Hugging Face's logo

NithaRenjith
/
swin-tiny-patch4-window7-224-finetuned-bootcamp

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
NithaRenjith commited on
Commit
0845996
·
verified ·
1 Parent(s): 65fa44e

Model save

Browse files
Files changed (2) hide show
  1. README.md +166 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,166 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-finetuned-bootcamp
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: 0.7323943661971831
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-finetuned-bootcamp
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: 0.8963
36
+ - Accuracy: 0.7324
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: 100
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
70
+ | No log | 0.8889 | 6 | 4.2849 | 0.0047 |
71
+ | 4.3139 | 1.9259 | 13 | 4.1846 | 0.0329 |
72
+ | 4.1651 | 2.9630 | 20 | 4.0585 | 0.0563 |
73
+ | 4.1651 | 4.0 | 27 | 3.9527 | 0.0610 |
74
+ | 3.9272 | 4.8889 | 33 | 3.8813 | 0.0610 |
75
+ | 3.7461 | 5.9259 | 40 | 3.7536 | 0.0845 |
76
+ | 3.7461 | 6.9630 | 47 | 3.6486 | 0.1080 |
77
+ | 3.5254 | 8.0 | 54 | 3.5603 | 0.1362 |
78
+ | 3.3478 | 8.8889 | 60 | 3.4566 | 0.1362 |
79
+ | 3.3478 | 9.9259 | 67 | 3.2986 | 0.1502 |
80
+ | 3.0423 | 10.9630 | 74 | 3.2166 | 0.1549 |
81
+ | 2.7931 | 12.0 | 81 | 3.0203 | 0.2160 |
82
+ | 2.7931 | 12.8889 | 87 | 2.8991 | 0.2911 |
83
+ | 2.541 | 13.9259 | 94 | 2.7941 | 0.2911 |
84
+ | 2.3487 | 14.9630 | 101 | 2.7337 | 0.2911 |
85
+ | 2.3487 | 16.0 | 108 | 2.5401 | 0.3662 |
86
+ | 2.1043 | 16.8889 | 114 | 2.5088 | 0.3803 |
87
+ | 1.8892 | 17.9259 | 121 | 2.3596 | 0.4131 |
88
+ | 1.8892 | 18.9630 | 128 | 2.3180 | 0.4178 |
89
+ | 1.7167 | 20.0 | 135 | 2.1820 | 0.4272 |
90
+ | 1.5748 | 20.8889 | 141 | 2.0547 | 0.4413 |
91
+ | 1.5748 | 21.9259 | 148 | 1.9472 | 0.4930 |
92
+ | 1.4052 | 22.9630 | 155 | 1.9053 | 0.4883 |
93
+ | 1.2535 | 24.0 | 162 | 1.8179 | 0.5117 |
94
+ | 1.2535 | 24.8889 | 168 | 1.7600 | 0.5305 |
95
+ | 1.1687 | 25.9259 | 175 | 1.6922 | 0.5493 |
96
+ | 1.0719 | 26.9630 | 182 | 1.6076 | 0.5587 |
97
+ | 1.0719 | 28.0 | 189 | 1.5316 | 0.5587 |
98
+ | 1.0577 | 28.8889 | 195 | 1.5365 | 0.5775 |
99
+ | 0.9558 | 29.9259 | 202 | 1.4488 | 0.6291 |
100
+ | 0.9558 | 30.9630 | 209 | 1.4185 | 0.6150 |
101
+ | 0.8771 | 32.0 | 216 | 1.3906 | 0.6056 |
102
+ | 0.8146 | 32.8889 | 222 | 1.3828 | 0.6150 |
103
+ | 0.8146 | 33.9259 | 229 | 1.3927 | 0.5822 |
104
+ | 0.8228 | 34.9630 | 236 | 1.3036 | 0.6385 |
105
+ | 0.6878 | 36.0 | 243 | 1.2240 | 0.6808 |
106
+ | 0.6878 | 36.8889 | 249 | 1.2388 | 0.6714 |
107
+ | 0.6471 | 37.9259 | 256 | 1.1345 | 0.6808 |
108
+ | 0.6102 | 38.9630 | 263 | 1.1815 | 0.6573 |
109
+ | 0.6599 | 40.0 | 270 | 1.1720 | 0.6526 |
110
+ | 0.6599 | 40.8889 | 276 | 1.1336 | 0.6526 |
111
