Hugging Face's logo

hyeongjin99
/
vit_base_aihub_model_py

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
1
hyeongjin99 commited on
Commit
d3426b5
•
1 Parent(s): 7679dc0

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.9985872380503885
28
  - name: Precision
29
  type: precision
30
- value: 0.9989954885489135
31
  - name: Recall
32
  type: recall
33
- value: 0.998161142953993
34
  - name: F1
35
  type: f1
36
- value: 0.9985770990024514
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
43
 
44
  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.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 0.0217
47
- - Accuracy: 0.9986
48
- - Precision: 0.9990
49
- - Recall: 0.9982
50
- - F1: 0.9986
51
 
52
  ## Model description
53
 
@@ -81,11 +81,11 @@ The following hyperparameters were used during training:
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
83
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
84
- | 0.1235 | 1.0 | 149 | 0.0936 | 0.9858 | 0.9845 | 0.9814 | 0.9830 |
85
- | 0.067 | 2.0 | 299 | 0.0622 | 0.9878 | 0.9909 | 0.9813 | 0.9859 |
86
- | 0.049 | 3.0 | 448 | 0.0322 | 0.9968 | 0.9969 | 0.9959 | 0.9964 |
87
- | 0.0477 | 4.0 | 598 | 0.0249 | 0.9978 | 0.9985 | 0.9965 | 0.9975 |
88
- | 0.0336 | 4.98 | 745 | 0.0217 | 0.9986 | 0.9990 | 0.9982 | 0.9986 |
89
 
90
 
91
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.9977631269131152
28
  - name: Precision
29
  type: precision
30
+ value: 0.998134723737648
31
  - name: Recall
32
  type: recall
33
+ value: 0.9974298183920257
34
  - name: F1
35
  type: f1
36
+ value: 0.9977816548360952
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
 
44
  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.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.0228
47
+ - Accuracy: 0.9978
48
+ - Precision: 0.9981
49
+ - Recall: 0.9974
50
+ - F1: 0.9978
51
 
52
  ## Model description
53
 
 
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
83
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
84
+ | 0.1415 | 1.0 | 149 | 0.1286 | 0.9712 | 0.9788 | 0.9623 | 0.9700 |
85
+ | 0.0671 | 2.0 | 299 | 0.0463 | 0.9948 | 0.9917 | 0.9946 | 0.9932 |
86
+ | 0.0423 | 3.0 | 448 | 0.0356 | 0.9952 | 0.9970 | 0.9908 | 0.9939 |
87
+ | 0.0383 | 4.0 | 598 | 0.0242 | 0.9976 | 0.9980 | 0.9972 | 0.9976 |
88
+ | 0.033 | 4.98 | 745 | 0.0228 | 0.9978 | 0.9981 | 0.9974 | 0.9978 |
89
 
90
 
91
  ### Framework versions