Mirror/AI-on-the-edge-device-docs
1
0
Fork 0
mirror of https://github.com/jomjol/AI-on-the-edge-device-docs.git synced 2025-12-06 19:46:56 +03:00
Code Issues Packages Projects Releases Wiki Activity

.

Browse Source
This commit is contained in:
CaCO3
2025-04-13 21:59:46 +02:00
parent ec107cb7f7
commit 82bb46bf64
1 changed files with 5 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docs/Choosing-the-Model.md
View File

@@ -15,9 +15,11 @@ For digits on water meters, gas-meters or power meters you can select between tw
- `dig-class11`
- `dig-class100` and `dig-cont`
`class` stands for **classification** and `cont` stands for **continuous**. The `11` means that there are 11 states (`0..9` and `N`). The `100` indicates that the model resolves into `x.1` steps.
### `dig-class11`
This model can recognize **full digits**. It was the first model version. All intermediate states shown a `N` for not a number. But in post process it uses older values to fill up the `N` values if possible.
This model can recognize **full digits**. It was the first model version. All intermediate states shown a `N` for not-a-number (aka. `NaN`). But in post process it uses older values to fill up the `N` values if possible.
![](img/dig-class11.png){: style="width:300px"}
@@ -42,7 +44,7 @@ Main features:
The difference between `dig-class100` and `dig-cont` is in the internal processing.
The `dig-class100` is a standard classification model. Each tenth step is an output.
`dig-cont` uses two outputs and arctangent to get the result. You see very complicated.
`dig-cont` uses two outputs and arctangent to get the result.
!!! Note
Try both models on your device and take the one that gives you the best results.
@@ -63,6 +65,7 @@ For pointers on water meters use the analog models:
- `ana-cont`
Both do mainly the same.
`class` stands for **classification** and `cont` stands for **continuous**.
Main features: