ydmeira
/

segformer-b0-finetuned-pokemon

Transformers

PyTorch

TensorBoard

segformer

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

ydmeira commited on Jul 24, 2022

Commit

c683ef3

1 Parent(s): 2a17c69

update model card README.md

Browse files

Files changed (1) hide show

README.md +16 -21

README.md CHANGED Viewed

@@ -12,14 +12,14 @@ should probably proofread and complete it, then remove this comment. -->
 # segformer-b0-finetuned-pokemon
-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: 0.0298
-- Mean Iou: 0.4971
-- Mean Accuracy: 0.9941
-- Overall Accuracy: 0.9941
-- Per Category Iou: [0.0, 0.99410193702663]
-- Per Category Accuracy: [nan, 0.99410193702663]
 ## Model description
@@ -44,23 +44,18 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 50
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou          | Per Category Accuracy     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------------:|:-------------------------:|
-| 0.0286        | 40.0  | 1160 | 0.0304          | 0.4965   | 0.9929        | 0.9929           | [0.0, 0.9929262067682688] | [nan, 0.9929262067682688] |
-| 0.0272        | 41.0  | 1189 | 0.0301          | 0.4966   | 0.9933        | 0.9933           | [0.0, 0.9932505252321254] | [nan, 0.9932505252321254] |
-| 0.0279        | 42.0  | 1218 | 0.0305          | 0.4973   | 0.9947        | 0.9947           | [0.0, 0.994698129326027]  | [nan, 0.994698129326027]  |
-| 0.0309        | 43.0  | 1247 | 0.0295          | 0.4966   | 0.9931        | 0.9931           | [0.0, 0.9931164081595019] | [nan, 0.9931164081595019] |
-| 0.028         | 44.0  | 1276 | 0.0294          | 0.4967   | 0.9934        | 0.9934           | [0.0, 0.9933975466612431] | [nan, 0.9933975466612431] |
-| 0.0276        | 45.0  | 1305 | 0.0298          | 0.4970   | 0.9941        | 0.9941           | [0.0, 0.994062837929389]  | [nan, 0.994062837929389]  |
-| 0.0281        | 46.0  | 1334 | 0.0300          | 0.4969   | 0.9939        | 0.9939           | [0.0, 0.9938931511561724] | [nan, 0.9938931511561724] |
-| 0.0273        | 47.0  | 1363 | 0.0297          | 0.4968   | 0.9936        | 0.9936           | [0.0, 0.993593207587916]  | [nan, 0.993593207587916]  |
-| 0.0291        | 48.0  | 1392 | 0.0297          | 0.4970   | 0.9941        | 0.9941           | [0.0, 0.9940591430922732] | [nan, 0.9940591430922732] |
-| 0.0269        | 49.0  | 1421 | 0.0294          | 0.4968   | 0.9936        | 0.9936           | [0.0, 0.9936409647363091] | [nan, 0.9936409647363091] |
-| 0.0279        | 50.0  | 1450 | 0.0298          | 0.4971   | 0.9941        | 0.9941           | [0.0, 0.99410193702663]   | [nan, 0.99410193702663]   |
 ### Framework versions

 # segformer-b0-finetuned-pokemon
+This model is a fine-tuned version of [ydmeira/segformer-b0-finetuned-pokemon](https://huggingface.co/ydmeira/segformer-b0-finetuned-pokemon) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0225
+- Mean Accuracy: 0.9927
+- Mean Iou: 0.4964
+- Overall Accuracy: 0.9927
+- Per Category Accuracy: [nan, 0.9927247002783977]
+- Per Category Iou: [0.0, 0.9927247002783977]
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 20
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Mean Accuracy | Mean Iou | Overall Accuracy | Per Category Accuracy     | Per Category Iou          |
+|:-------------:|:-----:|:----:|:---------------:|:-------------:|:--------:|:----------------:|:-------------------------:|:-------------------------:|
+| 0.0217        | 15.0  | 435  | 0.0228          | 0.9944        | 0.4972   | 0.9944           | [nan, 0.9944285716570368] | [0.0, 0.9944285716570368] |
+| 0.0228        | 16.0  | 464  | 0.0227          | 0.9943        | 0.4971   | 0.9943           | [nan, 0.9942943994375907] | [0.0, 0.9942943994375907] |
+| 0.0204        | 17.0  | 493  | 0.0226          | 0.9933        | 0.4967   | 0.9933           | [nan, 0.9933366094222428] | [0.0, 0.9933366094222428] |
+| 0.0202        | 18.0  | 522  | 0.0226          | 0.9929        | 0.4964   | 0.9929           | [nan, 0.9928635048309444] | [0.0, 0.9928635048309444] |
+| 0.021         | 19.0  | 551  | 0.0226          | 0.9924        | 0.4962   | 0.9924           | [nan, 0.9924163192462797] | [0.0, 0.9924163192462797] |
+| 0.0203        | 20.0  | 580  | 0.0225          | 0.9927        | 0.4964   | 0.9927           | [nan, 0.9927247002783977] | [0.0, 0.9927247002783977] |
 ### Framework versions