawal2807 |
|
| Superimpose figures | Scientifix | 2 | 4,669 |
Aug-16-2019, 04:06 PM Last Post: Nitram |
|
| How to superscript figures? | Felipe | 0 | 3,050 |
Feb-06-2017, 05:56 PM Last Post: Felipe |
|
