Hugging Face's logo

ahmedALM1221
/
swinv2-large-patch4-window12-192-22k-finetuned-eurosat-50

Image Classification
Transformers
PyTorch
TensorBoard
swinv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ahmedALM1221 commited on
Commit
3216a1b
•
1 Parent(s): d8d7231

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +96 -0
README.md ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: swinv2-large-patch4-window12-192-22k-finetuned-eurosat-50
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: Skin_Cancer
19
+ split: train
20
+ args: Skin_Cancer
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.7220338983050848
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
+ # swinv2-large-patch4-window12-192-22k-finetuned-eurosat-50
31
+
32
+ This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-large-patch4-window12-192-22k) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.6967
35
+ - Accuracy: 0.7220
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-06
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: 0.005
63
+ - num_epochs: 20
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 0.97 | 9 | 1.6984 | 0.3729 |
70
+ | No log | 1.95 | 18 | 1.5150 | 0.4881 |
71
+ | 1.6944 | 2.92 | 27 | 1.3304 | 0.5390 |
72
+ | 1.6944 | 4.0 | 37 | 1.1761 | 0.6 |
73
+ | 1.3633 | 4.97 | 46 | 1.0588 | 0.6373 |
74
+ | 1.3633 | 5.95 | 55 | 0.9952 | 0.6475 |
75
+ | 1.1208 | 6.92 | 64 | 0.9326 | 0.6610 |
76
+ | 1.1208 | 8.0 | 74 | 0.8785 | 0.6712 |
77
+ | 0.9891 | 8.97 | 83 | 0.8478 | 0.6746 |
78
+ | 0.9891 | 9.95 | 92 | 0.8144 | 0.6847 |
79
+ | 0.9011 | 10.92 | 101 | 0.7774 | 0.7017 |
80
+ | 0.9011 | 12.0 | 111 | 0.7567 | 0.6983 |
81
+ | 0.8143 | 12.97 | 120 | 0.7525 | 0.6949 |
82
+ | 0.8143 | 13.95 | 129 | 0.7309 | 0.7051 |
83
+ | 0.8143 | 14.92 | 138 | 0.7141 | 0.7119 |
84
+ | 0.7926 | 16.0 | 148 | 0.7095 | 0.7186 |
85
+ | 0.7926 | 16.97 | 157 | 0.7057 | 0.7220 |
86
+ | 0.7439 | 17.95 | 166 | 0.6988 | 0.7220 |
87
+ | 0.7439 | 18.92 | 175 | 0.6967 | 0.7220 |
88
+ | 0.7533 | 19.46 | 180 | 0.6967 | 0.7220 |
89
+
90
+
91
+ ### Framework versions
92
+
93
+ - Transformers 4.30.2
94
+ - Pytorch 2.0.1+cu118
95
+ - Datasets 2.13.1
96
+ - Tokenizers 0.13.3