Hugging Face's logo

Gokulapriyan
/
swin-tiny-patch4-window7-224-finetuned-new_dataset_50e

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Gokulapriyan commited on
Commit
1c098ae
·
1 Parent(s): b77ca3c

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +126 -0
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: swin-tiny-patch4-window7-224-finetuned-new_dataset_50e
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: train
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.7837837837837838
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # swin-tiny-patch4-window7-224-finetuned-new_dataset_50e
31
+
32
+ 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.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.7626
35
+ - Accuracy: 0.7838
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 32
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 128
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 50
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.94 | 4 | 0.5406 | 0.7568 |
70
+ | No log | 1.94 | 8 | 0.5781 | 0.7297 |
71
+ | 0.369 | 2.94 | 12 | 0.5188 | 0.7568 |
72
+ | 0.369 | 3.94 | 16 | 0.4889 | 0.7703 |
73
+ | 0.3889 | 4.94 | 20 | 0.4707 | 0.7703 |
74
+ | 0.3889 | 5.94 | 24 | 0.4914 | 0.7703 |
75
+ | 0.3889 | 6.94 | 28 | 0.6717 | 0.7432 |
76
+ | 0.3537 | 7.94 | 32 | 0.6126 | 0.7973 |
77
+ | 0.3537 | 8.94 | 36 | 0.5298 | 0.7568 |
78
+ | 0.3356 | 9.94 | 40 | 0.5882 | 0.7432 |
79
+ | 0.3356 | 10.94 | 44 | 0.5746 | 0.7432 |
80
+ | 0.3356 | 11.94 | 48 | 0.6622 | 0.7297 |
81
+ | 0.3231 | 12.94 | 52 | 0.5718 | 0.7703 |
82
+ | 0.3231 | 13.94 | 56 | 0.7128 | 0.7297 |
83
+ | 0.3732 | 14.94 | 60 | 0.5254 | 0.7838 |
84
+ | 0.3732 | 15.94 | 64 | 0.7287 | 0.7162 |
85
+ | 0.3732 | 16.94 | 68 | 0.5491 | 0.7568 |
86
+ | 0.3704 | 17.94 | 72 | 0.6270 | 0.8108 |
87
+ | 0.3704 | 18.94 | 76 | 0.5768 | 0.7973 |
88
+ | 0.3005 | 19.94 | 80 | 0.5718 | 0.7568 |
89
+ | 0.3005 | 20.94 | 84 | 0.6060 | 0.7838 |
90
+ | 0.3005 | 21.94 | 88 | 0.6006 | 0.7568 |
91
+ | 0.2739 | 22.94 | 92 | 0.5254 | 0.7703 |
92
+ | 0.2739 | 23.94 | 96 | 0.6768 | 0.7297 |
93
+ | 0.2627 | 24.94 | 100 | 0.6552 | 0.7838 |
94
+ | 0.2627 | 25.94 | 104 | 0.6359 | 0.7568 |
95
+ | 0.2627 | 26.94 | 108 | 0.6695 | 0.7568 |
96
+ | 0.2573 | 27.94 | 112 | 0.6321 | 0.7838 |
97
+ | 0.2573 | 28.94 | 116 | 0.6559 | 0.7973 |
98
+ | 0.2336 | 29.94 | 120 | 0.7345 | 0.7838 |
99
+ | 0.2336 | 30.94 | 124 | 0.6289 | 0.7703 |
100
+ | 0.2336 | 31.94 | 128 | 0.8608 | 0.6892 |
101
+ | 0.2126 | 32.94 | 132 | 0.8152 | 0.7838 |
102
+ | 0.2126 | 33.94 | 136 | 0.9124 | 0.7162 |
103
+ | 0.2 | 34.94 | 140 | 0.7841 | 0.7703 |
104
+ | 0.2 | 35.94 | 144 | 0.7741 | 0.7838 |
105
+ | 0.2 | 36.94 | 148 | 0.7580 | 0.7973 |
106
+ | 0.1858 | 37.94 | 152 | 0.7781 | 0.7973 |
107
+ | 0.1858 | 38.94 | 156 | 0.7539 | 0.7568 |
108
+ | 0.1806 | 39.94 | 160 | 0.7460 | 0.7703 |
109
+ | 0.1806 | 40.94 | 164 | 0.7814 | 0.7703 |
110
+ | 0.1806 | 41.94 | 168 | 0.7745 | 0.7973 |
111
+ | 0.1771 | 42.94 | 172 | 0.7551 | 0.7838 |
112
+ | 0.1771 | 43.94 | 176 | 0.7821 | 0.7838 |
113
+ | 0.1649 | 44.94 | 180 | 0.7822 | 0.7703 |
114
+ | 0.1649 | 45.94 | 184 | 0.7580 | 0.7838 |
115
+ | 0.1649 | 46.94 | 188 | 0.7376 | 0.7703 |
116
+ | 0.1711 | 47.94 | 192 | 0.7495 | 0.7703 |
117
+ | 0.1711 | 48.94 | 196 | 0.7561 | 0.7703 |
118
+ | 0.1579 | 49.94 | 200 | 0.7626 | 0.7838 |
119
+
120
+
121
+ ### Framework versions
122
+
123
+ - Transformers 4.26.0
124
+ - Pytorch 1.13.1+cu116
125
+ - Datasets 2.9.0
126
+ - Tokenizers 0.13.2