Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,14 @@
|
|
| 1 |
---
|
| 2 |
license: bsd
|
| 3 |
pipeline_tag: image-segmentation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
|
| 6 |
|
|
@@ -29,6 +37,7 @@ The models of the current version have not been trained in exterior and may lead
|
|
| 29 |
on the edge of the pore. It is therefore recommended to avoid the usage of models on highly porous materials.
|
| 30 |
|
| 31 |
## Training Details
|
|
|
|
| 32 |
|
| 33 |
### Training Data
|
| 34 |
|
|
|
|
| 1 |
---
|
| 2 |
license: bsd
|
| 3 |
pipeline_tag: image-segmentation
|
| 4 |
+
base_model:
|
| 5 |
+
- timm/resnext101_32x8d
|
| 6 |
+
library_name: segmentation_models
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
---
|
| 13 |
|
| 14 |
|
|
|
|
| 37 |
on the edge of the pore. It is therefore recommended to avoid the usage of models on highly porous materials.
|
| 38 |
|
| 39 |
## Training Details
|
| 40 |
+
The models originate from https://github.com/qubvel-org/segmentation_models.pytorch library, and are retrained on dataset crackenpy_dataset.
|
| 41 |
|
| 42 |
### Training Data
|
| 43 |
|