Hugging Face's logo

Augusto777
/
swinv2-tiny-patch4-window8-256-ve-U13-b-80

Image Classification
Transformers
TensorBoard
Safetensors
swinv2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Augusto777 commited on
Commit
0736fe0
•
1 Parent(s): cec703a

Model save

Browse files
Files changed (3) hide show
  1. README.md +151 -0
  2. model.safetensors +1 -1
  3. runs/Jun12_10-54-32_DESKTOP-SKBE9FB/events.out.tfevents.1718211273.DESKTOP-SKBE9FB.8968.0 +2 -2
README.md ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-ve-U13-b-80
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: 0.6739130434782609
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-ve-U13-b-80
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: 1.3988
36
+ - Accuracy: 0.6739
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: 5.5e-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: 0.05
64
+ - num_epochs: 80
65
+
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
69
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
70
+ | No log | 0.92 | 6 | 1.3858 | 0.1304 |
71
+ | 1.3856 | 2.0 | 13 | 1.3777 | 0.3696 |
72
+ | 1.3856 | 2.92 | 19 | 1.3488 | 0.2391 |
73
+ | 1.361 | 4.0 | 26 | 1.2503 | 0.2826 |
74
+ | 1.2088 | 4.92 | 32 | 1.1317 | 0.4130 |
75
+ | 1.2088 | 6.0 | 39 | 1.0244 | 0.4565 |
76
+ | 1.0729 | 6.92 | 45 | 1.0413 | 0.4565 |
77
+ | 0.9554 | 8.0 | 52 | 0.9286 | 0.5652 |
78
+ | 0.9554 | 8.92 | 58 | 0.9103 | 0.5652 |
79
+ | 0.8221 | 10.0 | 65 | 0.8519 | 0.6522 |
80
+ | 0.732 | 10.92 | 71 | 0.8300 | 0.5870 |
81
+ | 0.732 | 12.0 | 78 | 0.8103 | 0.6304 |
82
+ | 0.6491 | 12.92 | 84 | 0.9533 | 0.5870 |
83
+ | 0.5724 | 14.0 | 91 | 0.7882 | 0.7391 |
84
+ | 0.5724 | 14.92 | 97 | 0.8072 | 0.6957 |
85
+ | 0.5305 | 16.0 | 104 | 0.7651 | 0.7391 |
86
+ | 0.4879 | 16.92 | 110 | 0.7379 | 0.7174 |
87
+ | 0.4879 | 18.0 | 117 | 0.7590 | 0.6739 |
88
+ | 0.4346 | 18.92 | 123 | 0.9283 | 0.6739 |
89
+ | 0.3671 | 20.0 | 130 | 1.0188 | 0.6304 |
90
+ | 0.3671 | 20.92 | 136 | 0.8959 | 0.7391 |
91
+ | 0.3725 | 22.0 | 143 | 0.9502 | 0.6957 |
92
+ | 0.3725 | 22.92 | 149 | 0.9627 | 0.6522 |
93
+ | 0.3321 | 24.0 | 156 | 0.9619 | 0.6957 |
94
+ | 0.3376 | 24.92 | 162 | 1.0459 | 0.6739 |
95
+ | 0.3376 | 26.0 | 169 | 1.0167 | 0.6522 |
96
+ | 0.3699 | 26.92 | 175 | 0.9949 | 0.6304 |
97
+ | 0.3098 | 28.0 | 182 | 0.9944 | 0.6739 |
98
+ | 0.3098 | 28.92 | 188 | 1.0860 | 0.6304 |
99
+ | 0.253 | 30.0 | 195 | 1.1721 | 0.6522 |
100
+ | 0.2615 | 30.92 | 201 | 1.1626 | 0.6739 |
101
+ | 0.2615 | 32.0 | 208 | 1.2464 | 0.6304 |
102
+ | 0.242 | 32.92 | 214 | 1.2179 | 0.6522 |
103
+ | 0.2173 | 34.0 | 221 | 1.2407 | 0.6304 |
104
+ | 0.2173 | 34.92 | 227 | 1.1585 | 0.6739 |
105
