Update README.md
Browse files
README.md
CHANGED
|
@@ -4,4 +4,30 @@ datasets:
|
|
| 4 |
- jonathan-roberts1/Satellite-Images-of-Hurricane-Damage
|
| 5 |
tags:
|
| 6 |
- climate
|
| 7 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
- jonathan-roberts1/Satellite-Images-of-Hurricane-Damage
|
| 5 |
tags:
|
| 6 |
- climate
|
| 7 |
+
---
|
| 8 |
+
# Model Card for Model ID
|
| 9 |
+
|
| 10 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 11 |
+
|
| 12 |
+
This model is trained on a subset of `jonathan-roberts1/Satellite-Images-of-Hurricane-Damage?` and performs binary classification on satellite images into either damaged or not damaged.
|
| 13 |
+
|
| 14 |
+
The model was trained using PyTorch on Intel Developer Cloud using ipex optimization. Here is the Neural Network architecture:
|
| 15 |
+
|
| 16 |
+
```python
|
| 17 |
+
model.fc = nn.Sequential(
|
| 18 |
+
nn.Linear(2048, 128),
|
| 19 |
+
nn.ReLU(inplace=True),
|
| 20 |
+
nn.Linear(128, 64),
|
| 21 |
+
nn.ReLU(inplace=True),
|
| 22 |
+
nn.Linear(64, 2))
|
| 23 |
+
```
|
| 24 |
+
|
| 25 |
+
## Uses
|
| 26 |
+
|
| 27 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 28 |
+
|
| 29 |
+
Some use cases include emergency response and disaster detection.
|
| 30 |
+
|
| 31 |
+
## Bias, Risks, and Limitations
|
| 32 |
+
|
| 33 |
+
This model is limited in use as it only performs binary classification. Further extensions include adding more classes to the model or more diverse data to the model.
|