Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,7 @@ tags:
|
|
| 6 |
model-index:
|
| 7 |
- name: SegFormer_mit-b5_Clean-Set3-Grayscale_Augmented_Medium
|
| 8 |
results: []
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,7 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [nvidia/mit-b5](https://huggingface.co/nvidia/mit-b5) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss: 0.
|
|
|
|
| 19 |
- Mean Iou: 0.9793
|
| 20 |
- Mean Accuracy: 0.9903
|
| 21 |
- Overall Accuracy: 0.9947
|
|
@@ -94,4 +96,4 @@ The following hyperparameters were used during training:
|
|
| 94 |
- Transformers 4.41.2
|
| 95 |
- Pytorch 2.0.1+cu117
|
| 96 |
- Datasets 2.19.2
|
| 97 |
-
- Tokenizers 0.19.1
|
|
|
|
| 6 |
model-index:
|
| 7 |
- name: SegFormer_mit-b5_Clean-Set3-Grayscale_Augmented_Medium
|
| 8 |
results: []
|
| 9 |
+
pipeline_tag: image-segmentation
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [nvidia/mit-b5](https://huggingface.co/nvidia/mit-b5) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Train-Loss: 0.0088
|
| 20 |
+
- Val-Loss: 0.0134
|
| 21 |
- Mean Iou: 0.9793
|
| 22 |
- Mean Accuracy: 0.9903
|
| 23 |
- Overall Accuracy: 0.9947
|
|
|
|
| 96 |
- Transformers 4.41.2
|
| 97 |
- Pytorch 2.0.1+cu117
|
| 98 |
- Datasets 2.19.2
|
| 99 |
+
- Tokenizers 0.19.1
|