AykeeSalazar
commited on
Commit
•
0b22199
1
Parent(s):
148aab4
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-v3
|
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: 0.8218352310783658
|
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-v3
|
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: 0.8889
|
33 |
+
- Accuracy: 0.8218
|
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 | 0.38 | 100 | 0.8208 | 0.7147 |
|
66 |
+
| No log | 0.76 | 200 | 0.8861 | 0.7595 |
|
67 |
+
| No log | 1.14 | 300 | 0.4306 | 0.7910 |
|
68 |
+
| No log | 1.52 | 400 | 0.5222 | 0.8245 |
|
69 |
+
| 0.3448 | 1.9 | 500 | 0.8621 | 0.7602 |
|
70 |
+
| 0.3448 | 2.28 | 600 | 0.2902 | 0.8801 |
|
71 |
+
| 0.3448 | 2.66 | 700 | 0.3687 | 0.8426 |
|
72 |
+
| 0.3448 | 3.04 | 800 | 0.3585 | 0.8694 |
|
73 |
+
| 0.3448 | 3.42 | 900 | 0.6546 | 0.7897 |
|
74 |
+
| 0.2183 | 3.8 | 1000 | 0.3881 | 0.8272 |
|
75 |
+
| 0.2183 | 4.18 | 1100 | 0.9650 | 0.7709 |
|
76 |
+
| 0.2183 | 4.56 | 1200 | 0.6444 | 0.7917 |
|
77 |
+
| 0.2183 | 4.94 | 1300 | 0.4685 | 0.8707 |
|
78 |
+
| 0.2183 | 5.32 | 1400 | 0.4972 | 0.8506 |
|
79 |
+
| 0.157 | 5.7 | 1500 | 0.4010 | 0.8513 |
|
80 |
+
| 0.157 | 6.08 | 1600 | 0.4629 | 0.8419 |
|
81 |
+
| 0.157 | 6.46 | 1700 | 0.4258 | 0.8714 |
|
82 |
+
| 0.157 | 6.84 | 1800 | 0.4383 | 0.8573 |
|
83 |
+
| 0.157 | 7.22 | 1900 | 0.5324 | 0.8493 |
|
84 |
+
| 0.113 | 7.6 | 2000 | 0.3212 | 0.8942 |
|
85 |
+
| 0.113 | 7.98 | 2100 | 0.8621 | 0.8326 |
|
86 |
+
| 0.113 | 8.37 | 2200 | 0.6050 | 0.8131 |
|
87 |
+
| 0.113 | 8.75 | 2300 | 0.7173 | 0.7991 |
|
88 |
+
| 0.113 | 9.13 | 2400 | 0.5313 | 0.8125 |
|
89 |
+
| 0.0921 | 9.51 | 2500 | 0.6584 | 0.8158 |
|
90 |
+
| 0.0921 | 9.89 | 2600 | 0.8727 | 0.7930 |
|
91 |
+
| 0.0921 | 10.27 | 2700 | 0.4222 | 0.8922 |
|
92 |
+
| 0.0921 | 10.65 | 2800 | 0.5811 | 0.8265 |
|
93 |
+
| 0.0921 | 11.03 | 2900 | 0.6175 | 0.8372 |
|
94 |
+
| 0.0701 | 11.41 | 3000 | 0.3914 | 0.8835 |
|
95 |
+
| 0.0701 | 11.79 | 3100 | 0.3364 | 0.8654 |
|
96 |
+
| 0.0701 | 12.17 | 3200 | 0.6223 | 0.8359 |
|
97 |
+
| 0.0701 | 12.55 | 3300 | 0.7830 | 0.8125 |
|
98 |
+
| 0.0701 | 12.93 | 3400 | 0.4356 | 0.8942 |
|
99 |
+
| 0.0552 | 13.31 | 3500 | 0.7553 | 0.8232 |
|
100 |
+
| 0.0552 | 13.69 | 3600 | 0.9107 | 0.8292 |
|
101 |
+
| 0.0552 | 14.07 | 3700 | 0.6108 | 0.8580 |
|
102 |
+
| 0.0552 | 14.45 | 3800 | 0.5732 | 0.8567 |
|
103 |
+
| 0.0552 | 14.83 | 3900 | 0.5087 | 0.8614 |
|
104 |
+
| 0.0482 | 15.21 | 4000 | 0.8889 | 0.8218 |
|
105 |
+
|
106 |
+
|
107 |
+
### Framework versions
|
108 |
+
|
109 |
+
- Transformers 4.20.1
|
110 |
+
- Pytorch 1.12.0+cu113
|
111 |
+
- Datasets 2.3.2
|
112 |
+
- Tokenizers 0.12.1
|