Hugging Face's logo

DiTo97
/
swinv2-base-panorama-IQA

Image Classification
TensorBoard
Safetensors
swinv2
vision
Generated from Trainer
Model card Files Metrics Community
DiTo97 commited on
Commit
de4eb28
•
1 Parent(s): 37e507d

Model save

Browse files
Files changed (2) hide show
  1. README.md +30 -39
  2. model.safetensors +1 -1
README.md CHANGED
@@ -2,8 +2,6 @@
2
  license: apache-2.0
3
  base_model: microsoft/swinv2-base-patch4-window8-256
4
  tags:
5
- - image-classification
6
- - vision
7
  - generated_from_trainer
8
  datasets:
9
  - generator
@@ -17,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # swinv2-base-panorama-IQA
19
 
20
- This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on the isiqa-2019-hf dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.0254
23
- - Srocc: 0.1552
24
- - Lcc: 0.2308
25
 
26
  ## Model description
27
 
@@ -55,39 +53,32 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Srocc | Lcc |
57
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
58
- | No log | 0.8571 | 3 | 0.2656 | -0.1585 | -0.1388 |
59
- | No log | 2.0 | 7 | 0.0658 | -0.1810 | -0.1277 |
60
- | 0.2144 | 2.8571 | 10 | 0.1341 | -0.1684 | -0.1185 |
61
- | 0.2144 | 4.0 | 14 | 0.0562 | -0.2382 | -0.1379 |
62
- | 0.2144 | 4.8571 | 17 | 0.0616 | -0.1657 | -0.1428 |
63
- | 0.0575 | 6.0 | 21 | 0.0594 | -0.1501 | -0.1185 |
64
- | 0.0575 | 6.8571 | 24 | 0.0513 | -0.1204 | -0.1122 |
65
- | 0.0575 | 8.0 | 28 | 0.0417 | -0.0693 | -0.0987 |
66
- | 0.0201 | 8.8571 | 31 | 0.0406 | -0.0714 | -0.0813 |
67
- | 0.0201 | 10.0 | 35 | 0.0343 | -0.0236 | -0.0385 |
68
- | 0.0201 | 10.8571 | 38 | 0.0315 | 0.0074 | 0.0011 |
69
- | 0.0142 | 12.0 | 42 | 0.0309 | 0.0218 | 0.0326 |
70
- | 0.0142 | 12.8571 | 45 | 0.0310 | 0.0381 | 0.0466 |
71
- | 0.0142 | 14.0 | 49 | 0.0299 | 0.0535 | 0.0681 |
72
- | 0.0097 | 14.8571 | 52 | 0.0314 | 0.0604 | 0.0749 |
73
- | 0.0097 | 16.0 | 56 | 0.0288 | 0.0785 | 0.1049 |
74
- | 0.0097 | 16.8571 | 59 | 0.0283 | 0.0944 | 0.1269 |
75
- | 0.0083 | 18.0 | 63 | 0.0298 | 0.1022 | 0.1448 |
76
- | 0.0083 | 18.8571 | 66 | 0.0274 | 0.1118 | 0.1651 |
77
- | 0.0063 | 20.0 | 70 | 0.0286 | 0.1224 | 0.1703 |
78
- | 0.0063 | 20.8571 | 73 | 0.0283 | 0.1371 | 0.1833 |
79
- | 0.0063 | 22.0 | 77 | 0.0282 | 0.1317 | 0.1944 |
80
- | 0.0059 | 22.8571 | 80 | 0.0277 | 0.1382 | 0.2035 |
81
- | 0.0059 | 24.0 | 84 | 0.0270 | 0.1479 | 0.2146 |
82
- | 0.0059 | 24.8571 | 87 | 0.0263 | 0.1500 | 0.2197 |
83
- | 0.0046 | 26.0 | 91 | 0.0269 | 0.1364 | 0.2199 |
84
- | 0.0046 | 26.8571 | 94 | 0.0259 | 0.1406 | 0.2251 |
85
- | 0.0046 | 28.0 | 98 | 0.0254 | 0.1552 | 0.2308 |
86
- | 0.0039 | 28.8571 | 101 | 0.0267 | 0.1480 | 0.2261 |
87
- | 0.0039 | 30.0 | 105 | 0.0270 | 0.1489 | 0.2247 |
88
- | 0.0039 | 30.8571 | 108 | 0.0261 | 0.1576 | 0.2319 |
89
- | 0.0041 | 32.0 | 112 | 0.0268 | 0.1630 | 0.2311 |
90
- | 0.0041 | 32.8571 | 115 | 0.0282 | 0.1570 | 0.2257 |
91
 
