Erik W commited on
Commit
d7aaa97
1 Parent(s): 172a035

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +95 -0
README.md ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - imagefolder
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: swinv2-small-patch4-window16-256-finetuned-eurosat
13
+ results:
14
+ - task:
15
+ name: Image Classification
16
+ type: image-classification
17
+ dataset:
18
+ name: imagefolder
19
+ type: imagefolder
20
+ config: default
21
+ split: train
22
+ args: default
23
+ metrics:
24
+ - name: Accuracy
25
+ type: accuracy
26
+ value: 0.9892592592592593
27
+ - name: F1
28
+ type: f1
29
+ value: 0.9892542163878574
30
+ - name: Precision
31
+ type: precision
32
+ value: 0.9892896521886161
33
+ - name: Recall
34
+ type: recall
35
+ value: 0.9892592592592593
36
+ ---
37
+
38
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
39
+ should probably proofread and complete it, then remove this comment. -->
40
+
41
+ # swinv2-small-patch4-window16-256-finetuned-eurosat
42
+
43
+ This model is a fine-tuned version of [microsoft/swinv2-small-patch4-window16-256](https://huggingface.co/microsoft/swinv2-small-patch4-window16-256) on the imagefolder dataset.
44
+ It achieves the following results on the evaluation set:
45
+ - Loss: 0.0328
46
+ - Accuracy: 0.9893
47
+ - F1: 0.9893
48
+ - Precision: 0.9893
49
+ - Recall: 0.9893
50
+
51
+ ## Model description
52
+
53
+ More information needed
54
+
55
+ ## Intended uses & limitations
56
+
57
+ More information needed
58
+
59
+ ## Training and evaluation data
60
+
61
+ More information needed
62
+
63
+ ## Training procedure
64
+
65
+ ### Training hyperparameters
66
+
67
+ The following hyperparameters were used during training:
68
+ - learning_rate: 0.0001
69
+ - train_batch_size: 24
70
+ - eval_batch_size: 24
71
+ - seed: 42
72
+ - gradient_accumulation_steps: 4
73
+ - total_train_batch_size: 96
74
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
+ - lr_scheduler_type: linear
76
+ - lr_scheduler_warmup_ratio: 0.2
77
+ - num_epochs: 5
78
+
79
+ ### Training results
80
+
81
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
82
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
83
+ | 0.2326 | 1.0 | 253 | 0.0870 | 0.9715 | 0.9716 | 0.9720 | 0.9715 |
84
+ | 0.1955 | 2.0 | 506 | 0.0576 | 0.9789 | 0.9788 | 0.9794 | 0.9789 |
85
+ | 0.1229 | 3.0 | 759 | 0.0450 | 0.9837 | 0.9837 | 0.9839 | 0.9837 |
86
+ | 0.0797 | 4.0 | 1012 | 0.0332 | 0.9889 | 0.9889 | 0.9889 | 0.9889 |
87
+ | 0.0826 | 5.0 | 1265 | 0.0328 | 0.9893 | 0.9893 | 0.9893 | 0.9893 |
88
+
89
+
90
+ ### Framework versions
91
+
92
+ - Transformers 4.22.1
93
+ - Pytorch 1.12.1+cu113
94
+ - Datasets 2.5.1
95
+ - Tokenizers 0.12.1