Hugging Face's logo

usamaaleem99tech
/
segformer-class-classWeights-augmentation

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
4
usamaaleem99tech commited on
Commit
5b0319a
•
1 Parent(s): a651da9

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9655172413793104
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.0355
36
- - Accuracy: 0.9655
37
 
38
  ## Model description
39
 
@@ -67,24 +67,24 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.89 | 6 | 1.0977 | 0.5517 |
71
- | 1.0215 | 1.93 | 13 | 0.6858 | 0.7931 |
72
- | 0.6364 | 2.96 | 20 | 0.9383 | 0.6897 |
73
- | 0.6364 | 4.0 | 27 | 0.2391 | 0.9310 |
74
- | 0.2716 | 4.89 | 33 | 0.1767 | 0.8966 |
75
- | 0.2295 | 5.93 | 40 | 0.2729 | 0.9310 |
76
- | 0.2295 | 6.96 | 47 | 0.1429 | 0.9655 |
77
- | 0.1311 | 8.0 | 54 | 0.1929 | 0.9655 |
78
- | 0.1503 | 8.89 | 60 | 0.1718 | 0.9655 |
79
- | 0.1503 | 9.93 | 67 | 0.1631 | 0.9655 |
80
- | 0.1554 | 10.96 | 74 | 0.2690 | 0.9655 |
81
- | 0.1157 | 12.0 | 81 | 0.1331 | 0.9655 |
82
- | 0.1157 | 12.89 | 87 | 0.0512 | 0.9655 |
83
- | 0.1093 | 13.93 | 94 | 0.0273 | 1.0 |
84
- | 0.134 | 14.96 | 101 | 0.0356 | 0.9655 |
85
- | 0.134 | 16.0 | 108 | 0.0477 | 0.9655 |
86
- | 0.0926 | 16.89 | 114 | 0.0381 | 0.9655 |
87
- | 0.1363 | 17.78 | 120 | 0.0355 | 0.9655 |
88
 
89
 
90
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 1.0
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.0018
36
+ - Accuracy: 1.0
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.89 | 6 | 0.9811 | 0.5862 |
71
+ | 1.0899 | 1.93 | 13 | 0.9601 | 0.5862 |
72
+ | 0.7599 | 2.96 | 20 | 0.8930 | 0.6897 |
73
+ | 0.7599 | 4.0 | 27 | 0.5230 | 0.7931 |
74
+ | 0.3436 | 4.89 | 33 | 0.1652 | 0.9310 |
75
+ | 0.1853 | 5.93 | 40 | 0.0544 | 1.0 |
76
+ | 0.1853 | 6.96 | 47 | 0.0937 | 0.9655 |
77
+ | 0.1839 | 8.0 | 54 | 0.0566 | 0.9655 |
78
+ | 0.1772 | 8.89 | 60 | 0.0084 | 1.0 |
79
+ | 0.1772 | 9.93 | 67 | 0.0114 | 1.0 |
80
+ | 0.1016 | 10.96 | 74 | 0.0039 | 1.0 |
81
+ | 0.1534 | 12.0 | 81 | 0.0038 | 1.0 |
82
+ | 0.1534 | 12.89 | 87 | 0.0187 | 0.9655 |
83
+ | 0.1256 | 13.93 | 94 | 0.0023 | 1.0 |
84
+ | 0.1234 | 14.96 | 101 | 0.0016 | 1.0 |
85
+ | 0.1234 | 16.0 | 108 | 0.0019 | 1.0 |
86
+ | 0.1129 | 16.89 | 114 | 0.0018 | 1.0 |
87
+ | 0.17 | 17.78 | 120 | 0.0018 | 1.0 |
88
 
89
 
90
  ### Framework versions