Hugging Face's logo

jeemsterri
/
fish_classification

Image Classification
Transformers
Safetensors
vit
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
jtas commited on
Commit
88b5320
·
verified ·
1 Parent(s): 13f4a45

Model save

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -23,10 +23,10 @@ model-index:
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.9984615384615385
27
  - name: F1
28
  type: f1
29
- value: 0.9985045948203843
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -36,9 +36,9 @@ should probably proofread and complete it, then remove this comment. -->
36
 
37
  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.
38
  It achieves the following results on the evaluation set:
39
- - Loss: 0.1970
40
- - Accuracy: 0.9985
41
- - F1: 0.9985
42
 
43
  ## Model description
44
 
@@ -69,13 +69,13 @@ The following hyperparameters were used during training:
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
- | 1.0209 | 1.0 | 71 | 0.7163 | 0.9969 | 0.9970 |
73
- | 0.4711 | 2.0 | 142 | 0.3916 | 0.9985 | 0.9985 |
74
- | 0.2876 | 3.0 | 213 | 0.2855 | 0.9985 | 0.9985 |
75
- | 0.2222 | 4.0 | 284 | 0.2376 | 0.9985 | 0.9985 |
76
- | 0.1915 | 5.0 | 355 | 0.2120 | 0.9985 | 0.9985 |
77
- | 0.1754 | 6.0 | 426 | 0.1990 | 0.9985 | 0.9985 |
78
- | 0.1682 | 7.0 | 497 | 0.1970 | 0.9985 | 0.9985 |
79
 
80
 
81
  ### Framework versions
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9969230769230769
27
  - name: F1
28
  type: f1
29
+ value: 0.9970182569296375
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
36
 
37
  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.
38
  It achieves the following results on the evaluation set:
39
+ - Loss: 0.2213
40
+ - Accuracy: 0.9969
41
+ - F1: 0.9970
42
 
43
  ## Model description
44
 
 
69
 
70
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
71
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
72
+ | 1.5189 | 1.0 | 71 | 1.0828 | 0.9969 | 0.9970 |
73
+ | 0.7083 | 2.0 | 142 | 0.5398 | 0.9954 | 0.9955 |
74
+ | 0.3727 | 3.0 | 213 | 0.3473 | 0.9954 | 0.9955 |
75
+ | 0.2624 | 4.0 | 284 | 0.2734 | 0.9985 | 0.9985 |
76
+ | 0.2184 | 5.0 | 355 | 0.2401 | 0.9985 | 0.9985 |
77
+ | 0.1972 | 6.0 | 426 | 0.2238 | 0.9985 | 0.9985 |
78
+ | 0.1879 | 7.0 | 497 | 0.2213 | 0.9969 | 0.9970 |
79
 
80
 
81
  ### Framework versions