Hugging Face's logo

DiTo97
/
swinv2-base-panorama-IQA

Image Classification
TensorBoard
Safetensors
swinv2
vision
Generated from Trainer
Model card Files
xet
Metrics Community
DiTo97 commited on
Commit
b6db9d7
·
verified ·
1 Parent(s): e572afc

Model save

Browse files
Files changed (2) hide show
  1. README.md +49 -34
  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: 0.0246
23
- - Srocc: 0.0896
24
- - Lcc: 0.1773
25
 
26
  ## Model description
27
 
@@ -40,14 +38,14 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 2e-05
44
  - train_batch_size: 16
45
  - eval_batch_size: 32
46
  - seed: 10
47
  - gradient_accumulation_steps: 4
48
  - total_train_batch_size: 64
49
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
50
- - lr_scheduler_type: linear
51
  - lr_scheduler_warmup_ratio: 0.1
52
  - num_epochs: 50.0
53
 
@@ -55,32 +53,49 @@ The following hyperparameters were used during training:
55
 
56
  | Training Loss | Epoch | Step | Validation Loss | Srocc | Lcc |
57
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
58
- | No log | 0.8571 | 3 | 0.2685 | -0.1661 | -0.1400 |
59
- | No log | 2.0 | 7 | 0.0675 | -0.2071 | -0.1319 |
60
- | 0.223 | 2.8571 | 10 | 0.1380 | -0.1972 | -0.1144 |
61
- | 0.223 | 4.0 | 14 | 0.0639 | -0.2362 | -0.1162 |
62
- | 0.223 | 4.8571 | 17 | 0.0601 | -0.1760 | -0.1097 |
63
- | 0.0607 | 6.0 | 21 | 0.0627 | -0.1290 | -0.0852 |
64
- | 0.0607 | 6.8571 | 24 | 0.0543 | -0.1050 | -0.0791 |
65
- | 0.0607 | 8.0 | 28 | 0.0408 | -0.0683 | -0.0702 |
66
- | 0.0212 | 8.8571 | 31 | 0.0419 | -0.0692 | -0.0567 |
67
- | 0.0212 | 10.0 | 35 | 0.0343 | -0.0370 | -0.0274 |
68
- | 0.0212 | 10.8571 | 38 | 0.0307 | -0.0339 | -0.0013 |
69
- | 0.0168 | 12.0 | 42 | 0.0299 | -0.0281 | 0.0233 |
70
- | 0.0168 | 12.8571 | 45 | 0.0300 | -0.0428 | 0.0326 |
71
- | 0.0168 | 14.0 | 49 | 0.0286 | -0.0238 | 0.0517 |
72
- | 0.0143 | 14.8571 | 52 | 0.0283 | -0.0186 | 0.0601 |
73
- | 0.0143 | 16.0 | 56 | 0.0273 | -0.0024 | 0.0868 |
74
- | 0.0143 | 16.8571 | 59 | 0.0257 | 0.0283 | 0.1119 |
75
- | 0.013 | 18.0 | 63 | 0.0247 | 0.0542 | 0.1404 |
76
- | 0.013 | 18.8571 | 66 | 0.0247 | 0.0703 | 0.1533 |
77
- | 0.0111 | 20.0 | 70 | 0.0246 | 0.0800 | 0.1670 |
78
- | 0.0111 | 20.8571 | 73 | 0.0246 | 0.0896 | 0.1773 |
79
- | 0.0111 | 22.0 | 77 | 0.0257 | 0.0998 | 0.1835 |
80
- | 0.0104 | 22.8571 | 80 | 0.0255 | 0.1017 | 0.1943 |
81
- | 0.0104 | 24.0 | 84 | 0.0255 | 0.1149 | 0.2085 |
82
- | 0.0104 | 24.8571 | 87 | 0.0255 | 0.1245 | 0.2155 |
83
- | 0.0088 | 26.0 | 91 | 0.0262 | 0.1319 | 0.2258 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
 
85
 
86
  ### 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: 0.0312
21
+ - Srocc: 0.1132
22
+ - Lcc: 0.1584
23
 
