Dalmatiner commited on
Commit
375bd91
·
verified ·
1 Parent(s): 735a7e5

Model save

Browse files
README.md CHANGED
@@ -3,14 +3,6 @@ library_name: transformers
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224
5
  tags:
6
- - image-classification
7
- - animals
8
- - transfer-learning
9
- - vision-transformer
10
- - vit
11
- - own-dataset
12
- - pytorch
13
- - huggingface
14
  - generated_from_trainer
15
  datasets:
16
  - imagefolder
@@ -23,7 +15,7 @@ model-index:
23
  name: Image Classification
24
  type: image-classification
25
  dataset:
26
- name: animals
27
  type: imagefolder
28
  config: default
29
  split: train
@@ -31,7 +23,7 @@ model-index:
31
  metrics:
32
  - name: Accuracy
33
  type: accuracy
34
- value: 0.987037037037037
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -39,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
39
 
40
  # cv_animals
41
 
42
- This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the animals dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.0833
45
- - Accuracy: 0.9870
46
 
47
  ## Model description
48
 
@@ -73,11 +65,11 @@ The following hyperparameters were used during training:
73
 
74
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
75
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
76
- | 1.1803 | 1.0 | 270 | 0.3215 | 0.9630 |
77
- | 0.2779 | 2.0 | 540 | 0.1634 | 0.9648 |
78
- | 0.1745 | 3.0 | 810 | 0.1407 | 0.9648 |
79
- | 0.1608 | 4.0 | 1080 | 0.1322 | 0.9630 |
80
- | 0.1486 | 5.0 | 1350 | 0.1281 | 0.9648 |
81
 
82
 
83
  ### Framework versions
 
3
  license: apache-2.0
4
  base_model: google/vit-base-patch16-224
5
  tags:
 
 
 
 
 
 
 
 
6
  - generated_from_trainer
7
  datasets:
8
  - imagefolder
 
15
  name: Image Classification
16
  type: image-classification
17
  dataset:
18
+ name: imagefolder
19
  type: imagefolder
20
  config: default
21
  split: train
 
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.9833333333333333
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  # cv_animals
33
 
34
+ 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.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.0876
37
+ - Accuracy: 0.9833
38
 
39
  ## Model description
40
 
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
67
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
68
+ | 1.1951 | 1.0 | 270 | 0.3316 | 0.9648 |
69
+ | 0.2763 | 2.0 | 540 | 0.1710 | 0.9667 |
70
+ | 0.1772 | 3.0 | 810 | 0.1482 | 0.9648 |
71
+ | 0.1533 | 4.0 | 1080 | 0.1391 | 0.9704 |
72
+ | 0.1462 | 5.0 | 1350 | 0.1350 | 0.9685 |
73
 
74
 
75
  ### Framework versions
runs/Jun01_04-17-38_ip-10-192-12-140/events.out.tfevents.1748753698.ip-10-192-12-140.2205.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86b4d09e522d1e301a8ab4aff1eb45b14804d879ffe315ab5db01fa603a0de82
3
+ size 411