Hugging Face's logo

ydmeira
/
segformer-b0-finetuned-pokemon

Transformers
PyTorch
TensorBoard
segformer
generated_from_trainer
Inference Endpoints
Model card Files Metrics Community
ydmeira commited on
Commit
0a6e016
•
1 Parent(s): be8131d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -20
README.md CHANGED
@@ -14,12 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  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.
16
  It achieves the following results on the evaluation set:
17
- - Loss: 0.0190
18
- - Mean Iou: 0.4972
19
- - Mean Accuracy: 0.9944
20
- - Overall Accuracy: 0.9944
21
- - Per Category Iou: [0.0, 0.9944194724313037]
22
- - Per Category Accuracy: [nan, 0.9944194724313037]
23
 
24
  ## Model description
25
 
@@ -48,20 +48,14 @@ The following hyperparameters were used during training:
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss | Mean Accuracy | Mean Iou | Overall Accuracy | Per Category Accuracy | Per Category Iou |
52
- |:-------------:|:-----:|:----:|:---------------:|:-------------:|:--------:|:----------------:|:-------------------------:|:-------------------------:|
53
- | 0.0217 | 15.0 | 435 | 0.0228 | 0.9944 | 0.4972 | 0.9944 | [nan, 0.9944285716570368] | [0.0, 0.9944285716570368] |
54
- | 0.0228 | 16.0 | 464 | 0.0227 | 0.9943 | 0.4971 | 0.9943 | [nan, 0.9942943994375907] | [0.0, 0.9942943994375907] |
55
- | 0.0204 | 17.0 | 493 | 0.0226 | 0.9933 | 0.4967 | 0.9933 | [nan, 0.9933366094222428] | [0.0, 0.9933366094222428] |
56
- | 0.0202 | 18.0 | 522 | 0.0226 | 0.9929 | 0.4964 | 0.9929 | [nan, 0.9928635048309444] | [0.0, 0.9928635048309444] |
57
- | 0.021 | 19.0 | 551 | 0.0226 | 0.9924 | 0.4962 | 0.9924 | [nan, 0.9924163192462797] | [0.0, 0.9924163192462797] |
58
- | 0.0203 | 20.0 | 580 | 0.0225 | 0.9927 | 0.4964 | 0.9927 | [nan, 0.9927247002783977] | [0.0, 0.9927247002783977] |
59
- | 0.0184 | 45.0 | 1305 | 0.0193 | 0.4974 | 0.9949 | 0.9949 | [0.0, 0.9948637903811919] | [nan, 0.9948637903811919] |
60
- | 0.0183 | 46.0 | 1334 | 0.0192 | 0.4972 | 0.9944 | 0.9944 | [0.0, 0.9943721564574917] | [nan, 0.9943721564574917] |
61
- | 0.0183 | 47.0 | 1363 | 0.0191 | 0.4972 | 0.9945 | 0.9945 | [0.0, 0.994473240583363] | [nan, 0.994473240583363] |
62
- | 0.02 | 48.0 | 1392 | 0.0188 | 0.4972 | 0.9944 | 0.9944 | [0.0, 0.9943908512303614] | [nan, 0.9943908512303614] |
63
- | 0.0176 | 49.0 | 1421 | 0.0188 | 0.4971 | 0.9942 | 0.9942 | [0.0, 0.9941838300582279] | [nan, 0.9941838300582279] |
64
- | 0.0189 | 50.0 | 1450 | 0.0190 | 0.4972 | 0.9944 | 0.9944 | [0.0, 0.9944194724313037] | [nan, 0.9944194724313037] |
65
 
66
 
67
  ### Framework versions
14
 
15
  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.
16
  It achieves the following results on the evaluation set:
17
+ - Loss: 0.0157
18
+ - Mean Iou: 0.4970
19
+ - Mean Accuracy: 0.9940
20
+ - Overall Accuracy: 0.9940
21
+ - Per Category Iou: [0.0, 0.9940101727137823]
22
+ - Per Category Accuracy: [nan, 0.9940101727137823]
23
 
24
  ## Model description
25
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Per Category Iou | Per Category Accuracy |
52
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:-------------:|:----------------:|:-------------------------:|:-------------------------:|
53
+ | 0.0175 | 45.0 | 1305 | 0.0157 | 0.4971 | 0.9943 | 0.9943 | [0.0, 0.9942906494536522] | [nan, 0.9942906494536522] |
54
+ | 0.018 | 46.0 | 1334 | 0.0157 | 0.4968 | 0.9936 | 0.9936 | [0.0, 0.9936369941650801] | [nan, 0.9936369941650801] |
55
+ | 0.0185 | 47.0 | 1363 | 0.0157 | 0.4971 | 0.9943 | 0.9943 | [0.0, 0.9942791789145462] | [nan, 0.9942791789145462] |
56
+ | 0.018 | 48.0 | 1392 | 0.0157 | 0.4969 | 0.9937 | 0.9937 | [0.0, 0.9937245121725857] | [nan, 0.9937245121725857] |
57
+ | 0.0183 | 49.0 | 1421 | 0.0157 | 0.4969 | 0.9939 | 0.9939 | [0.0, 0.9938530594161242] | [nan, 0.9938530594161242] |
58
+ | 0.0196 | 50.0 | 1450 | 0.0157 | 0.4970 | 0.9940 | 0.9940 | [0.0, 0.9940101727137823] | [nan, 0.9940101727137823] |
 
 
 
 
 
 
59
 
60
 
61
  ### Framework versions