Create models/README.md
Browse files- models/README.md +14 -0
models/README.md
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Card_Segmentation Model Information
|
| 2 |
+
## Model Details
|
| 3 |
+
- Architecture: lraspp_mobilenet_v3_large
|
| 4 |
+
- Input Size: 320x240
|
| 5 |
+
- Number of Classes: 2
|
| 6 |
+
- Classes: Background (0), Card (1)
|
| 7 |
+
|
| 8 |
+
## Model Files
|
| 9 |
+
- `card_segmentation.onnx`: ONNX format for cross-platform deployment
|
| 10 |
+
|
| 11 |
+
## Input/Output
|
| 12 |
+
- Input: RGB image tensor of shape (1, 3, 320, 240)
|
| 13 |
+
- Input normalization: mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]
|
| 14 |
+
- Output: Segmentation logits of shape (1, 2, 320, 240)
|