Hugging Face's logo

Dhika
/
leaves

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
1
Dhika commited on
Commit
772a4c3
·
1 Parent(s): d020b80

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +113 -0
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: leaves
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: Dhika--Leaves
19
+ split: validation
20
+ args: Dhika--Leaves
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 1.0
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
+ # leaves
31
+
32
+ This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0012
35
+ - Accuracy: 1.0
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: 0.0002
55
+ - train_batch_size: 10
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 50
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
65
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
66
+ | 0.2249 | 1.25 | 10 | 0.0323 | 1.0 |
67
+ | 0.0177 | 2.5 | 20 | 0.0112 | 1.0 |
68
+ | 0.0086 | 3.75 | 30 | 0.0075 | 1.0 |
69
+ | 0.0063 | 5.0 | 40 | 0.0059 | 1.0 |
70
+ | 0.0051 | 6.25 | 50 | 0.0050 | 1.0 |
71
+ | 0.0045 | 7.5 | 60 | 0.0044 | 1.0 |
72
+ | 0.004 | 8.75 | 70 | 0.0040 | 1.0 |
73
+ | 0.0036 | 10.0 | 80 | 0.0036 | 1.0 |
74
+ | 0.0033 | 11.25 | 90 | 0.0034 | 1.0 |
75
+ | 0.0031 | 12.5 | 100 | 0.0031 | 1.0 |
76
+ | 0.0028 | 13.75 | 110 | 0.0029 | 1.0 |
77
+ | 0.0026 | 15.0 | 120 | 0.0027 | 1.0 |
78
+ | 0.0025 | 16.25 | 130 | 0.0025 | 1.0 |
79
+ | 0.0023 | 17.5 | 140 | 0.0024 | 1.0 |
80
+ | 0.0022 | 18.75 | 150 | 0.0023 | 1.0 |
81
+ | 0.0021 | 20.0 | 160 | 0.0021 | 1.0 |
82
+ | 0.002 | 21.25 | 170 | 0.0020 | 1.0 |
83
+ | 0.0019 | 22.5 | 180 | 0.0019 | 1.0 |
84
+ | 0.0018 | 23.75 | 190 | 0.0019 | 1.0 |
85
+ | 0.0017 | 25.0 | 200 | 0.0018 | 1.0 |
86
+ | 0.0016 | 26.25 | 210 | 0.0017 | 1.0 |
87
+ | 0.0016 | 27.5 | 220 | 0.0017 | 1.0 |
88
+ | 0.0015 | 28.75 | 230 | 0.0016 | 1.0 |
89
+ | 0.0015 | 30.0 | 240 | 0.0015 | 1.0 |
90
+ | 0.0014 | 31.25 | 250 | 0.0015 | 1.0 |
91
+ | 0.0014 | 32.5 | 260 | 0.0015 | 1.0 |
92
+ | 0.0013 | 33.75 | 270 | 0.0014 | 1.0 |
93
+ | 0.0013 | 35.0 | 280 | 0.0014 | 1.0 |
94
+ | 0.0013 | 36.25 | 290 | 0.0014 | 1.0 |
95
+ | 0.0013 | 37.5 | 300 | 0.0013 | 1.0 |
96
+ | 0.0012 | 38.75 | 310 | 0.0013 | 1.0 |
97
+ | 0.0012 | 40.0 | 320 | 0.0013 | 1.0 |
98
+ | 0.0012 | 41.25 | 330 | 0.0013 | 1.0 |
99
+ | 0.0012 | 42.5 | 340 | 0.0013 | 1.0 |
100
+ | 0.0012 | 43.75 | 350 | 0.0012 | 1.0 |
101
+ | 0.0012 | 45.0 | 360 | 0.0012 | 1.0 |
102
+ | 0.0011 | 46.25 | 370 | 0.0012 | 1.0 |
103
+ | 0.0012 | 47.5 | 380 | 0.0012 | 1.0 |
104
+ | 0.0011 | 48.75 | 390 | 0.0012 | 1.0 |
105
+ | 0.0011 | 50.0 | 400 | 0.0012 | 1.0 |
106
+
107
+
108
+ ### Framework versions
109
+
110
+ - Transformers 4.29.2
111
+ - Pytorch 2.0.1+cu118
112
+ - Datasets 2.12.0
113
+ - Tokenizers 0.13.3