24
  ## Model description
25
 
 
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
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Srocc | Lcc |
55
  |:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
56
+ | No log | 0.8571 | 3 | 0.3021 | -0.1668 | -0.1392 |
57
+ | No log | 2.0 | 7 | 0.1286 | -0.1808 | -0.1347 |
58
+ | 0.2494 | 2.8571 | 10 | 0.0678 | -0.1784 | -0.1273 |
59
+ | 0.2494 | 4.0 | 14 | 0.1143 | -0.1625 | -0.1114 |
60
+ | 0.2494 | 4.8571 | 17 | 0.0686 | -0.1939 | -0.1152 |
61
+ | 0.069 | 6.0 | 21 | 0.0572 | -0.2063 | -0.1376 |
62
+ | 0.069 | 6.8571 | 24 | 0.0537 | -0.1965 | -0.1405 |
63
+ | 0.069 | 8.0 | 28 | 0.0671 | -0.1794 | -0.1289 |
64
+ | 0.0276 | 8.8571 | 31 | 0.0551 | -0.1443 | -0.1164 |
65
+ | 0.0276 | 10.0 | 35 | 0.0492 | -0.1110 | -0.0948 |
66
+ | 0.0276 | 10.8571 | 38 | 0.0465 | -0.0945 | -0.0767 |
67
+ | 0.0181 | 12.0 | 42 | 0.0449 | -0.0830 | -0.0464 |
68
+ | 0.0181 | 12.8571 | 45 | 0.0402 | -0.0659 | -0.0280 |
69
+ | 0.0181 | 14.0 | 49 | 0.0389 | -0.0411 | -0.0117 |
70
+ | 0.0128 | 14.8571 | 52 | 0.0380 | -0.0348 | -0.0055 |
71
+ | 0.0128 | 16.0 | 56 | 0.0371 | -0.0232 | 0.0088 |
72
+ | 0.0128 | 16.8571 | 59 | 0.0360 | 0.0048 | 0.0205 |
73
+ | 0.0112 | 18.0 | 63 | 0.0354 | 0.0128 | 0.0385 |
74
+ | 0.0112 | 18.8571 | 66 | 0.0352 | 0.0197 | 0.0509 |
75
+ | 0.0088 | 20.0 | 70 | 0.0346 | 0.0331 | 0.0670 |
76
+ | 0.0088 | 20.8571 | 73 | 0.0337 | 0.0412 | 0.0801 |
77
+ | 0.0088 | 22.0 | 77 | 0.0347 | 0.0396 | 0.0879 |
78
+ | 0.008 | 22.8571 | 80 | 0.0348 | 0.0512 | 0.0954 |
79
+ | 0.008 | 24.0 | 84 | 0.0339 | 0.0643 | 0.1071 |
80
+ | 0.008 | 24.8571 | 87 | 0.0332 | 0.0765 | 0.1143 |
81
+ | 0.0066 | 26.0 | 91 | 0.0334 | 0.0855 | 0.1240 |
82
+ | 0.0066 | 26.8571 | 94 | 0.0330 | 0.0938 | 0.1292 |
83
+ | 0.0066 | 28.0 | 98 | 0.0317 | 0.0997 | 0.1381 |
84
+ | 0.006 | 28.8571 | 101 | 0.0314 | 0.1087 | 0.1432 |
85
+ | 0.006 | 30.0 | 105 | 0.0317 | 0.1053 | 0.1446 |
86
+ | 0.006 | 30.8571 | 108 | 0.0317 | 0.0971 | 0.1465 |
87
+ | 0.0062 | 32.0 | 112 | 0.0315 | 0.1032 | 0.1496 |
88
+ | 0.0062 | 32.8571 | 115 | 0.0315 | 0.1032 | 0.1511 |
89
+ | 0.0062 | 34.0 | 119 | 0.0314 | 0.1032 | 0.1533 |
90
+ | 0.0057 | 34.8571 | 122 | 0.0314 | 0.1094 | 0.1543 |
91
+ | 0.0057 | 36.0 | 126 | 0.0313 | 0.1091 | 0.1558 |
92
+ | 0.0057 | 36.8571 | 129 | 0.0312 | 0.1132 | 0.1570 |
93
+ | 0.006 | 38.0 | 133 | 0.0312 | 0.1132 | 0.1577 |
94
+ | 0.006 | 38.8571 | 136 | 0.0312 | 0.1132 | 0.1581 |
95
+ | 0.0058 | 40.0 | 140 | 0.0312 | 0.1132 | 0.1583 |
96
+ | 0.0058 | 40.8571 | 143 | 0.0312 | 0.1132 | 0.1584 |
97
+ | 0.0058 | 42.0 | 147 | 0.0312 | 0.1132 | 0.1584 |
98
+ | 0.006 | 42.8571 | 150 | 0.0312 | 0.1132 | 0.1584 |
99
 
100
 
101
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f0e9e1d7ed0c89454c1bfc6fa23559380f1927a59f5ae1026b7b4c3e4d59885
3
  size 347641380
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dcf0be0fbf2217722f11a5632ddddaabec86b525beb40c4e32f64f9add75c6e
3
  size 347641380