AykeeSalazar
commited on
Commit
•
a968522
1
Parent(s):
bef774a
update model card README.md
Browse files
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
|