Hugging Face's logo

ongkn
/
attraction-classifier

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Community
5
ongkn commited on
Commit
a9bbd1a
·
unverified ·
1 Parent(s): c6ed5ea

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -16,13 +16,13 @@ model-index:
16
  dataset:
17
  name: imagefolder
18
  type: imagefolder
19
- config: smtn_girls_likeOrNot
20
  split: train
21
- args: smtn_girls_likeOrNot
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8284457478005866
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: 0.4361
36
- - Accuracy: 0.8284
37
 
38
  ## Model description
39
 
@@ -67,16 +67,16 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.6014 | 0.98 | 42 | 0.5286 | 0.7507 |
71
- | 0.4479 | 1.99 | 85 | 0.4547 | 0.8094 |
72
- | 0.3988 | 2.99 | 128 | 0.4259 | 0.8284 |
73
- | 0.3773 | 4.0 | 171 | 0.4475 | 0.7962 |
74
- | 0.3217 | 4.98 | 213 | 0.4155 | 0.8226 |
75
- | 0.2844 | 5.99 | 256 | 0.4423 | 0.8065 |
76
- | 0.2519 | 6.99 | 299 | 0.4961 | 0.8065 |
77
- | 0.2527 | 8.0 | 342 | 0.4642 | 0.8123 |
78
- | 0.2165 | 8.98 | 384 | 0.4860 | 0.8050 |
79
- | 0.2323 | 9.82 | 420 | 0.4361 | 0.8284 |
80
 
81
 
82
  ### Framework versions
 
16
  dataset:
17
  name: imagefolder
18
  type: imagefolder
19
+ config: .faces
20
  split: train
21
+ args: .faces
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8254437869822485
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: 0.4452
36
+ - Accuracy: 0.8254
37
 
38
  ## Model description
39
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.622 | 0.99 | 42 | 0.4917 | 0.7825 |
71
+ | 0.5018 | 1.99 | 84 | 0.4727 | 0.7840 |
72
+ | 0.4308 | 2.98 | 126 | 0.4231 | 0.8254 |
73
+ | 0.3811 | 4.0 | 169 | 0.4085 | 0.8254 |
74
+ | 0.304 | 4.99 | 211 | 0.4239 | 0.8062 |
75
+ | 0.2844 | 5.99 | 253 | 0.4529 | 0.8047 |
76
+ | 0.2549 | 6.98 | 295 | 0.4248 | 0.8254 |
77
+ | 0.2162 | 8.0 | 338 | 0.4202 | 0.8195 |
78
+ | 0.2073 | 8.99 | 380 | 0.4388 | 0.8328 |
79
+ | 0.1751 | 9.94 | 420 | 0.4452 | 0.8254 |
80
 
81
 
82
  ### Framework versions