Hugging Face's logo

jayanta
/
google-vit-base-patch16-224-face

Image Classification
Transformers
PyTorch
TensorBoard
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
2
paul commited on
Commit
d4a67db
·
1 Parent(s): 884b0dc

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
- value: 0.6960989202368513
28
  - name: Precision
29
  type: precision
30
- value: 0.6966334506335445
31
  - name: Recall
32
  type: recall
33
- value: 0.6960989202368513
34
  - name: F1
35
  type: f1
36
- value: 0.6957934361657124
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 1.3257
47
- - Accuracy: 0.6961
48
- - Precision: 0.6966
49
- - Recall: 0.6961
50
- - F1: 0.6958
51
 
52
  ## Model description
53
 
@@ -81,14 +81,14 @@ The following hyperparameters were used during training:
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
83
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
84
- | 0.8364 | 0.99 | 89 | 0.9453 | 0.6484 | 0.6462 | 0.6484 | 0.6385 |
85
- | 0.7433 | 1.99 | 178 | 0.8876 | 0.6778 | 0.6794 | 0.6778 | 0.6730 |
86
- | 0.4732 | 2.99 | 267 | 0.9043 | 0.6872 | 0.6907 | 0.6872 | 0.6841 |
87
- | 0.2861 | 3.99 | 356 | 0.9865 | 0.6848 | 0.6808 | 0.6848 | 0.6813 |
88
- | 0.1234 | 4.99 | 445 | 1.1048 | 0.6853 | 0.6907 | 0.6853 | 0.6872 |
89
- | 0.0599 | 5.99 | 534 | 1.2362 | 0.6890 | 0.6897 | 0.6890 | 0.6876 |
90
- | 0.0289 | 6.99 | 623 | 1.3141 | 0.6931 | 0.6926 | 0.6931 | 0.6921 |
91
- | 0.0134 | 7.99 | 712 | 1.3257 | 0.6961 | 0.6966 | 0.6961 | 0.6958 |
92
 
93
 
94
  ### Framework versions
 
24
  metrics:
25
  - name: Accuracy
26
  type: accuracy
27
+ value: 0.7248574809078198
28
  - name: Precision
29
  type: precision
30
+ value: 0.717172031675939
31
  - name: Recall
32
  type: recall
33
+ value: 0.7248574809078198
34
  - name: F1
35
  type: f1
36
+ value: 0.7195690317790054
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](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 1.4531
47
+ - Accuracy: 0.7249
48
+ - Precision: 0.7172
49
+ - Recall: 0.7249
50
+ - F1: 0.7196
51
 
52
  ## Model description
53
 
 
81
 
82
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
83
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
84
+ | 0.8514 | 1.0 | 290 | 0.8464 | 0.7048 | 0.7035 | 0.7048 | 0.6909 |
85
+ | 0.7202 | 2.0 | 580 | 0.7791 | 0.7283 | 0.7297 | 0.7283 | 0.7111 |
86
+ | 0.5455 | 3.0 | 870 | 0.7950 | 0.7285 | 0.7174 | 0.7285 | 0.7171 |
87
+ | 0.334 | 4.0 | 1160 | 0.8948 | 0.7155 | 0.7152 | 0.7155 | 0.7145 |
88
+ | 0.1644 | 5.0 | 1450 | 1.0820 | 0.7239 | 0.7189 | 0.7239 | 0.7194 |
89
+ | 0.0482 | 6.0 | 1740 | 1.2792 | 0.7204 | 0.7144 | 0.7204 | 0.7160 |
90
+ | 0.0236 | 7.0 | 2030 | 1.4162 | 0.7279 | 0.7195 | 0.7279 | 0.7209 |
91
+ | 0.0049 | 8.0 | 2320 | 1.4531 | 0.7249 | 0.7172 | 0.7249 | 0.7196 |
92
 
93
 
94
  ### Framework versions