Hugging Face's logo

Skafu
/
swin-tiny-patch4-window7-224-finetuned-eurosat

Image Classification
Transformers
PyTorch
TensorBoard
swin
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Skafu commited on
Commit
76c2d87
•
1 Parent(s): 4406c0e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -3,7 +3,7 @@ license: apache-2.0
3
  tags:
4
  - generated_from_trainer
5
  datasets:
6
- - cifar10
7
  metrics:
8
  - accuracy
9
  model-index:
@@ -13,15 +13,15 @@ model-index:
13
  name: Image Classification
14
  type: image-classification
15
  dataset:
16
- name: cifar10
17
- type: cifar10
18
- config: plain_text
19
  split: train
20
- args: plain_text
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
- value: 0.9708
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,10 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  # swin-tiny-patch4-window7-224-finetuned-eurosat
31
 
32
- 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 cifar10 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.0835
35
- - Accuracy: 0.9708
36
 
37
  ## Model description
38
 
@@ -66,14 +66,14 @@ The following hyperparameters were used during training:
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
- | 0.4207 | 1.0 | 351 | 0.1444 | 0.952 |
70
- | 0.3908 | 2.0 | 703 | 0.1035 | 0.964 |
71
- | 0.3587 | 2.99 | 1053 | 0.0835 | 0.9708 |
72
 
73
 
74
  ### Framework versions
75
 
76
- - Transformers 4.28.0
77
  - Pytorch 2.0.1+cu118
78
  - Datasets 2.12.0
79
  - Tokenizers 0.13.3
 
3
  tags:
4
  - generated_from_trainer
5
  datasets:
6
+ - cifar100
7
  metrics:
8
  - accuracy
9
  model-index:
 
13
  name: Image Classification
14
  type: image-classification
15
  dataset:
16
+ name: cifar100
17
+ type: cifar100
18
+ config: cifar100
19
  split: train
20
+ args: cifar100
21
  metrics:
22
  - name: Accuracy
23
  type: accuracy
24
+ value: 0.8056
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  # swin-tiny-patch4-window7-224-finetuned-eurosat
31
 
32
+ 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 cifar100 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.6458
35
+ - Accuracy: 0.8056
36
 
37
  ## Model description
38
 
 
66
 
67
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 1.6622 | 1.0 | 351 | 0.9554 | 0.7292 |
70
+ | 1.2947 | 2.0 | 703 | 0.6968 | 0.7906 |
71
+ | 1.202 | 2.99 | 1053 | 0.6458 | 0.8056 |
72
 
73
 
74
  ### Framework versions
75
 
76
+ - Transformers 4.30.1
77
  - Pytorch 2.0.1+cu118
78
  - Datasets 2.12.0
79
  - Tokenizers 0.13.3