hchcsuim commited on
Commit
c07b127
·
verified ·
1 Parent(s): 99e5e46

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +12 -5
README.md CHANGED
@@ -11,7 +11,7 @@ metrics:
11
  - recall
12
  - f1
13
  model-index:
14
- - name: swin-tiny-patch4-window7-224-finetuned-FaceAIorNot-105330
15
  results:
16
  - task:
17
  name: Image Classification
@@ -40,7 +40,9 @@ model-index:
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
41
  should probably proofread and complete it, then remove this comment. -->
42
 
43
- # swin-tiny-patch4-window7-224-finetuned-FaceAIorNot-105330
 
 
44
 
45
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
46
  It achieves the following results on the evaluation set:
@@ -52,15 +54,20 @@ It achieves the following results on the evaluation set:
52
 
53
  ## Model description
54
 
55
- More information needed
56
 
57
  ## Intended uses & limitations
58
 
59
- More information needed
 
60
 
61
  ## Training and evaluation data
62
 
63
- More information needed
 
 
 
 
64
 
65
  ## Training procedure
66
 
 
11
  - recall
12
  - f1
13
  model-index:
14
+ - name: FaceAIorNot
15
  results:
16
  - task:
17
  name: Image Classification
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
41
  should probably proofread and complete it, then remove this comment. -->
42
 
43
+ # FaceAIorNot
44
+
45
+ Face AI or Not
46
 
47
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
48
  It achieves the following results on the evaluation set:
 
54
 
55
  ## Model description
56
 
57
+ Two classes: AI-generated, Not AI-generated
58
 
59
  ## Intended uses & limitations
60
 
61
+ Classify an face image if is generated by AI.
62
+ The classify result may not is 100% right.
63
 
64
  ## Training and evaluation data
65
 
66
+ Finetune in 105,330 face images.
67
+ 17 datasets.
68
+ 14 AI Image Generation Techniques.
69
+ 50% real faces and 50% AI-generated faces.
70
+ Data set cut into 90% Train set, 10% Test set(evaluation set).
71
 
72
  ## Training procedure
73