Update README.md
Browse files
README.md
CHANGED
|
@@ -36,17 +36,12 @@ It achieves the following results on the evaluation set:
|
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
| 39 |
-
|
| 40 |
|
| 41 |
-
|
| 42 |
-
|
| 43 |
-
More
|
| 44 |
-
|
| 45 |
-
## Training and evaluation data
|
| 46 |
-
|
| 47 |
-
More information needed
|
| 48 |
-
|
| 49 |
-
## Training procedure
|
| 50 |
|
| 51 |
### Training hyperparameters
|
| 52 |
|
|
|
|
| 36 |
|
| 37 |
## Model description
|
| 38 |
|
| 39 |
+
The German Traffic Sign Benchmark is a multi-class, single-image classification challenge held at the International Joint Conference on Neural Networks (IJCNN) 2011. We cordially invite researchers from relevant fields to participate: The competition is designed to allow for participation without special domain knowledge. Our benchmark has the following properties:
|
| 40 |
|
| 41 |
+
- Single-image, multi-class classification problem
|
| 42 |
+
- More than 40 classes
|
| 43 |
+
- More than 50,000 images in total
|
| 44 |
+
- Large, lifelike database
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
| 46 |
### Training hyperparameters
|
| 47 |
|