Hugging Face's logo

AykeeSalazar
/
vc-bantai-vit-withoutAMBI-adunest-v2

Image Classification Transformers PyTorch TensorBoard
vit generated_from_trainer Eval Results Inference Endpoints
Model card Files Metrics Community
AykeeSalazar commited on
Commit
a968522
•
1 Parent(s): bef774a

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: vc-bantai-vit-withoutAMBI-adunest-v2
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ args: Violation-Classification---Raw-10
19
+ metrics:
20
+ - name: Accuracy
21
+ type: accuracy
22
+ value: 0.7705338809034907
23
+ ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # vc-bantai-vit-withoutAMBI-adunest-v2
29
+
30
+ 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.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 0.8271
33
+ - Accuracy: 0.7705
34
+
35
+ ## Model description
36
+
37
+ More information needed
38
+
39
+ ## Intended uses & limitations
40
+
41
+ More information needed
42
+
43
+ ## Training and evaluation data
44
+
45
+ More information needed
46
+
47
+ ## Training procedure
48
+
49
+ ### Training hyperparameters
50
+
51
+ The following hyperparameters were used during training:
52
+ - learning_rate: 0.0005
53
+ - train_batch_size: 32
54
+ - eval_batch_size: 32
55
+ - seed: 42
56
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
+ - lr_scheduler_type: linear
58
+ - num_epochs: 200
59
+ - mixed_precision_training: Native AMP
60
+
61
+ ### Training results
62
+
63
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
64
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
65
+ | No log | 0.4 | 100 | 0.3811 | 0.8511 |
66
+ | No log | 0.81 | 200 | 0.3707 | 0.8609 |
67
+ | No log | 1.21 | 300 | 0.5708 | 0.7325 |
68
+ | No log | 1.61 | 400 | 0.3121 | 0.8778 |
69
+ | 0.3308 | 2.02 | 500 | 0.3358 | 0.8445 |
70
+ | 0.3308 | 2.42 | 600 | 0.2820 | 0.8768 |
71
+ | 0.3308 | 2.82 | 700 | 0.4825 | 0.7695 |
72
+ | 0.3308 | 3.23 | 800 | 0.3133 | 0.8640 |
73
+ | 0.3308 | 3.63 | 900 | 0.4509 | 0.8219 |
74
+ | 0.2028 | 4.03 | 1000 | 0.5426 | 0.7551 |
75
+ | 0.2028 | 4.44 | 1100 | 0.4886 | 0.8552 |
76
+ | 0.2028 | 4.84 | 1200 | 0.5649 | 0.7695 |
77
+ | 0.2028 | 5.24 | 1300 | 0.5925 | 0.7900 |
78
+ | 0.2028 | 5.65 | 1400 | 0.4203 | 0.8439 |
79
+ | 0.1471 | 6.05 | 1500 | 0.4275 | 0.8486 |
80
+ | 0.1471 | 6.45 | 1600 | 0.3683 | 0.8727 |
81
+ | 0.1471 | 6.85 | 1700 | 0.5709 | 0.8121 |
82
+ | 0.1471 | 7.26 | 1800 | 0.6209 | 0.7680 |
83
+ | 0.1471 | 7.66 | 1900 | 0.4971 | 0.8147 |
84
+ | 0.101 | 8.06 | 2000 | 0.8792 | 0.7567 |
85
+ | 0.101 | 8.47 | 2100 | 0.3288 | 0.8670 |
86
+ | 0.101 | 8.87 | 2200 | 0.3643 | 0.8342 |
87
+ | 0.101 | 9.27 | 2300 | 0.4883 | 0.8711 |
88
+ | 0.101 | 9.68 | 2400 | 0.2892 | 0.8943 |
89
+ | 0.0667 | 10.08 | 2500 | 0.5437 | 0.8398 |
90
+ | 0.0667 | 10.48 | 2600 | 0.5841 | 0.8450 |
91
+ | 0.0667 | 10.89 | 2700 | 0.8016 | 0.8219 |
92
+ | 0.0667 | 11.29 | 2800 | 0.6389 | 0.7772 |
93
+ | 0.0667 | 11.69 | 2900 | 0.3714 | 0.8753 |
94
+ | 0.0674 | 12.1 | 3000 | 0.9811 | 0.7130 |
95
+ | 0.0674 | 12.5 | 3100 | 0.6359 | 0.8101 |
96
+ | 0.0674 | 12.9 | 3200 | 0.5691 | 0.8285 |
97
+ | 0.0674 | 13.31 | 3300 | 0.6123 | 0.8316 |
98
+ | 0.0674 | 13.71 | 3400 | 0.3655 | 0.8978 |
99
+ | 0.0525 | 14.11 | 3500 | 0.4988 | 0.8583 |
100
+ | 0.0525 | 14.52 | 3600 | 0.6153 | 0.8450 |
101
+ | 0.0525 | 14.92 | 3700 | 0.4189 | 0.8881 |
102
+ | 0.0525 | 15.32 | 3800 | 0.9713 | 0.7967 |
103
+ | 0.0525 | 15.73 | 3900 | 1.1224 | 0.7967 |
104
+ | 0.0438 | 16.13 | 4000 | 0.5725 | 0.8578 |
105
+ | 0.0438 | 16.53 | 4100 | 0.4725 | 0.8532 |
106
+ | 0.0438 | 16.94 | 4200 | 0.4696 | 0.8640 |
107
+ | 0.0438 | 17.34 | 4300 | 0.4028 | 0.8789 |
108
+ | 0.0438 | 17.74 | 4400 | 0.9452 | 0.7746 |
109
+ | 0.0462 | 18.15 | 4500 | 0.4455 | 0.8783 |
110
+ | 0.0462 | 18.55 | 4600 | 0.6328 | 0.8311 |
111
+ | 0.0462 | 18.95 | 4700 | 0.6707 | 0.8296 |
112
+ | 0.0462 | 19.35 | 4800 | 0.7771 | 0.8429 |
113
+ | 0.0462 | 19.76 | 4900 | 1.2832 | 0.7408 |
114
+ | 0.0381 | 20.16 | 5000 | 0.5415 | 0.8737 |
115
+ | 0.0381 | 20.56 | 5100 | 0.8932 | 0.7977 |
116
+ | 0.0381 | 20.97 | 5200 | 0.5182 | 0.8691 |
117
+ | 0.0381 | 21.37 | 5300 | 0.5967 | 0.8794 |
118
+ | 0.0381 | 21.77 | 5400 | 0.8271 | 0.7705 |
119
+
120
+
121
+ ### Framework versions
122
+
123
+ - Transformers 4.20.1
124
+ - Pytorch 1.12.0+cu113
125
+ - Datasets 2.3.2
126
+ - Tokenizers 0.12.1