Hugging Face's logo

Augusto777
/
swin-tiny-patch4-window7-224-ve-U11-b-60

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
db7708b
·
verified ·
1 Parent(s): a1babf8

Model save

Browse files
Files changed (3) hide show
  1. README.md +133 -0
  2. model.safetensors +1 -1
  3. runs/Jun11_21-49-36_DESKTOP-SKBE9FB/events.out.tfevents.1718164177.DESKTOP-SKBE9FB.4240.0 +2 -2
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swin-tiny-patch4-window7-224
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - imagefolder
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: swin-tiny-patch4-window7-224-ve-U11-b-60
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: 0.7391304347826086
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
+ # swin-tiny-patch4-window7-224-ve-U11-b-60
32
+
33
+ This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 0.8884
36
+ - Accuracy: 0.7391
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: 5e-05
56
+ - train_batch_size: 32
57
+ - eval_batch_size: 32
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 128
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: 60
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.92 | 6 | 1.3859 | 0.1304 |
71
+ | 1.3858 | 2.0 | 13 | 1.3818 | 0.2609 |
72
+ | 1.3858 | 2.92 | 19 | 1.3723 | 0.2609 |
73
+ | 1.3747 | 4.0 | 26 | 1.3355 | 0.2174 |
74
+ | 1.3001 | 4.92 | 32 | 1.2625 | 0.3696 |
75
+ | 1.3001 | 6.0 | 39 | 1.1306 | 0.4565 |
76
+ | 1.141 | 6.92 | 45 | 1.0510 | 0.4783 |
77
+ | 0.9784 | 8.0 | 52 | 0.9585 | 0.5435 |
78
+ | 0.9784 | 8.92 | 58 | 0.9895 | 0.4783 |
79
+ | 0.8533 | 10.0 | 65 | 0.9512 | 0.5 |
80
+ | 0.7564 | 10.92 | 71 | 0.9522 | 0.5217 |
81
+ | 0.7564 | 12.0 | 78 | 0.9144 | 0.5 |
82
+ | 0.6735 | 12.92 | 84 | 0.9070 | 0.6087 |
83
+ | 0.5919 | 14.0 | 91 | 0.7915 | 0.6522 |
84
+ | 0.5919 | 14.92 | 97 | 0.7989 | 0.6522 |
85
+ | 0.504 | 16.0 | 104 | 0.9510 | 0.6522 |
86
+ | 0.4422 | 16.92 | 110 | 0.8196 | 0.6739 |
87
+ | 0.4422 | 18.0 | 117 | 0.6629 | 0.7609 |
88
+ | 0.4031 | 18.92 | 123 | 0.8767 | 0.6522 |
89
+ | 0.3752 | 20.0 | 130 | 0.8253 | 0.6739 |
90
+ | 0.3752 | 20.92 | 136 | 0.7183 | 0.7391 |
91
+ | 0.3424 | 22.0 | 143 | 0.8852 | 0.6739 |
92
+ | 0.3424 | 22.92 | 149 | 0.7360 | 0.7391 |
93
+ | 0.3293 | 24.0 | 156 | 0.7230 | 0.8043 |
94
+ | 0.2822 | 24.92 | 162 | 0.8271 | 0.6957 |
95
+ | 0.2822 | 26.0 | 169 | 0.7443 | 0.8043 |
96
+ | 0.2623 | 26.92 | 175 | 0.9371 | 0.6739 |
97
+ | 0.2807 | 28.0 | 182 | 0.7392 | 0.7391 |
98
+ | 0.2807 | 28.92 | 188 | 0.8754 | 0.6739 |
99
+ | 0.223 | 30.0 | 195 | 0.7146 | 0.7826 |
100
+ | 0.2185 | 30.92 | 201 | 0.7702 | 0.7391 |
101
+ | 0.2185 | 32.0 | 208 | 0.7330 | 0.7174 |
102
+ | 0.2157 | 32.92 | 214 | 0.8817 | 0.6957 |
103
+ | 0.2011 | 34.0 | 221 | 0.7460 | 0.7174 |
104
+ | 0.2011 | 34.92 | 227 | 0.9663 | 0.6739 |
105
+ | 0.2204 | 36.0 | 234 | 0.8056 | 0.7174 |
106
+ | 0.1856 | 36.92 | 240 | 0.7799 | 0.7174 |
107
+ | 0.1856 | 38.0 | 247 | 0.8410 | 0.6957 |
108
+ | 0.1678 | 38.92 | 253 | 0.7334 | 0.7391 |
109
+ | 0.1682 | 40.0 | 260 | 0.8508 | 0.6957 |
110
+ | 0.1682 | 40.92 | 266 | 0.8106 | 0.6957 |
111
+ | 0.1638 | 42.0 | 273 | 0.8403 | 0.7174 |
112
+ | 0.1638 | 42.92 | 279 | 0.9157 | 0.6957 |
113
+ | 0.1573 | 44.0 | 286 | 0.9271 | 0.7391 |
114
+ | 0.1476 | 44.92 | 292 | 0.9167 | 0.7174 |
115
+ | 0.1476 | 46.0 | 299 | 0.9309 | 0.7174 |
116
+ | 0.1466 | 46.92 | 305 | 0.8236 | 0.7826 |
117
+ | 0.1457 | 48.0 | 312 | 0.8835 | 0.7826 |
118
+ | 0.1457 | 48.92 | 318 | 0.9162 | 0.7391 |
119
+ | 0.1625 | 50.0 | 325 | 0.8969 | 0.7391 |
120
+ | 0.1163 | 50.92 | 331 | 0.9183 | 0.7391 |
121
+ | 0.1163 | 52.0 | 338 | 0.9173 | 0.7391 |
122
+ | 0.1375 | 52.92 | 344 | 0.8886 | 0.7609 |
123
+ | 0.1379 | 54.0 | 351 | 0.8771 | 0.7391 |
124
+ | 0.1379 | 54.92 | 357 | 0.8857 | 0.7391 |
125
+ | 0.1321 | 55.38 | 360 | 0.8884 | 0.7391 |
126
+
127
+
128
+ ### Framework versions
129
+
130
+ - Transformers 4.36.2
131
+ - Pytorch 2.1.2+cu118
132
+ - Datasets 2.16.1
133
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15eb173ca876da42ea21e5bdebae61c146707d35213fb5a25972124b8511c752
3
  size 110348984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c92e5c53da5ec858724cf9c84203e198eebf05310cda765af89bad505d25eec
3
  size 110348984
runs/Jun11_21-49-36_DESKTOP-SKBE9FB/events.out.tfevents.1718164177.DESKTOP-SKBE9FB.4240.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bbef6930a30a64330ae840e9649de439d5186c0c597224004833c76e217a8d44
3
- size 27203
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ddefe1d26320b4734d060d4f5742c605fcf85628926bc9cd36a31e1eb2e3c8a
3
+ size 28840