Hugging Face's logo

Alex-VisTas
/
swin-tiny-patch4-window7-224-finetuned-woody_90epochs

Image Classification
Transformers
PyTorch
TensorBoard
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Alex-VisTas commited on
Commit
0d075df
•
1 Parent(s): 34080e6

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +166 -0
README.md ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - imagefolder
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: swin-tiny-patch4-window7-224-finetuned-woody_90epochs
11
+ results:
12
+ - task:
13
+ name: Image Classification
14
+ type: image-classification
15
+ dataset:
16
+ name: imagefolder
17
+ type: imagefolder
18
+ config: default
19
+ split: train
20
+ args: default
21
+ metrics:
22
+ - name: Accuracy
23
+ type: accuracy
24
+ value: 0.8424242424242424
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # swin-tiny-patch4-window7-224-finetuned-woody_90epochs
31
+
32
+ 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.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.4351
35
+ - Accuracy: 0.8424
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 32
56
+ - eval_batch_size: 32
57
+ - seed: 42
58
+ - gradient_accumulation_steps: 4
59
+ - total_train_batch_size: 128
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - lr_scheduler_warmup_ratio: 0.1
63
+ - num_epochs: 90
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.6659 | 1.0 | 58 | 0.6216 | 0.6558 |
70
+ | 0.6181 | 2.0 | 116 | 0.5616 | 0.7115 |
71
+ | 0.5941 | 3.0 | 174 | 0.5464 | 0.7224 |
72
+ | 0.5727 | 4.0 | 232 | 0.5368 | 0.7297 |
73
+ | 0.573 | 5.0 | 290 | 0.4971 | 0.7539 |
74
+ | 0.5724 | 6.0 | 348 | 0.4920 | 0.7467 |
75
+ | 0.5584 | 7.0 | 406 | 0.4949 | 0.7564 |
76
+ | 0.5352 | 8.0 | 464 | 0.5255 | 0.7406 |
77
+ | 0.5857 | 9.0 | 522 | 0.4954 | 0.7515 |
78
+ | 0.5352 | 10.0 | 580 | 0.4888 | 0.7455 |
79
+ | 0.5161 | 11.0 | 638 | 0.5306 | 0.7224 |
80
+ | 0.5457 | 12.0 | 696 | 0.4856 | 0.76 |
81
+ | 0.5309 | 13.0 | 754 | 0.4647 | 0.7612 |
82
+ | 0.5357 | 14.0 | 812 | 0.4688 | 0.7697 |
83
+ | 0.5183 | 15.0 | 870 | 0.4830 | 0.7527 |
84
+ | 0.4837 | 16.0 | 928 | 0.5238 | 0.7370 |
85
+ | 0.51 | 17.0 | 986 | 0.4658 | 0.7745 |
86
+ | 0.533 | 18.0 | 1044 | 0.4589 | 0.7673 |
87
+ | 0.4808 | 19.0 | 1102 | 0.4375 | 0.7794 |
88
+ | 0.4854 | 20.0 | 1160 | 0.4574 | 0.7745 |
89
+ | 0.4708 | 21.0 | 1218 | 0.4738 | 0.7709 |
90
+ | 0.4801 | 22.0 | 1276 | 0.4688 | 0.76 |
91
+ | 0.4751 | 23.0 | 1334 | 0.4610 | 0.7648 |
92
+ | 0.497 | 24.0 | 1392 | 0.5058 | 0.7624 |
93
+ | 0.4767 | 25.0 | 1450 | 0.4709 | 0.7721 |
94
+ | 0.4805 | 26.0 | 1508 | 0.4447 | 0.7697 |
95
+ | 0.4557 | 27.0 | 1566 | 0.4558 | 0.7721 |
96
+ | 0.4636 | 28.0 | 1624 | 0.4325 | 0.8036 |
97
+ | 0.4285 | 29.0 | 1682 | 0.4526 | 0.7794 |
98
+ | 0.4358 | 30.0 | 1740 | 0.4302 | 0.8048 |
99
+ | 0.4257 | 31.0 | 1798 | 0.4373 | 0.7927 |
100
+ | 0.4137 | 32.0 | 1856 | 0.4458 | 0.7903 |
101
+ | 0.4389 | 33.0 | 1914 | 0.4522 | 0.7988 |
