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
2eef93a
•
1 Parent(s): 48d9e23

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -13
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.9310344827586207
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: 0.2606
36
- - Accuracy: 0.9310
37
 
38
  ## Model description
39
 
@@ -61,21 +61,30 @@ The following hyperparameters were used during training:
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
- - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | No log | 0.89 | 6 | 1.0179 | 0.5862 |
71
- | 0.9897 | 1.93 | 13 | 0.7600 | 0.7241 |
72
- | 0.5848 | 2.96 | 20 | 0.8368 | 0.5862 |
73
- | 0.5848 | 4.0 | 27 | 0.4708 | 0.8621 |
74
- | 0.2747 | 4.89 | 33 | 0.3727 | 0.8966 |
75
- | 0.2259 | 5.93 | 40 | 0.3100 | 0.9310 |
76
- | 0.2259 | 6.96 | 47 | 0.2294 | 0.9310 |
77
- | 0.1596 | 8.0 | 54 | 0.2631 | 0.8966 |
78
- | 0.1844 | 8.89 | 60 | 0.2606 | 0.9310 |
 
 
 
 
 
 
 
 
 
79
 
80
 
81
  ### 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: 0.0021
36
+ - Accuracy: 1.0
37
 
38
  ## Model description
39
 
 
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
64
+ - num_epochs: 20
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.89 | 6 | 1.1566 | 0.2414 |
71
+ | 1.11 | 1.93 | 13 | 0.9865 | 0.6552 |
72
+ | 0.8833 | 2.96 | 20 | 0.8093 | 0.6552 |
73
+ | 0.8833 | 4.0 | 27 | 0.4920 | 0.8276 |
74
+ | 0.5072 | 4.89 | 33 | 0.3906 | 0.8276 |
75
+ | 0.2935 | 5.93 | 40 | 0.0612 | 1.0 |
76
+ | 0.2935 | 6.96 | 47 | 0.0375 | 1.0 |
77
+ | 0.2311 | 8.0 | 54 | 0.2657 | 0.8621 |
78
+ | 0.2665 | 8.89 | 60 | 0.0595 | 1.0 |
79
+ | 0.2665 | 9.93 | 67 | 0.1044 | 0.9655 |
80
+ | 0.2008 | 10.96 | 74 | 0.0150 | 1.0 |
81
+ | 0.1557 | 12.0 | 81 | 0.0056 | 1.0 |
82
+ | 0.1557 | 12.89 | 87 | 0.0028 | 1.0 |
83
+ | 0.131 | 13.93 | 94 | 0.0011 | 1.0 |
84
+ | 0.1708 | 14.96 | 101 | 0.0019 | 1.0 |
85
+ | 0.1708 | 16.0 | 108 | 0.0023 | 1.0 |
86
+ | 0.1799 | 16.89 | 114 | 0.0021 | 1.0 |
87
+ | 0.1598 | 17.78 | 120 | 0.0021 | 1.0 |
88
 
89
 
90
  ### Framework versions