Hugging Face's logo

AykeeSalazar
/
violation-classification-bantai-vit-v100ep

Image Classification Transformers PyTorch TensorBoard
vit generated_from_trainer Eval Results Inference Endpoints
Model card Files Metrics Community
1
AykeeSalazar commited on
Commit
ba59511
•
1 Parent(s): 1a7ee01

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -12
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.8969686033922771
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
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 image_folder dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.3011
33
- - Accuracy: 0.8970
34
 
35
  ## Model description
36
 
@@ -64,15 +64,17 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | 1.2596 | 1.0 | 101 | 1.2230 | 0.5615 |
68
- | 0.8527 | 2.0 | 202 | 0.8234 | 0.6840 |
69
- | 0.6375 | 3.0 | 303 | 0.6001 | 0.7846 |
70
- | 0.555 | 4.0 | 404 | 0.5038 | 0.8178 |
71
- | 0.4433 | 5.0 | 505 | 0.4338 | 0.8436 |
72
- | 0.406 | 6.0 | 606 | 0.3765 | 0.8661 |
73
- | 0.3517 | 7.0 | 707 | 0.3466 | 0.8793 |
74
- | 0.312 | 8.0 | 808 | 0.3011 | 0.8970 |
75
- | 0.2842 | 9.0 | 909 | 0.2943 | 0.8961 |
 
 
76
 
77
 
78
  ### Framework versions
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
+ value: 0.9155539516420065
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
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 image_folder dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.2400
33
+ - Accuracy: 0.9156
34
 
35
  ## Model description
36
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | 0.2811 | 1.0 | 101 | 0.2855 | 0.9027 |
68
+ | 0.2382 | 2.0 | 202 | 0.2763 | 0.9085 |
69
+ | 0.2361 | 3.0 | 303 | 0.2605 | 0.9109 |
70
+ | 0.196 | 4.0 | 404 | 0.2652 | 0.9110 |
71
+ | 0.1395 | 5.0 | 505 | 0.2648 | 0.9134 |
72
+ | 0.155 | 6.0 | 606 | 0.2656 | 0.9152 |
73
+ | 0.1422 | 7.0 | 707 | 0.2607 | 0.9141 |
74
+ | 0.1511 | 8.0 | 808 | 0.2557 | 0.9157 |
75
+ | 0.1938 | 9.0 | 909 | 0.2679 | 0.9049 |
76
+ | 0.2094 | 10.0 | 1010 | 0.2392 | 0.9137 |
77
+ | 0.1835 | 11.0 | 1111 | 0.2400 | 0.9156 |
78
 
79
 
80
  ### Framework versions