Hugging Face's logo

howdyaendra
/
microsoft-swinv2-small-patch4-window16-256-finetuned-xblockm

Image Classification
Transformers
ONNX
Safetensors
swinv2
Generated from Trainer
Model card Files Community
howdyaendra commited on
Commit
a8f0a5d
·
verified ·
1 Parent(s): 8497273

Model save

Browse files
Files changed (2) hide show
  1. README.md +11 -13
  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/swinv2-small-patch4-window16-256](https://huggingface.co/microsoft/swinv2-small-patch4-window16-256) on the imagefolder dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.1533
22
- - Roc Auc: 0.9388
23
 
24
  ## Model description
25
 
@@ -47,22 +47,20 @@ The following hyperparameters were used during training:
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
50
- - num_epochs: 10
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Roc Auc |
55
  |:-------------:|:------:|:----:|:---------------:|:-------:|
56
- | 0.4351 | 0.9877 | 20 | 0.2316 | 0.8063 |
57
- | 0.2035 | 1.9753 | 40 | 0.1882 | 0.8732 |
58
- | 0.1716 | 2.9630 | 60 | 0.1662 | 0.8984 |
59
- | 0.1582 | 4.0 | 81 | 0.1470 | 0.9205 |
60
- | 0.1358 | 4.9877 | 101 | 0.1439 | 0.9304 |
61
- | 0.1148 | 5.9753 | 121 | 0.1332 | 0.9426 |
62
- | 0.1011 | 6.9630 | 141 | 0.1450 | 0.9291 |
63
- | 0.0778 | 8.0 | 162 | 0.1358 | 0.9432 |
64
- | 0.0571 | 8.9877 | 182 | 0.1447 | 0.9419 |
65
- | 0.0428 | 9.8765 | 200 | 0.1533 | 0.9388 |
66
 
67
 
68
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/swinv2-small-patch4-window16-256](https://huggingface.co/microsoft/swinv2-small-patch4-window16-256) on the imagefolder dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.1252
22
+ - Roc Auc: 0.9535
23
 
24
  ## Model description
25
 
 
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
50
+ - num_epochs: 8
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Roc Auc |
55
  |:-------------:|:------:|:----:|:---------------:|:-------:|
56
+ | 0.4357 | 0.9877 | 20 | 0.2544 | 0.7784 |
57
+ | 0.2027 | 1.9753 | 40 | 0.2016 | 0.8431 |
58
+ | 0.1743 | 2.9630 | 60 | 0.1701 | 0.8912 |
59
+ | 0.1625 | 4.0 | 81 | 0.1677 | 0.9083 |
60
+ | 0.1321 | 4.9877 | 101 | 0.1447 | 0.9246 |
61
+ | 0.1155 | 5.9753 | 121 | 0.1418 | 0.9311 |
62
+ | 0.0959 | 6.9630 | 141 | 0.1381 | 0.9460 |
63
+ | 0.0788 | 7.9012 | 160 | 0.1252 | 0.9535 |
 
 
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ef7e3400d5b8464dd8ae04d63a9b53e715257ab21a628d063201e79a75dd0b9
3
  size 195939300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c83df852fc34e53825c72d3da95f260345158cc64404d7c146975d945a6efb25
3
  size 195939300