Hugging Face's logo

navradio
/
swinv2-tiny-patch4-window8-256-finetuned-PE

Image Classification
Transformers
PyTorch
swinv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
navradio commited on
Commit
a4fa134
·
1 Parent(s): 6f4da01

Model save

Browse files
Files changed (2) hide show
  1. README.md +124 -0
  2. pytorch_model.bin +1 -1
README.md ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: swinv2-tiny-patch4-window8-256-finetuned-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: 0.8720186154741129
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
+ # swinv2-tiny-patch4-window8-256-finetuned-PE
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: 0.3083
36
+ - Accuracy: 0.8720
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: 0.00025
56
+ - train_batch_size: 256
57
+ - eval_batch_size: 256
58
+ - seed: 42
59
+ - gradient_accumulation_steps: 4
60
+ - total_train_batch_size: 1024
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
+ | No log | 0.92 | 9 | 0.6391 | 0.6690 |
71
+ | 0.6873 | 1.95 | 19 | 0.5293 | 0.7376 |
72
+ | 0.6233 | 2.97 | 29 | 0.6385 | 0.6853 |
73
+ | 0.5976 | 4.0 | 39 | 0.4447 | 0.7970 |
74
+ | 0.5552 | 4.92 | 48 | 0.4029 | 0.8266 |
75
+ | 0.552 | 5.95 | 58 | 0.3675 | 0.8429 |
76
+ | 0.5055 | 6.97 | 68 | 0.3409 | 0.8581 |
77
+ | 0.4816 | 8.0 | 78 | 0.3322 | 0.8615 |
78
+ | 0.455 | 8.92 | 87 | 0.3166 | 0.8639 |
79
+ | 0.4428 | 9.95 | 97 | 0.3100 | 0.8662 |
80
+ | 0.4398 | 10.97 | 107 | 0.3713 | 0.8365 |
81
+ | 0.4318 | 12.0 | 117 | 0.4019 | 0.8284 |
82
+ | 0.4431 | 12.92 | 126 | 0.3074 | 0.8714 |
83
+ | 0.4437 | 13.95 | 136 | 0.3156 | 0.8656 |
84
+ | 0.4482 | 14.97 | 146 | 0.3516 | 0.8476 |
85
+ | 0.4353 | 16.0 | 156 | 0.3162 | 0.8598 |
86
+ | 0.4218 | 16.92 | 165 | 0.3018 | 0.8685 |
87
+ | 0.4111 | 17.95 | 175 | 0.3143 | 0.8650 |
88
+ | 0.4224 | 18.97 | 185 | 0.3146 | 0.8592 |
89
+ | 0.4114 | 20.0 | 195 | 0.3097 | 0.8691 |
90
+ | 0.4103 | 20.92 | 204 | 0.3038 | 0.8703 |
91
+ | 0.3989 | 21.95 | 214 | 0.2893 | 0.8796 |
92
+ | 0.3908 | 22.97 | 224 | 0.2956 | 0.8755 |
93
+ | 0.3923 | 24.0 | 234 | 0.3041 | 0.8685 |
94
+ | 0.3842 | 24.92 | 243 | 0.2876 | 0.8749 |
95
+ | 0.3808 | 25.95 | 253 | 0.2907 | 0.8767 |
96
+ | 0.382 | 26.97 | 263 | 0.3018 | 0.8738 |
97
+ | 0.3816 | 28.0 | 273 | 0.2812 | 0.8825 |
98
+ | 0.379 | 28.92 | 282 | 0.2960 | 0.8633 |
99
+ | 0.3858 | 29.95 | 292 | 0.2960 | 0.8743 |
100
+ | 0.3546 | 30.97 | 302 | 0.2850 | 0.8807 |
101
+ | 0.3656 | 32.0 | 312 | 0.2905 | 0.8784 |
102
+ | 0.3707 | 32.92 | 321 | 0.2926 | 0.8743 |
103
+ | 0.3651 | 33.95 | 331 | 0.2941 | 0.8796 |
104
+ | 0.3584 | 34.97 | 341 | 0.3133 | 0.8615 |
105
+ | 0.36 | 36.0 | 351 | 0.3181 | 0.8679 |
106
+ | 0.3496 | 36.92 | 360 | 0.3036 | 0.8685 |
107
+ | 0.3458 | 37.95 | 370 | 0.2939 | 0.8732 |
108
+ | 0.3431 | 38.97 | 380 | 0.3062 | 0.8703 |
109
+ | 0.3512 | 40.0 | 390 | 0.2914 | 0.8755 |
110
+ | 0.3512 | 40.92 | 399 | 0.3164 | 0.8674 |
111
+ | 0.3403 | 41.95 | 409 | 0.3063 | 0.8679 |
112
+ | 0.3423 | 42.97 | 419 | 0.3018 | 0.8720 |
113
+ | 0.3312 | 44.0 | 429 | 0.3094 | 0.8697 |
114
+ | 0.3365 | 44.92 | 438 | 0.3062 | 0.8755 |
115
+ | 0.3319 | 45.95 | 448 | 0.3081 | 0.8720 |
116
+ | 0.3409 | 46.15 | 450 | 0.3083 | 0.8720 |
117
+
118
+
119
+ ### Framework versions
120
+
121
+ - Transformers 4.33.3
122
+ - Pytorch 2.0.1+cu117
123
+ - Datasets 2.14.5
124
+ - Tokenizers 0.13.3
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f8da354283aeed5bfe55382bf60cc40705af3aee359d67c00ca4dfb5e93646a
3
  size 110405153
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1501418007a7ec0718618759576d9aa0d2d855bc1594b762bfefea7a8f4a8731
3
  size 110405153