+ | 0.5742 | 41.9259 | 283 | 1.0863 | 0.6714 |
112
+ | 0.5478 | 42.9630 | 290 | 1.0910 | 0.6714 |
113
+ | 0.5478 | 44.0 | 297 | 1.0746 | 0.6620 |
114
+ | 0.557 | 44.8889 | 303 | 1.0724 | 0.6808 |
115
+ | 0.5753 | 45.9259 | 310 | 1.0108 | 0.7136 |
116
+ | 0.5753 | 46.9630 | 317 | 1.1296 | 0.6432 |
117
+ | 0.5325 | 48.0 | 324 | 1.0361 | 0.6901 |
118
+ | 0.4349 | 48.8889 | 330 | 1.0237 | 0.6995 |
119
+ | 0.4349 | 49.9259 | 337 | 0.9790 | 0.7183 |
120
+ | 0.447 | 50.9630 | 344 | 1.0409 | 0.6808 |
121
+ | 0.4502 | 52.0 | 351 | 1.0467 | 0.6714 |
122
+ | 0.4502 | 52.8889 | 357 | 0.9773 | 0.7183 |
123
+ | 0.4345 | 53.9259 | 364 | 0.9931 | 0.6808 |
124
+ | 0.4557 | 54.9630 | 371 | 0.9685 | 0.7136 |
125
+ | 0.4557 | 56.0 | 378 | 0.9547 | 0.7371 |
126
+ | 0.4109 | 56.8889 | 384 | 1.0015 | 0.6948 |
127
+ | 0.4406 | 57.9259 | 391 | 0.9410 | 0.7230 |
128
+ | 0.4406 | 58.9630 | 398 | 0.9765 | 0.6808 |
129
+ | 0.4039 | 60.0 | 405 | 0.9505 | 0.7089 |
130
+ | 0.396 | 60.8889 | 411 | 0.9539 | 0.7183 |
131
+ | 0.396 | 61.9259 | 418 | 1.0391 | 0.6761 |
132
+ | 0.3958 | 62.9630 | 425 | 0.9576 | 0.7136 |
133
+ | 0.3763 | 64.0 | 432 | 0.9380 | 0.7230 |
134
+ | 0.3763 | 64.8889 | 438 | 0.9363 | 0.7277 |
135
+ | 0.3985 | 65.9259 | 445 | 0.9400 | 0.7089 |
136
+ | 0.3701 | 66.9630 | 452 | 0.9769 | 0.7183 |
137
+ | 0.3701 | 68.0 | 459 | 0.9604 | 0.7277 |
138
+ | 0.3729 | 68.8889 | 465 | 0.9883 | 0.7089 |
139
+ | 0.3958 | 69.9259 | 472 | 0.9516 | 0.7277 |
140
+ | 0.3958 | 70.9630 | 479 | 0.9252 | 0.7183 |
141
+ | 0.359 | 72.0 | 486 | 0.9196 | 0.7136 |
142
+ | 0.362 | 72.8889 | 492 | 0.9104 | 0.7230 |
143
+ | 0.362 | 73.9259 | 499 | 0.9255 | 0.7136 |
144
+ | 0.353 | 74.9630 | 506 | 0.9359 | 0.7089 |
145
+ | 0.345 | 76.0 | 513 | 0.9274 | 0.7230 |
146
+ | 0.345 | 76.8889 | 519 | 0.9206 | 0.7371 |
147
+ | 0.3414 | 77.9259 | 526 | 0.9229 | 0.7277 |
148
+ | 0.3298 | 78.9630 | 533 | 0.9102 | 0.7418 |
149
+ | 0.3394 | 80.0 | 540 | 0.8955 | 0.7512 |
150
+ | 0.3394 | 80.8889 | 546 | 0.8956 | 0.7371 |
151
+ | 0.3384 | 81.9259 | 553 | 0.8927 | 0.7277 |
152
+ | 0.3164 | 82.9630 | 560 | 0.8885 | 0.7418 |
153
+ | 0.3164 | 84.0 | 567 | 0.8941 | 0.7371 |
154
+ | 0.3055 | 84.8889 | 573 | 0.8963 | 0.7418 |
155
+ | 0.3355 | 85.9259 | 580 | 0.8992 | 0.7324 |
156
+ | 0.3355 | 86.9630 | 587 | 0.8988 | 0.7324 |
157
+ | 0.3101 | 88.0 | 594 | 0.8969 | 0.7324 |
158
+ | 0.3218 | 88.8889 | 600 | 0.8963 | 0.7324 |
159
+
160
+
161
+ ### Framework versions
162
+
163
+ - Transformers 4.42.3
164
+ - Pytorch 2.3.1
165
+ - Datasets 2.20.0
166
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8231df06a96d2d745dca0ce8e32847de1f765765c9278e5beb01a7878be049e
3
  size 110548940
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50629305aa484e9844bc9c8424f33bd2615d0e16d000bbd68ed3d42acbc57ea3
3
  size 110548940