Hugging Face's logo

PHVK1611
/
swin-tiny-patch4-window7-224-finetuned-eurosat

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
PHVK1611 commited on
Commit
666311d
•
1 Parent(s): 194075b

Model save

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8009728415079044
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3679
36
- - Accuracy: 0.8010
37
 
38
  ## Model description
39
 
@@ -53,11 +53,11 @@ More information needed
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
- - train_batch_size: 32
57
- - eval_batch_size: 32
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
- - total_train_batch_size: 128
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
@@ -65,16 +65,16 @@ The following hyperparameters were used during training:
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.5941 | 1.0 | 694 | 0.4620 | 0.7458 |
71
- | 0.4836 | 2.0 | 1388 | 0.3887 | 0.7924 |
72
- | 0.4672 | 3.0 | 2082 | 0.3679 | 0.8010 |
73
 
74
 
75
  ### Framework versions
76
 
77
- - Transformers 4.35.0
78
- - Pytorch 1.12.1+cu113
79
- - Datasets 2.17.1
80
- - Tokenizers 0.14.1
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.9675748705246566
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 [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.1382
36
+ - Accuracy: 0.9676
37
 
38
  ## Model description
39
 
 
53
 
54
  The following hyperparameters were used during training:
55
  - learning_rate: 5e-05
56
+ - train_batch_size: 1
57
+ - eval_batch_size: 1
58
  - seed: 42
59
  - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 4
61
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
62
  - lr_scheduler_type: linear
63
  - lr_scheduler_warmup_ratio: 0.1
 
65
 
66
  ### Training results
67
 
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:------:|:-----:|:---------------:|:--------:|
70
+ | 0.318 | 1.0000 | 19982 | 0.2505 | 0.9418 |
71
+ | 0.3994 | 2.0 | 39965 | 0.1906 | 0.9531 |
72
+ | 0.4436 | 2.9999 | 59946 | 0.1382 | 0.9676 |
73
 
74
 
75
  ### Framework versions
76
 
77
+ - Transformers 4.40.2
78
+ - Pytorch 1.13.1+cu116
79
+ - Datasets 2.19.1
80
+ - Tokenizers 0.19.1