Hugging Face's logo

DiTo97
/
swinv2-small-panorama-IQA

Image Classification
TensorBoard
Safetensors
swinv2
vision
Generated from Trainer
Model card Files Metrics Community
DiTo97 commited on
Commit
514770f
•
1 Parent(s): 291da9f

Model save

Browse files
Files changed (1) hide show
  1. README.md +106 -0
README.md ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-small-patch4-window16-256
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - generator
8
+ model-index:
9
+ - name: swinv2-small-panorama-IQA
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # swinv2-small-panorama-IQA
17
+
18
+ This model is a fine-tuned version of [microsoft/swinv2-small-patch4-window16-256](https://huggingface.co/microsoft/swinv2-small-patch4-window16-256) on the generator dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0223
21
+ - Srocc: 0.1291
22
+ - Lcc: 0.1271
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 1e-05
42
+ - train_batch_size: 16
43
+ - eval_batch_size: 32
44
+ - seed: 10
45
+ - gradient_accumulation_steps: 4
46
+ - total_train_batch_size: 64
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 50.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Srocc | Lcc |
55
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
56
+ | No log | 0.8571 | 3 | 0.2948 | -0.3890 | -0.3824 |
57
+ | No log | 2.0 | 7 | 0.1143 | -0.3665 | -0.3732 |
58
+ | 0.1552 | 2.8571 | 10 | 0.0768 | -0.3477 | -0.3657 |
59
+ | 0.1552 | 4.0 | 14 | 0.0748 | -0.3395 | -0.3504 |
60
+ | 0.1552 | 4.8571 | 17 | 0.0517 | -0.3498 | -0.3322 |
61
+ | 0.0657 | 6.0 | 21 | 0.0553 | -0.3337 | -0.3060 |
62
+ | 0.0657 | 6.8571 | 24 | 0.0434 | -0.2921 | -0.2810 |
63
+ | 0.0657 | 8.0 | 28 | 0.0406 | -0.2481 | -0.2570 |
64
+ | 0.0249 | 8.8571 | 31 | 0.0402 | -0.2346 | -0.2478 |
65
+ | 0.0249 | 10.0 | 35 | 0.0384 | -0.2076 | -0.2182 |
66
+ | 0.0249 | 10.8571 | 38 | 0.0317 | -0.1919 | -0.1923 |
67
+ | 0.0215 | 12.0 | 42 | 0.0310 | -0.1518 | -0.1636 |
68
+ | 0.0215 | 12.8571 | 45 | 0.0317 | -0.1291 | -0.1549 |
69
+ | 0.0215 | 14.0 | 49 | 0.0301 | -0.0975 | -0.1292 |
70
+ | 0.0154 | 14.8571 | 52 | 0.0285 | -0.0804 | -0.1057 |
71
+ | 0.0154 | 16.0 | 56 | 0.0277 | -0.0461 | -0.0762 |
72
+ | 0.0154 | 16.8571 | 59 | 0.0263 | -0.0357 | -0.0485 |
73
+ | 0.0128 | 18.0 | 63 | 0.0263 | -0.0171 | -0.0317 |
74
+ | 0.0128 | 18.8571 | 66 | 0.0265 | -0.0040 | -0.0236 |
75
+ | 0.0113 | 20.0 | 70 | 0.0263 | 0.0227 | -0.0089 |
76
+ | 0.0113 | 20.8571 | 73 | 0.0256 | 0.0254 | 0.0081 |
77
+ | 0.0113 | 22.0 | 77 | 0.0249 | 0.0493 | 0.0233 |
78
+ | 0.0104 | 22.8571 | 80 | 0.0246 | 0.0616 | 0.0330 |
79
+ | 0.0104 | 24.0 | 84 | 0.0242 | 0.0691 | 0.0435 |
80
+ | 0.0104 | 24.8571 | 87 | 0.0240 | 0.0796 | 0.0518 |
81
+ | 0.0095 | 26.0 | 91 | 0.0238 | 0.0830 | 0.0679 |
82
+ | 0.0095 | 26.8571 | 94 | 0.0235 | 0.0929 | 0.0747 |
83
+ | 0.0095 | 28.0 | 98 | 0.0232 | 0.1003 | 0.0862 |
84
+ | 0.009 | 28.8571 | 101 | 0.0229 | 0.1050 | 0.0955 |
85
+ | 0.009 | 30.0 | 105 | 0.0226 | 0.1072 | 0.1052 |
86
+ | 0.009 | 30.8571 | 108 | 0.0226 | 0.1177 | 0.1110 |
87
+ | 0.0084 | 32.0 | 112 | 0.0225 | 0.1286 | 0.1152 |
88
+ | 0.0084 | 32.8571 | 115 | 0.0224 | 0.1296 | 0.1167 |
89
+ | 0.0084 | 34.0 | 119 | 0.0224 | 0.1296 | 0.1185 |
90
+ | 0.0085 | 34.8571 | 122 | 0.0224 | 0.1310 | 0.1200 |
91
+ | 0.0085 | 36.0 | 126 | 0.0224 | 0.1263 | 0.1221 |
92
+ | 0.0085 | 36.8571 | 129 | 0.0224 | 0.1249 | 0.1233 |
93
+ | 0.0082 | 38.0 | 133 | 0.0223 | 0.1272 | 0.1247 |
94
+ | 0.0082 | 38.8571 | 136 | 0.0223 | 0.1272 | 0.1255 |
95
+ | 0.008 | 40.0 | 140 | 0.0223 | 0.1291 | 0.1265 |
96
+ | 0.008 | 40.8571 | 143 | 0.0223 | 0.1291 | 0.1269 |
97
+ | 0.008 | 42.0 | 147 | 0.0223 | 0.1291 | 0.1271 |
98
+ | 0.0078 | 42.8571 | 150 | 0.0223 | 0.1291 | 0.1271 |
99
+
100
+
101
+ ### Framework versions
102
+
103
+ - Transformers 4.42.3
104
+ - Pytorch 2.1.2
105
+ - Datasets 2.20.0
106
+ - Tokenizers 0.19.1