Hugging Face's logo

djbp
/
swin-base-patch4-window7-224-MM_Classification_base

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
djbp commited on
Commit
967c8b4
•
1 Parent(s): a22bb56

Model save

Browse files
Files changed (3) hide show
  1. README.md +14 -19
  2. model.safetensors +1 -1
  3. runs/Jul29_05-32-15_57c74b225367/events.out.tfevents.1722231150.57c74b225367 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.8681177976952625
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-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 0.3364
36
- - Accuracy: 0.8681
37
 
38
  ## Model description
39
 
@@ -61,27 +61,22 @@ The following hyperparameters were used during training:
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
64
- - num_epochs: 15
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
- | 0.9771 | 1.0 | 19 | 0.5489 | 0.7913 |
71
- | 0.4913 | 2.0 | 38 | 0.3562 | 0.8553 |
72
- | 0.3633 | 3.0 | 57 | 0.3353 | 0.8668 |
73
- | 0.3343 | 4.0 | 76 | 0.3177 | 0.8656 |
74
- | 0.3096 | 5.0 | 95 | 0.3072 | 0.8758 |
75
- | 0.2822 | 6.0 | 114 | 0.3213 | 0.8630 |
76
- | 0.2749 | 7.0 | 133 | 0.3173 | 0.8643 |
77
- | 0.2526 | 8.0 | 152 | 0.3110 | 0.8758 |
78
- | 0.2405 | 9.0 | 171 | 0.3263 | 0.8758 |
79
- | 0.2152 | 10.0 | 190 | 0.3268 | 0.8656 |
80
- | 0.2226 | 11.0 | 209 | 0.3209 | 0.8732 |
81
- | 0.2067 | 12.0 | 228 | 0.3289 | 0.8771 |
82
- | 0.2019 | 13.0 | 247 | 0.3316 | 0.8745 |
83
- | 0.195 | 14.0 | 266 | 0.3398 | 0.8732 |
84
- | 0.1862 | 15.0 | 285 | 0.3364 | 0.8681 |
85
 
86
 
87
  ### Framework versions
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.8758002560819462
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-base-patch4-window7-224](https://huggingface.co/microsoft/swin-base-patch4-window7-224) on the imagefolder dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 0.2978
36
+ - Accuracy: 0.8758
37
 
38
  ## Model description
39
 
 
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
64
+ - num_epochs: 10
65
 
66
  ### Training results
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.887 | 1.0 | 19 | 0.4012 | 0.8566 |
71
+ | 0.4302 | 2.0 | 38 | 0.3361 | 0.8656 |
72
+ | 0.3477 | 3.0 | 57 | 0.3272 | 0.8656 |
73
+ | 0.3281 | 4.0 | 76 | 0.3129 | 0.8694 |
74
+ | 0.308 | 5.0 | 95 | 0.2984 | 0.8732 |
75
+ | 0.2821 | 6.0 | 114 | 0.3010 | 0.8694 |
76
+ | 0.2763 | 7.0 | 133 | 0.2998 | 0.8771 |
77
+ | 0.2607 | 8.0 | 152 | 0.2938 | 0.8720 |
78
+ | 0.2502 | 9.0 | 171 | 0.2990 | 0.8732 |
79
+ | 0.2337 | 10.0 | 190 | 0.2978 | 0.8758 |
 
 
 
 
 
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7395e51425b3caa911fb9839154fc30de2d752efb98fbd94b8ef190f7742498
3
  size 347502916
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d85e674dc68228e67515b026e7c08821158e09b56e66e777fbc5ab0fc69f70f9
3
  size 347502916
runs/Jul29_05-32-15_57c74b225367/events.out.tfevents.1722231150.57c74b225367 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6466651515138ff8f1c42cecf316316eb3eab4c789e133a1b2371a4e2d6bb6c
3
- size 12232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c700580d2a3b19a79aa9c6da5ef369ae75231078d13d8deafad50a3124982d
3
+ size 12909