kasumi222
/

segformer-b0-finetuned-busigt2

Image Segmentation

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

kasumi222 commited on Sep 11, 2022

Commit

3a1d87e

·

1 Parent(s): 3cd73fb

update model card README.md

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -14,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6642
-- Mean Iou: 0.1376
-- Mean Accuracy: 0.2220
-- Overall Accuracy: 0.2268
-- Per Category Iou: [0.0, 0.22412411489163372, 0.18861218384055423]
-- Per Category Accuracy: [nan, 0.25080184838168496, 0.1931572008973657]
 ## Model description
@@ -48,9 +48,9 @@ The following hyperparameters were used during training:
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou                                | Per Category Accuracy                          |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-----------------------------------------------:|:----------------------------------------------:|
-| 0.7101        | 0.61  | 20   | 0.6642          | 0.1376   | 0.2220        | 0.2268           | [0.0, 0.22412411489163372, 0.18861218384055423] | [nan, 0.25080184838168496, 0.1931572008973657] |
 ### Framework versions

 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.6495
+- Mean Iou: 0.1549
+- Mean Accuracy: 0.2548
+- Overall Accuracy: 0.2632
+- Per Category Iou: [0.0, 0.2648086869349988, 0.1998372928797926]
+- Per Category Accuracy: [nan, 0.30456581671196054, 0.20506315591233834]
 ## Model description
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou                              | Per Category Accuracy                           |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:---------------------------------------------:|:-----------------------------------------------:|
+| 0.7106        | 0.61  | 20   | 0.6495          | 0.1549   | 0.2548        | 0.2632           | [0.0, 0.2648086869349988, 0.1998372928797926] | [nan, 0.30456581671196054, 0.20506315591233834] |
 ### Framework versions