Hugging Face's logo

karim155
/
swin-tiny-patch4-window7-224-finetuned

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
karim155 commited on
Commit
6a5e8a7
·
verified ·
1 Parent(s): d67fa45

Model save

Browse files
Files changed (2) hide show
  1. README.md +15 -15
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  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 None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 1.0175
25
- - Accuracy: 0.6477
26
- - Precision: 0.6509
27
- - Recall: 0.6477
28
- - F1: 0.6485
29
 
30
  ## Model description
31
 
@@ -59,16 +59,16 @@ The following hyperparameters were used during training:
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
61
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
62
- | 1.3888 | 0.9846 | 32 | 1.2314 | 0.5371 | 0.5735 | 0.5371 | 0.5336 |
63
- | 1.1842 | 2.0 | 65 | 1.1335 | 0.5630 | 0.5982 | 0.5630 | 0.5670 |
64
- | 1.0504 | 2.9846 | 97 | 1.0643 | 0.5948 | 0.6230 | 0.5948 | 0.5972 |
65
- | 1.036 | 4.0 | 130 | 1.0435 | 0.5756 | 0.6274 | 0.5756 | 0.5911 |
66
- | 0.9591 | 4.9846 | 162 | 1.0463 | 0.5987 | 0.6253 | 0.5987 | 0.6030 |
67
- | 0.8893 | 6.0 | 195 | 1.0203 | 0.6035 | 0.6298 | 0.6035 | 0.6112 |
68
- | 0.8339 | 6.9846 | 227 | 1.0156 | 0.6400 | 0.6397 | 0.6400 | 0.6384 |
69
- | 0.8154 | 8.0 | 260 | 1.0042 | 0.6141 | 0.6328 | 0.6141 | 0.6209 |
70
- | 0.767 | 8.9846 | 292 | 1.0123 | 0.6391 | 0.6472 | 0.6391 | 0.6424 |
71
- | 0.7554 | 9.8462 | 320 | 1.0175 | 0.6477 | 0.6509 | 0.6477 | 0.6485 |
72
 
73
 
74
  ### Framework versions
 
21
 
22
  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 None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 1.0150
25
+ - Accuracy: 0.5582
26
+ - Precision: 0.6432
27
+ - Recall: 0.5582
28
+ - F1: 0.5799
29
 
30
  ## Model description
31
 
 
59
 
60
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
61
  |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
62
+ | 1.1775 | 0.9846 | 32 | 1.0874 | 0.3600 | 0.6471 | 0.3600 | 0.3554 |
63
+ | 1.1165 | 2.0 | 65 | 1.0633 | 0.4379 | 0.6194 | 0.4379 | 0.4705 |
64
+ | 0.9901 | 2.9846 | 97 | 1.0061 | 0.4995 | 0.6327 | 0.4995 | 0.5200 |
65
+ | 0.9606 | 4.0 | 130 | 0.9967 | 0.3994 | 0.6477 | 0.3994 | 0.4159 |
66
+ | 0.8326 | 4.9846 | 162 | 0.9942 | 0.4841 | 0.6228 | 0.4841 | 0.5036 |
67
+ | 0.824 | 6.0 | 195 | 0.9646 | 0.4937 | 0.6523 | 0.4937 | 0.5250 |
68
+ | 0.7647 | 6.9846 | 227 | 1.0272 | 0.5669 | 0.6401 | 0.5669 | 0.5827 |
69
+ | 0.7682 | 8.0 | 260 | 1.0007 | 0.5101 | 0.6531 | 0.5101 | 0.5371 |
70
+ | 0.721 | 8.9846 | 292 | 1.0121 | 0.5515 | 0.6464 | 0.5515 | 0.5744 |
71
+ | 0.6878 | 9.8462 | 320 | 1.0150 | 0.5582 | 0.6432 | 0.5582 | 0.5799 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:364f599b7a6ef13d2c1db5c4c85b0c19a45334e65cdad96e252b059025cbe71f
3
  size 110352060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3adc684231ac1da3fee3c174a352d077686ff8aa1d549b1769b8eeb5b37dcd28
3
  size 110352060