+ | 0.2305 | 36.0 | 234 | 1.3048 | 0.6522 |
106
+ | 0.2114 | 36.92 | 240 | 1.1776 | 0.6522 |
107
+ | 0.2114 | 38.0 | 247 | 1.1460 | 0.6522 |
108
+ | 0.2243 | 38.92 | 253 | 1.2424 | 0.6957 |
109
+ | 0.1822 | 40.0 | 260 | 1.2804 | 0.6739 |
110
+ | 0.1822 | 40.92 | 266 | 1.3472 | 0.6739 |
111
+ | 0.2065 | 42.0 | 273 | 1.3632 | 0.6739 |
112
+ | 0.2065 | 42.92 | 279 | 1.2832 | 0.6739 |
113
+ | 0.1942 | 44.0 | 286 | 1.3500 | 0.6739 |
114
+ | 0.1699 | 44.92 | 292 | 1.3242 | 0.6739 |
115
+ | 0.1699 | 46.0 | 299 | 1.3189 | 0.6957 |
116
+ | 0.1764 | 46.92 | 305 | 1.2840 | 0.6739 |
117
+ | 0.1771 | 48.0 | 312 | 1.3069 | 0.6957 |
118
+ | 0.1771 | 48.92 | 318 | 1.1585 | 0.6957 |
119
+ | 0.2095 | 50.0 | 325 | 1.3702 | 0.6957 |
120
+ | 0.1404 | 50.92 | 331 | 1.3539 | 0.6957 |
121
+ | 0.1404 | 52.0 | 338 | 1.3723 | 0.6957 |
122
+ | 0.1449 | 52.92 | 344 | 1.3877 | 0.6957 |
123
+ | 0.1348 | 54.0 | 351 | 1.3381 | 0.6739 |
124
+ | 0.1348 | 54.92 | 357 | 1.3700 | 0.6739 |
125
+ | 0.1683 | 56.0 | 364 | 1.2871 | 0.6957 |
126
+ | 0.1577 | 56.92 | 370 | 1.3214 | 0.6957 |
127
+ | 0.1577 | 58.0 | 377 | 1.3992 | 0.6522 |
128
+ | 0.1474 | 58.92 | 383 | 1.3800 | 0.6522 |
129
+ | 0.1267 | 60.0 | 390 | 1.2535 | 0.6739 |
130
+ | 0.1267 | 60.92 | 396 | 1.3200 | 0.6739 |
131
+ | 0.1171 | 62.0 | 403 | 1.3730 | 0.6739 |
132
+ | 0.1171 | 62.92 | 409 | 1.3678 | 0.6739 |
133
+ | 0.1461 | 64.0 | 416 | 1.3788 | 0.6739 |
134
+ | 0.1124 | 64.92 | 422 | 1.3944 | 0.6739 |
135
+ | 0.1124 | 66.0 | 429 | 1.3724 | 0.6739 |
136
+ | 0.1168 | 66.92 | 435 | 1.3553 | 0.6522 |
137
+ | 0.1243 | 68.0 | 442 | 1.3829 | 0.6739 |
138
+ | 0.1243 | 68.92 | 448 | 1.4040 | 0.6739 |
139
+ | 0.1375 | 70.0 | 455 | 1.4127 | 0.6522 |
140
+ | 0.1017 | 70.92 | 461 | 1.4070 | 0.6522 |
141
+ | 0.1017 | 72.0 | 468 | 1.3989 | 0.6739 |
142
+ | 0.1346 | 72.92 | 474 | 1.3995 | 0.6739 |
143
+ | 0.1382 | 73.85 | 480 | 1.3988 | 0.6739 |
144
+
145
+
146
+ ### Framework versions
147
+
148
+ - Transformers 4.36.2
149
+ - Pytorch 2.1.2+cu118
150
+ - Datasets 2.16.1
151
+ - Tokenizers 0.15.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78f93a33590c05ddfc5511e44db28bc1bc6180767d8a7c3630730bbfab4bb594
3
  size 110356296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339cdc53417437377c931408c38a4c0f170217425c2b514f050d1c75655a15c4
3
  size 110356296
runs/Jun12_10-54-32_DESKTOP-SKBE9FB/events.out.tfevents.1718211273.DESKTOP-SKBE9FB.8968.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1e3dcbd771713bef3ba9169246fa3fa1c1b7ef34d1e8ef55bf36ce496e0fd71
3
- size 35623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70025c67359612af1f3a939f9c2de1bb0876ee4f76d89744640748dc463d7e47
3
+ size 36457