92
 
93
  ### Framework versions
 
2
  license: apache-2.0
3
  base_model: microsoft/swinv2-base-patch4-window8-256
4
  tags:
 
 
5
  - generated_from_trainer
6
  datasets:
7
  - generator
 
15
 
16
  # swinv2-base-panorama-IQA
17
 
18
+ This model is a fine-tuned version of [microsoft/swinv2-base-patch4-window8-256](https://huggingface.co/microsoft/swinv2-base-patch4-window8-256) on the generator dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.0262
21
+ - Srocc: 0.1319
22
+ - Lcc: 0.2258
23
 
24
  ## Model description
25
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Srocc | Lcc |
55
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
56
+ | No log | 0.8571 | 3 | 0.2685 | -0.1661 | -0.1400 |
57
+ | No log | 2.0 | 7 | 0.0675 | -0.2071 | -0.1319 |
58
+ | 0.223 | 2.8571 | 10 | 0.1380 | -0.1972 | -0.1144 |
59
+ | 0.223 | 4.0 | 14 | 0.0639 | -0.2362 | -0.1162 |
60
+ | 0.223 | 4.8571 | 17 | 0.0601 | -0.1760 | -0.1097 |
61
+ | 0.0607 | 6.0 | 21 | 0.0627 | -0.1290 | -0.0852 |
62
+ | 0.0607 | 6.8571 | 24 | 0.0543 | -0.1050 | -0.0791 |
63
+ | 0.0607 | 8.0 | 28 | 0.0408 | -0.0683 | -0.0702 |
64
+ | 0.0212 | 8.8571 | 31 | 0.0419 | -0.0692 | -0.0567 |
65
+ | 0.0212 | 10.0 | 35 | 0.0343 | -0.0370 | -0.0274 |
66
+ | 0.0212 | 10.8571 | 38 | 0.0307 | -0.0339 | -0.0013 |
67
+ | 0.0168 | 12.0 | 42 | 0.0299 | -0.0281 | 0.0233 |
68
+ | 0.0168 | 12.8571 | 45 | 0.0300 | -0.0428 | 0.0326 |
69
+ | 0.0168 | 14.0 | 49 | 0.0286 | -0.0238 | 0.0517 |
70
+ | 0.0143 | 14.8571 | 52 | 0.0283 | -0.0186 | 0.0601 |
71
+ | 0.0143 | 16.0 | 56 | 0.0273 | -0.0024 | 0.0868 |
72
+ | 0.0143 | 16.8571 | 59 | 0.0257 | 0.0283 | 0.1119 |
73
+ | 0.013 | 18.0 | 63 | 0.0247 | 0.0542 | 0.1404 |
74
+ | 0.013 | 18.8571 | 66 | 0.0247 | 0.0703 | 0.1533 |
75
+ | 0.0111 | 20.0 | 70 | 0.0246 | 0.0800 | 0.1670 |
76
+ | 0.0111 | 20.8571 | 73 | 0.0246 | 0.0896 | 0.1773 |
77
+ | 0.0111 | 22.0 | 77 | 0.0257 | 0.0998 | 0.1835 |
78
+ | 0.0104 | 22.8571 | 80 | 0.0255 | 0.1017 | 0.1943 |
79
+ | 0.0104 | 24.0 | 84 | 0.0255 | 0.1149 | 0.2085 |
80
+ | 0.0104 | 24.8571 | 87 | 0.0255 | 0.1245 | 0.2155 |
81
+ | 0.0088 | 26.0 | 91 | 0.0262 | 0.1319 | 0.2258 |
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:902dad98d4d35b9918c28d446708f4a52eed52b4b5961ee825c4d6366091873e
3
  size 347641380
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81fc42b7d8cc2bfce8252e98118b50c6f56dcacb91e71081c8d7e8808e2eb8d4
3
  size 347641380