Hugging Face's logo

ahmedesmail16
/
Paper_Compared-swinv2-base

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ahmedesmail16 commited on
Commit
70c90d4
·
verified ·
1 Parent(s): 8e122a9

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -10
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-base-patch4-window12-192-22k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.4533
21
- - Accuracy: 0.8679
22
 
23
  ## Model description
24
 
@@ -46,19 +46,22 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - num_epochs: 7
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
- | 1.5496 | 0.9492 | 14 | 0.6299 | 0.8183 |
56
- | 0.61 | 1.9661 | 29 | 0.8504 | 0.7540 |
57
- | 0.199 | 2.9831 | 44 | 0.4179 | 0.8555 |
58
- | 0.1152 | 4.0 | 59 | 0.5128 | 0.8397 |
59
- | 0.0512 | 4.9492 | 73 | 0.4755 | 0.8544 |
60
- | 0.0297 | 5.9661 | 88 | 0.4363 | 0.8702 |
61
- | 0.0338 | 6.6441 | 98 | 0.4533 | 0.8679 |
 
 
 
62
 
63
 
64
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window12-192-22k](https://huggingface.co/microsoft/swinv2-base-patch4-window12-192-22k) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.7159
21
+ - Accuracy: 0.8533
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 10
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:------:|:----:|:---------------:|:--------:|
55
+ | 1.6917 | 0.9492 | 14 | 0.7844 | 0.7562 |
56
+ | 0.7734 | 1.9661 | 29 | 0.4380 | 0.8521 |
57
+ | 0.1927 | 2.9831 | 44 | 0.4694 | 0.8544 |
58
+ | 0.0956 | 4.0 | 59 | 0.6487 | 0.8251 |
59
+ | 0.0638 | 4.9492 | 73 | 0.6688 | 0.8296 |
60
+ | 0.0343 | 5.9661 | 88 | 0.7615 | 0.8352 |
61
+ | 0.0182 | 6.9831 | 103 | 0.7470 | 0.8352 |
62
+ | 0.038 | 8.0 | 118 | 0.7666 | 0.8465 |
63
+ | 0.0057 | 8.9492 | 132 | 0.7086 | 0.8454 |
64
+ | 0.0062 | 9.4915 | 140 | 0.7159 | 0.8533 |
65
 
66
 
67
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75c5487bd25ff88eea3b861fa5bdf5ec28d57e3a07646f669a627ab856753413
3
  size 347661896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9226551eb8b7fbf720c0b00c4af1072564ad13a36adb23c46c64198326a02c0
3
  size 347661896