Hugging Face's logo

EdBianchi
/
vit-fire-detection

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
10
EdBianchi commited on
Commit
a5f21da
•
1 Parent(s): 12d817e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  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 None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.0524
21
- - Precision: 0.9803
22
- - Recall: 0.9802
23
 
24
  ## Model description
25
 
@@ -38,7 +38,7 @@ More information needed
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
- - learning_rate: 0.002
42
  - train_batch_size: 32
43
  - eval_batch_size: 32
44
  - seed: 42
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall |
53
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
54
- | 0.5087 | 1.0 | 190 | 0.5356 | 0.8054 | 0.7421 |
55
- | 0.2943 | 2.0 | 380 | 0.1430 | 0.9536 | 0.9524 |
56
- | 0.2409 | 3.0 | 570 | 0.1360 | 0.9541 | 0.9537 |
57
- | 0.1722 | 4.0 | 760 | 0.1265 | 0.9557 | 0.9550 |
58
- | 0.1726 | 5.0 | 950 | 0.1011 | 0.9633 | 0.9630 |
59
- | 0.1563 | 6.0 | 1140 | 0.0946 | 0.9695 | 0.9696 |
60
- | 0.1181 | 7.0 | 1330 | 0.0961 | 0.9643 | 0.9630 |
61
- | 0.1288 | 8.0 | 1520 | 0.0616 | 0.9765 | 0.9762 |
62
- | 0.0858 | 9.0 | 1710 | 0.0699 | 0.9765 | 0.9762 |
63
- | 0.0539 | 10.0 | 1900 | 0.0524 | 0.9803 | 0.9802 |
64
 
65
 
66
  ### Framework versions
 
17
 
18
  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 None dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0126
21
+ - Precision: 0.9960
22
+ - Recall: 0.9960
23
 
24
  ## Model description
25
 
 
38
  ### Training hyperparameters
39
 
40
  The following hyperparameters were used during training:
41
+ - learning_rate: 0.0002
42
  - train_batch_size: 32
43
  - eval_batch_size: 32
44
  - seed: 42
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall |
53
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|
54
+ | 0.1018 | 1.0 | 190 | 0.0375 | 0.9934 | 0.9934 |
55
+ | 0.0484 | 2.0 | 380 | 0.0167 | 0.9961 | 0.9960 |
56
+ | 0.0357 | 3.0 | 570 | 0.0253 | 0.9948 | 0.9947 |
57
+ | 0.0133 | 4.0 | 760 | 0.0198 | 0.9961 | 0.9960 |
58
+ | 0.012 | 5.0 | 950 | 0.0203 | 0.9947 | 0.9947 |
59
+ | 0.0139 | 6.0 | 1140 | 0.0204 | 0.9947 | 0.9947 |
60
+ | 0.0076 | 7.0 | 1330 | 0.0175 | 0.9961 | 0.9960 |
61
+ | 0.0098 | 8.0 | 1520 | 0.0115 | 0.9974 | 0.9974 |
62
+ | 0.0062 | 9.0 | 1710 | 0.0133 | 0.9960 | 0.9960 |
63
+ | 0.0012 | 10.0 | 1900 | 0.0126 | 0.9960 | 0.9960 |
64
 
65
 
66
  ### Framework versions