102
+ | 0.4537 | 34.0 | 1972 | 0.4395 | 0.7927 |
103
+ | 0.4249 | 35.0 | 2030 | 0.4348 | 0.8 |
104
+ | 0.4244 | 36.0 | 2088 | 0.4650 | 0.7867 |
105
+ | 0.4256 | 37.0 | 2146 | 0.4402 | 0.8012 |
106
+ | 0.4118 | 38.0 | 2204 | 0.4394 | 0.7867 |
107
+ | 0.4128 | 39.0 | 2262 | 0.4225 | 0.8133 |
108
+ | 0.416 | 40.0 | 2320 | 0.4410 | 0.8073 |
109
+ | 0.4211 | 41.0 | 2378 | 0.4464 | 0.8024 |
110
+ | 0.3838 | 42.0 | 2436 | 0.4440 | 0.7976 |
111
+ | 0.374 | 43.0 | 2494 | 0.4175 | 0.7903 |
112
+ | 0.412 | 44.0 | 2552 | 0.4169 | 0.8109 |
113
+ | 0.3746 | 45.0 | 2610 | 0.4243 | 0.8012 |
114
+ | 0.3719 | 46.0 | 2668 | 0.4132 | 0.8242 |
115
+ | 0.381 | 47.0 | 2726 | 0.4485 | 0.7988 |
116
+ | 0.3708 | 48.0 | 2784 | 0.4200 | 0.8085 |
117
+ | 0.3591 | 49.0 | 2842 | 0.4071 | 0.8279 |
118
+ | 0.3762 | 50.0 | 2900 | 0.4428 | 0.8145 |
119
+ | 0.3426 | 51.0 | 2958 | 0.4058 | 0.8158 |
120
+ | 0.3541 | 52.0 | 3016 | 0.4470 | 0.8182 |
121
+ | 0.3373 | 53.0 | 3074 | 0.4252 | 0.8194 |
122
+ | 0.3303 | 54.0 | 3132 | 0.4040 | 0.8315 |
123
+ | 0.3275 | 55.0 | 3190 | 0.4235 | 0.8291 |
124
+ | 0.3151 | 56.0 | 3248 | 0.3984 | 0.8485 |
125
+ | 0.324 | 57.0 | 3306 | 0.4283 | 0.8291 |
126
+ | 0.3276 | 58.0 | 3364 | 0.4731 | 0.8145 |
127
+ | 0.3208 | 59.0 | 3422 | 0.4360 | 0.8255 |
128
+ | 0.3355 | 60.0 | 3480 | 0.4143 | 0.8230 |
129
+ | 0.3154 | 61.0 | 3538 | 0.4234 | 0.8267 |
130
+ | 0.3451 | 62.0 | 3596 | 0.4059 | 0.8242 |
131
+ | 0.3071 | 63.0 | 3654 | 0.3991 | 0.8267 |
132
+ | 0.3303 | 64.0 | 3712 | 0.4099 | 0.8242 |
133
+ | 0.29 | 65.0 | 3770 | 0.4140 | 0.8327 |
134
+ | 0.2937 | 66.0 | 3828 | 0.4590 | 0.8218 |
135
+ | 0.3322 | 67.0 | 3886 | 0.4111 | 0.8327 |
136
+ | 0.3219 | 68.0 | 3944 | 0.4299 | 0.8327 |
137
+ | 0.2839 | 69.0 | 4002 | 0.4074 | 0.8424 |
138
+ | 0.2903 | 70.0 | 4060 | 0.4366 | 0.8315 |
139
+ | 0.2851 | 71.0 | 4118 | 0.4132 | 0.8473 |
140
+ | 0.3029 | 72.0 | 4176 | 0.4239 | 0.8473 |
141
+ | 0.2693 | 73.0 | 4234 | 0.4194 | 0.8412 |
142
+ | 0.2715 | 74.0 | 4292 | 0.4384 | 0.8412 |
143
+ | 0.2842 | 75.0 | 4350 | 0.4279 | 0.8448 |
144
+ | 0.2733 | 76.0 | 4408 | 0.4174 | 0.84 |
145
+ | 0.2694 | 77.0 | 4466 | 0.3966 | 0.8388 |
146
+ | 0.2527 | 78.0 | 4524 | 0.4194 | 0.8364 |
147
+ | 0.2813 | 79.0 | 4582 | 0.4231 | 0.8436 |
148
+ | 0.2618 | 80.0 | 4640 | 0.4494 | 0.8352 |
149
+ | 0.2639 | 81.0 | 4698 | 0.4152 | 0.8388 |
150
+ | 0.2643 | 82.0 | 4756 | 0.4241 | 0.8448 |
151
+ | 0.276 | 83.0 | 4814 | 0.4518 | 0.8327 |
152
+ | 0.2761 | 84.0 | 4872 | 0.4349 | 0.8412 |
153
+ | 0.2295 | 85.0 | 4930 | 0.4504 | 0.8315 |
154
+ | 0.2723 | 86.0 | 4988 | 0.4385 | 0.8388 |
155
+ | 0.2559 | 87.0 | 5046 | 0.4362 | 0.8473 |
156
+ | 0.2583 | 88.0 | 5104 | 0.4273 | 0.8436 |
157
+ | 0.2523 | 89.0 | 5162 | 0.4292 | 0.8424 |
158
+ | 0.2563 | 90.0 | 5220 | 0.4351 | 0.8424 |
159
+
160
+
161
+ ### Framework versions
162
+
163
+ - Transformers 4.23.1
164
+ - Pytorch 1.12.1+cu113
165
+ - Datasets 2.6.1
166
+ - Tokenizers 0.13.1