Instructions to use AhamadShaik/SegFormer_PADDING_NLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AhamadShaik/SegFormer_PADDING_NLM with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoImageProcessor, SegformerForSemanticSegmentation processor = AutoImageProcessor.from_pretrained("AhamadShaik/SegFormer_PADDING_NLM") model = SegformerForSemanticSegmentation.from_pretrained("AhamadShaik/SegFormer_PADDING_NLM", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
0afbd20
1
Parent(s): eef58e5
Training in progress epoch 60
Browse files- README.md +7 -6
- tf_model.h5 +1 -1
README.md
CHANGED
|
@@ -15,13 +15,13 @@ probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Train Loss: 0.0159
|
| 18 |
-
- Train Dice Coef: 0.
|
| 19 |
-
- Train Iou: 0.
|
| 20 |
-
- Validation Loss: 0.
|
| 21 |
-
- Validation Dice Coef: 0.
|
| 22 |
-
- Validation Iou: 0.
|
| 23 |
- Train Lr: 1e-10
|
| 24 |
-
- Epoch:
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -107,6 +107,7 @@ The following hyperparameters were used during training:
|
|
| 107 |
| 0.0161 | 0.8061 | 0.6828 | 0.0226 | 0.8560 | 0.7506 | 6.25e-10 | 57 |
|
| 108 |
| 0.0160 | 0.8062 | 0.6833 | 0.0231 | 0.8560 | 0.7505 | 6.25e-10 | 58 |
|
| 109 |
| 0.0159 | 0.8037 | 0.6810 | 0.0227 | 0.8557 | 0.7500 | 1e-10 | 59 |
|
|
|
|
| 110 |
|
| 111 |
|
| 112 |
### Framework versions
|
|
|
|
| 15 |
This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on an unknown dataset.
|
| 16 |
It achieves the following results on the evaluation set:
|
| 17 |
- Train Loss: 0.0159
|
| 18 |
+
- Train Dice Coef: 0.8085
|
| 19 |
+
- Train Iou: 0.6859
|
| 20 |
+
- Validation Loss: 0.0223
|
| 21 |
+
- Validation Dice Coef: 0.8572
|
| 22 |
+
- Validation Iou: 0.7522
|
| 23 |
- Train Lr: 1e-10
|
| 24 |
+
- Epoch: 60
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 107 |
| 0.0161 | 0.8061 | 0.6828 | 0.0226 | 0.8560 | 0.7506 | 6.25e-10 | 57 |
|
| 108 |
| 0.0160 | 0.8062 | 0.6833 | 0.0231 | 0.8560 | 0.7505 | 6.25e-10 | 58 |
|
| 109 |
| 0.0159 | 0.8037 | 0.6810 | 0.0227 | 0.8557 | 0.7500 | 1e-10 | 59 |
|
| 110 |
+
| 0.0159 | 0.8085 | 0.6859 | 0.0223 | 0.8572 | 0.7522 | 1e-10 | 60 |
|
| 111 |
|
| 112 |
|
| 113 |
### Framework versions
|
tf_model.h5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15133664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b2ef77591dec1a612495c3642bc1e4af6a3d83e77ba8635fd3f99d12188ebb7
|
| 3 |
size 15133664
|