Hugging Face's logo

Augusto777
/
SW2-TO-DA

TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
Metrics Community
Augusto777 commited on
Commit
79b2276
·
verified ·
1 Parent(s): 03ed429

Model save

Browse files
Files changed (3) hide show
  1. README.md +116 -0
  2. model.safetensors +1 -1
  3. runs/Dec03_18-12-44_DESKTOP-SKBE9FB/events.out.tfevents.1733271166.DESKTOP-SKBE9FB.19208.0 +2 -2
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-tiny-patch4-window8-256
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: SW2-TO-DA
12
+ results:
13
+ - task:
14
+ name: Image Classification
15
+ type: image-classification
16
+ dataset:
17
+ name: imagefolder
18
+ type: imagefolder
19
+ config: default
20
+ split: validation
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.8870967741935484
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # SW2-TO-DA
32
+
33
+ This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co/microsoft/swinv2-tiny-patch4-window8-256) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.4650
36
+ - Accuracy: 0.8871
37
+
38
+ ## Model description
39
+
40
+ More information needed
41
+
42
+ ## Intended uses & limitations
43
+
44
+ More information needed
45
+
46
+ ## Training and evaluation data
47
+
48
+ More information needed
49
+
50
+ ## Training procedure
51
+
52
+ ### Training hyperparameters
53
+
54
+ The following hyperparameters were used during training:
55
+ - learning_rate: 0.00015
56
+ - train_batch_size: 16
57
+ - eval_batch_size: 16
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 64
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: 40
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 1.4955 | 0.97 | 14 | 1.5580 | 0.0806 |
71
+ | 1.3943 | 2.0 | 29 | 1.1316 | 0.6452 |
72
+ | 1.0056 | 2.97 | 43 | 0.6407 | 0.7419 |
73
+ | 0.7744 | 4.0 | 58 | 0.4265 | 0.8710 |
74
+ | 0.6022 | 4.97 | 72 | 0.4361 | 0.8548 |
75
+ | 0.5854 | 6.0 | 87 | 0.5508 | 0.8065 |
76
+ | 0.4581 | 6.97 | 101 | 0.3124 | 0.8548 |
77
+ | 0.386 | 8.0 | 116 | 0.3169 | 0.8548 |
78
+ | 0.347 | 8.97 | 130 | 0.2207 | 0.9194 |
79
+ | 0.3873 | 10.0 | 145 | 0.5969 | 0.8226 |
80
+ | 0.3508 | 10.97 | 159 | 0.3425 | 0.8871 |
81
+ | 0.274 | 12.0 | 174 | 0.3376 | 0.8710 |
82
+ | 0.2615 | 12.97 | 188 | 0.4913 | 0.8710 |
83
+ | 0.3118 | 14.0 | 203 | 0.4034 | 0.8871 |
84
+ | 0.2205 | 14.97 | 217 | 0.3167 | 0.8710 |
85
+ | 0.2325 | 16.0 | 232 | 0.3043 | 0.8871 |
86
+ | 0.1914 | 16.97 | 246 | 0.4256 | 0.8226 |
87
+ | 0.1997 | 18.0 | 261 | 0.3769 | 0.8548 |
88
+ | 0.1752 | 18.97 | 275 | 0.5875 | 0.8548 |
89
+ | 0.1685 | 20.0 | 290 | 0.4104 | 0.8871 |
90
+ | 0.1736 | 20.97 | 304 | 0.5481 | 0.8548 |
91
+ | 0.1901 | 22.0 | 319 | 0.3800 | 0.9032 |
92
+ | 0.1426 | 22.97 | 333 | 0.4425 | 0.8871 |
93
+ | 0.1251 | 24.0 | 348 | 0.3374 | 0.9032 |
94
+ | 0.1326 | 24.97 | 362 | 0.3627 | 0.8871 |
95
+ | 0.1271 | 26.0 | 377 | 0.4768 | 0.8710 |
96
+ | 0.1835 | 26.97 | 391 | 0.5604 | 0.8710 |
97
+ | 0.1378 | 28.0 | 406 | 0.4131 | 0.8871 |
98
+ | 0.1349 | 28.97 | 420 | 0.5103 | 0.8548 |
99
+ | 0.0999 | 30.0 | 435 | 0.3723 | 0.9194 |
100
+ | 0.1198 | 30.97 | 449 | 0.5361 | 0.8710 |
101
+ | 0.1195 | 32.0 | 464 | 0.4194 | 0.8871 |
102
+ | 0.0766 | 32.97 | 478 | 0.4133 | 0.8871 |
103
+ | 0.0862 | 34.0 | 493 | 0.4239 | 0.9032 |
104
+ | 0.1048 | 34.97 | 507 | 0.4120 | 0.9194 |
105
+ | 0.0902 | 36.0 | 522 | 0.4408 | 0.9032 |
106
+ | 0.088 | 36.97 | 536 | 0.4436 | 0.9032 |
107
+ | 0.089 | 38.0 | 551 | 0.4648 | 0.9032 |
108
+ | 0.1089 | 38.62 | 560 | 0.4650 | 0.8871 |
109
+
110
+
111
+ ### Framework versions
112
+
113
+ - Transformers 4.36.2
114
+ - Pytorch 2.1.2+cu118
115
+ - Datasets 2.16.1
116
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:017dcd9f9fef9b92a8d1f80c54ad17b2aaf092921c490f19320308783797dd1c
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dbaedf067ec5a705aa92b18f41f1239bcb67ae64ff3819b476544326ec373fa
3
  size 110356296
runs/Dec03_18-12-44_DESKTOP-SKBE9FB/events.out.tfevents.1733271166.DESKTOP-SKBE9FB.19208.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4908bb50510bcc6f32ccdf781d29df49f7c82281102752d5682ca18913226cec
3
- size 25558
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd164a39adfd561423add3100a0fd731f673374fcde2d4fc44e2b7243752a226
3
+ size 26392