Hugging Face's logo

bombshelll
/
swin-brain-plane-classification

Image Classification
Transformers
Safetensors
swin
Generated from Trainer
Model card Files
xet
Community
bombshelll commited on
Commit
b866b23
·
verified ·
1 Parent(s): fd34ac2

Model save

Browse files
Files changed (2) hide show
  1. README.md +17 -15
  2. model.safetensors +1 -1
README.md CHANGED
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4059
22
- - Accuracy: 0.9091
23
 
24
  ## Model description
25
 
@@ -39,11 +39,11 @@ More information needed
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 5e-05
42
- - train_batch_size: 16
43
- - eval_batch_size: 16
44
  - seed: 42
45
  - gradient_accumulation_steps: 4
46
- - total_train_batch_size: 64
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
@@ -51,16 +51,18 @@ The following hyperparameters were used during training:
51
 
52
  ### Training results
53
 
54
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
56
- | 1.5674 | 0.8 | 2 | 1.1258 | 0.3636 |
57
- | 0.8875 | 2.0 | 5 | 0.9127 | 0.7273 |
58
- | 1.1485 | 2.8 | 7 | 0.7617 | 0.7879 |
59
- | 0.6152 | 4.0 | 10 | 0.6071 | 0.8485 |
60
- | 0.7519 | 4.8 | 12 | 0.5297 | 0.8788 |
61
- | 0.4554 | 6.0 | 15 | 0.4559 | 0.9091 |
62
- | 0.5892 | 6.8 | 17 | 0.4248 | 0.9091 |
63
- | 0.4184 | 8.0 | 20 | 0.4059 | 0.9091 |
 
 
64
 
65
 
66
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.0752
22
+ - Accuracy: 0.9825
23
 
24
  ## Model description
25
 
 
39
 
40
  The following hyperparameters were used during training:
41
  - learning_rate: 5e-05
42
+ - train_batch_size: 32
43
+ - eval_batch_size: 32
44
  - seed: 42
45
  - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 128
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_ratio: 0.1
 
51
 
52
  ### Training results
53
 
54
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
56
+ | 1.1099 | 0.9412 | 4 | 0.8611 | 0.5614 |
57
+ | 0.8358 | 1.8824 | 8 | 0.4899 | 0.8947 |
58
+ | 0.5173 | 2.8235 | 12 | 0.3048 | 0.9298 |
59
+ | 0.2969 | 4.0 | 17 | 0.1527 | 0.9649 |
60
+ | 0.2504 | 4.9412 | 21 | 0.1039 | 0.9825 |
61
+ | 0.2023 | 5.8824 | 25 | 0.0993 | 0.9825 |
62
+ | 0.2172 | 6.8235 | 29 | 0.0748 | 0.9737 |
63
+ | 0.1187 | 8.0 | 34 | 0.0699 | 0.9737 |
64
+ | 0.139 | 8.9412 | 38 | 0.0748 | 0.9825 |
65
+ | 0.1269 | 9.4118 | 40 | 0.0752 | 0.9825 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb3cec5dacfc3392043332f1f8cb0683780456a18931e23bb5b8fad32f509631
3
  size 110345908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d67843074f9e5365e92bdc468a40a1e4c7f844602c484aed8316b043f6a5ea3
3
  size 110345908