@factfinder we needed 100's of images of each fish species for it to reliably recognize a fish species, more images gave the system greater confidence when identifying the fish species. Each time we needed to improve the system (by adding more images to a library for a fish species), or teach it a new species (with a new library of images for the target species) we needed to retrain the system in our office then deploy to the platform; which can become tedious. We were using Matlab
There was lots of work involved:
- obtaining the images of each fish species
- cleaning the image library and ensuring they were labelled correctly
- multiple iterations (10's not 100's) as we developed the model & trained the model to a suitable level of confidence
@factfinder we needed 100's of images of each fish species for...
-
- There are more pages in this discussion • 105 more messages in this thread...
You’re viewing a single post only. To view the entire thread just sign in or Join Now (FREE)
Add BRN (ASX) to my watchlist
 (20min delay)
|
|||||
|
Last
20.0¢ |
Change
-0.005(2.44%) |
Mkt cap ! $371.1M | |||
| Open | High | Low | Value | Volume |
| 20.5¢ | 20.5¢ | 19.5¢ | $843.2K | 4.220M |
Buyers (Bids)
| No. | Vol. | Price($) |
|---|---|---|
| 5 | 71948 | 20.0¢ |
Sellers (Offers)
| Price($) | Vol. | No. |
|---|---|---|
| 20.5¢ | 644737 | 16 |
View Market Depth
| Last trade - 16.10pm 26/07/2024 (20 minute delay) ? |
| BRN (ASX) Chart |