Hugging Face's logo

jalaneunos
/
vit-base-patch16-224-in21k-finetuned-FER2013

Image Classification
Transformers
TensorBoard
Safetensors
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
jalaneunos commited on
Commit
71af103
·
verified ·
1 Parent(s): b37612f

Model save

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8683385579937304
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  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.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3321
36
- - Accuracy: 0.8683
37
 
38
  ## Model description
39
 
@@ -67,21 +67,21 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.495 | 1.0 | 202 | 0.4660 | 0.7739 |
71
- | 0.4632 | 2.0 | 404 | 0.3820 | 0.8286 |
72
- | 0.4013 | 3.0 | 606 | 0.3562 | 0.8447 |
73
- | 0.3883 | 4.0 | 808 | 0.3426 | 0.8516 |
74
- | 0.3801 | 5.0 | 1010 | 0.3303 | 0.8561 |
75
- | 0.3612 | 6.0 | 1212 | 0.3362 | 0.8558 |
76
- | 0.3504 | 7.0 | 1414 | 0.3302 | 0.8652 |
77
- | 0.3366 | 8.0 | 1616 | 0.3321 | 0.8683 |
78
- | 0.3007 | 9.0 | 1818 | 0.3330 | 0.8666 |
79
- | 0.3089 | 10.0 | 2020 | 0.3327 | 0.8656 |
80
 
81
 
82
  ### Framework versions
83
 
84
- - Transformers 4.37.0
85
- - Pytorch 2.1.0+cu121
86
- - Datasets 2.16.1
87
- - Tokenizers 0.15.0
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8732149076976663
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  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.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.3264
36
+ - Accuracy: 0.8732
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.4811 | 1.0 | 202 | 0.4315 | 0.8004 |
71
+ | 0.4287 | 2.0 | 404 | 0.3579 | 0.8433 |
72
+ | 0.4184 | 3.0 | 606 | 0.3517 | 0.8467 |
73
+ | 0.3931 | 4.0 | 808 | 0.3308 | 0.8555 |
74
+ | 0.3667 | 5.0 | 1010 | 0.3204 | 0.8610 |
75
+ | 0.3545 | 6.0 | 1212 | 0.3144 | 0.8659 |
76
+ | 0.3137 | 7.0 | 1414 | 0.3308 | 0.8642 |
77
+ | 0.3178 | 8.0 | 1616 | 0.3230 | 0.8645 |
78
+ | 0.2998 | 9.0 | 1818 | 0.3206 | 0.8708 |
79
+ | 0.2773 | 10.0 | 2020 | 0.3264 | 0.8732 |
80
 
81
 
82
  ### Framework versions
83
 
84
+ - Transformers 4.38.2
85
+ - Pytorch 2.2.1+cu121
86
+ - Datasets 2.18.0
87
+ - Tokenizers 0.15.2