Hugging Face's logo

valadhi
/
swin-tiny-patch4-window7-224-finetuned-agrivision

Image Classification
Transformers
PyTorch
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
valadhi commited on
Commit
6e8fa4d
•
1 Parent(s): b8c0c6e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +106 -0
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-agrivision
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: 0.9230769230769231
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-agrivision
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: 0.2078
35
+ - Accuracy: 0.9231
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: 30
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | No log | 1.0 | 1 | 1.0943 | 0.3077 |
70
+ | No log | 2.0 | 2 | 1.0435 | 0.3846 |
71
+ | No log | 3.0 | 3 | 0.9499 | 0.6923 |
72
+ | No log | 4.0 | 4 | 0.8199 | 0.7692 |
73
+ | No log | 5.0 | 5 | 0.7033 | 0.7692 |
74
+ | No log | 6.0 | 6 | 0.6062 | 0.7692 |
75
+ | No log | 7.0 | 7 | 0.5142 | 0.7692 |
76
+ | No log | 8.0 | 8 | 0.4379 | 0.8462 |
77
+ | No log | 9.0 | 9 | 0.3900 | 0.8462 |
78
+ | 0.6751 | 10.0 | 10 | 0.3688 | 0.8462 |
79
+ | 0.6751 | 11.0 | 11 | 0.3510 | 0.8462 |
80
+ | 0.6751 | 12.0 | 12 | 0.3228 | 0.9231 |
81
+ | 0.6751 | 13.0 | 13 | 0.2788 | 0.9231 |
82
+ | 0.6751 | 14.0 | 14 | 0.2326 | 1.0 |
83
+ | 0.6751 | 15.0 | 15 | 0.2043 | 1.0 |
84
+ | 0.6751 | 16.0 | 16 | 0.1934 | 1.0 |
85
+ | 0.6751 | 17.0 | 17 | 0.1933 | 1.0 |
86
+ | 0.6751 | 18.0 | 18 | 0.1954 | 1.0 |
87
+ | 0.6751 | 19.0 | 19 | 0.2065 | 1.0 |
88
+ | 0.0563 | 20.0 | 20 | 0.2209 | 0.9231 |
89
+ | 0.0563 | 21.0 | 21 | 0.2424 | 0.8462 |
90
+ | 0.0563 | 22.0 | 22 | 0.2537 | 0.8462 |
91
+ | 0.0563 | 23.0 | 23 | 0.2508 | 0.8462 |
92
+ | 0.0563 | 24.0 | 24 | 0.2425 | 0.8462 |
93
+ | 0.0563 | 25.0 | 25 | 0.2381 | 0.8462 |
94
+ | 0.0563 | 26.0 | 26 | 0.2351 | 0.8462 |
95
+ | 0.0563 | 27.0 | 27 | 0.2266 | 0.9231 |
96
+ | 0.0563 | 28.0 | 28 | 0.2178 | 0.9231 |
97
+ | 0.0563 | 29.0 | 29 | 0.2111 | 0.9231 |
98
+ | 0.007 | 30.0 | 30 | 0.2078 | 0.9231 |
99
+
100
+
101
+ ### Framework versions
102
+
103
+ - Transformers 4.21.1
104
+ - Pytorch 1.12.1
105
+ - Datasets 2.4.0
106
+ - Tokenizers 0.12.1