Hugging Face's logo

navradio
/
swin-tiny-patch4-window7-224-PE

Image Classification
Transformers
PyTorch
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
navradio commited on
Commit
f1e309b
•
1 Parent(s): 6d459a9

Model save

Browse files
Files changed (2) hide show
  1. README.md +127 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-PE
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: train
21
+ args: default
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.797979797979798
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-PE
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: 0.4489
36
+ - Accuracy: 0.7980
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: 0.0025
56
+ - train_batch_size: 128
57
+ - eval_batch_size: 128
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 512
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: 50
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | 0.6872 | 1.0 | 11 | 0.6535 | 0.6061 |
71
+ | 0.7287 | 2.0 | 22 | 0.6601 | 0.6397 |
72
+ | 0.7212 | 3.0 | 33 | 0.6740 | 0.5657 |
73
+ | 0.6947 | 4.0 | 44 | 0.6531 | 0.6532 |
74
+ | 0.6783 | 5.0 | 55 | 0.6739 | 0.5724 |
75
+ | 0.6816 | 6.0 | 66 | 0.6274 | 0.6599 |
76
+ | 0.6428 | 7.0 | 77 | 0.6671 | 0.6330 |
77
+ | 0.6928 | 8.0 | 88 | 0.6380 | 0.6498 |
78
+ | 0.6767 | 9.0 | 99 | 0.6875 | 0.6061 |
79
+ | 0.6918 | 10.0 | 110 | 0.6859 | 0.5690 |
80
+ | 0.6845 | 11.0 | 121 | 0.6810 | 0.5657 |
81
+ | 0.6826 | 12.0 | 132 | 0.6919 | 0.5185 |
82
+ | 0.6877 | 13.0 | 143 | 0.6693 | 0.6061 |
83
+ | 0.6709 | 14.0 | 154 | 0.6660 | 0.5690 |
84
+ | 0.6707 | 15.0 | 165 | 0.6764 | 0.5690 |
85
+ | 0.6703 | 16.0 | 176 | 0.6467 | 0.6296 |
86
+ | 0.6629 | 17.0 | 187 | 0.6471 | 0.6431 |
87
+ | 0.6557 | 18.0 | 198 | 0.6597 | 0.6229 |
88
+ | 0.659 | 19.0 | 209 | 0.6451 | 0.6027 |
89
+ | 0.65 | 20.0 | 220 | 0.6638 | 0.6094 |
90
+ | 0.6453 | 21.0 | 231 | 0.6544 | 0.6162 |
91
+ | 0.6426 | 22.0 | 242 | 0.6565 | 0.5825 |
92
+ | 0.6339 | 23.0 | 253 | 0.6743 | 0.6296 |
93
+ | 0.6236 | 24.0 | 264 | 0.6669 | 0.5960 |
94
+ | 0.6427 | 25.0 | 275 | 0.6379 | 0.6532 |
95
+ | 0.6439 | 26.0 | 286 | 0.6361 | 0.6263 |
96
+ | 0.6212 | 27.0 | 297 | 0.6540 | 0.6465 |
97
+ | 0.6186 | 28.0 | 308 | 0.5925 | 0.6700 |
98
+ | 0.6162 | 29.0 | 319 | 0.6224 | 0.6734 |
99
+ | 0.6237 | 30.0 | 330 | 0.6018 | 0.6667 |
100
+ | 0.6061 | 31.0 | 341 | 0.5735 | 0.6801 |
101
+ | 0.6138 | 32.0 | 352 | 0.6425 | 0.6566 |
102
+ | 0.595 | 33.0 | 363 | 0.5827 | 0.6768 |
103
+ | 0.5869 | 34.0 | 374 | 0.5956 | 0.7172 |
104
+ | 0.577 | 35.0 | 385 | 0.5458 | 0.7003 |
105
+ | 0.5766 | 36.0 | 396 | 0.5603 | 0.6869 |
106
+ | 0.5726 | 37.0 | 407 | 0.5339 | 0.7340 |
107
+ | 0.5702 | 38.0 | 418 | 0.5577 | 0.7138 |
108
+ | 0.5762 | 39.0 | 429 | 0.5262 | 0.7374 |
109
+ | 0.5543 | 40.0 | 440 | 0.5091 | 0.7441 |
110
+ | 0.5339 | 41.0 | 451 | 0.5185 | 0.7542 |
111
+ | 0.5428 | 42.0 | 462 | 0.5023 | 0.7542 |
112
+ | 0.5349 | 43.0 | 473 | 0.5439 | 0.7306 |
113
+ | 0.5319 | 44.0 | 484 | 0.4745 | 0.7811 |
114
+ | 0.5294 | 45.0 | 495 | 0.5432 | 0.7172 |
115
+ | 0.5314 | 46.0 | 506 | 0.4511 | 0.7912 |
116
+ | 0.5073 | 47.0 | 517 | 0.4379 | 0.8047 |
117
+ | 0.5028 | 48.0 | 528 | 0.4487 | 0.7980 |
118
+ | 0.4985 | 49.0 | 539 | 0.4550 | 0.7946 |
119
+ | 0.4826 | 50.0 | 550 | 0.4489 | 0.7980 |
120
+
121
+
122
+ ### Framework versions
123
+
124
+ - Transformers 4.33.3
125
+ - Pytorch 2.0.1+cu117
126
+ - Datasets 2.14.5
127
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3481e7d6999f9c63c17eadf347773ee12bec3805ae50af4c0adfe272182a57fb
3
  size 110394865
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b45e3655d5628072cdd1599947f5c90041a705f3cf0b9846349a457b8996171d
3
  size 110394865