Hugging Face's logo

DiTo97
/
swinv2-large-panorama-IQA

Image Classification
TensorBoard
Safetensors
swinv2
vision
Generated from Trainer
Model card Files Metrics Community
DiTo97 commited on
Commit
9f33ac7
•
1 Parent(s): f856552

Model save

Browse files
Files changed (2) hide show
  1. README.md +93 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - generator
8
+ model-index:
9
+ - name: swinv2-large-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-large-panorama-IQA
17
+
18
+ This model is a fine-tuned version of [microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft](https://huggingface.co/microsoft/swinv2-large-patch4-window12to16-192to256-22kto1k-ft) on the generator dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.0370
21
+ - Srocc: 0.1002
22
+ - Lcc: 0.1984
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: 4
43
+ - eval_batch_size: 32
44
+ - seed: 10
45
+ - gradient_accumulation_steps: 16
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 | 0.8889 | 3 | 0.4401 | -0.1586 | -0.1147 |
57
+ | No log | 1.7778 | 6 | 0.2206 | -0.2675 | -0.1545 |
58
+ | 0.3084 | 2.9630 | 10 | 0.1910 | -0.2754 | -0.1813 |
59
+ | 0.3084 | 3.8519 | 13 | 0.2334 | -0.2170 | -0.1511 |
60
+ | 0.3084 | 4.7407 | 16 | 0.1484 | -0.2 | -0.1310 |
61
+ | 0.0852 | 5.9259 | 20 | 0.1259 | -0.1021 | -0.0852 |
62
+ | 0.0852 | 6.8148 | 23 | 0.1552 | -0.0709 | -0.0595 |
63
+ | 0.0852 | 8.0 | 27 | 0.0942 | -0.0948 | -0.0584 |
64
+ | 0.0406 | 8.8889 | 30 | 0.0841 | -0.0480 | -0.0550 |
65
+ | 0.0406 | 9.7778 | 33 | 0.0886 | -0.0576 | -0.0448 |
66
+ | 0.0406 | 10.9630 | 37 | 0.0721 | -0.0773 | -0.0474 |
67
+ | 0.023 | 11.8519 | 40 | 0.0697 | -0.0446 | -0.0364 |
68
+ | 0.023 | 12.7407 | 43 | 0.0577 | -0.0217 | -0.0091 |
69
+ | 0.023 | 13.9259 | 47 | 0.0666 | -0.0314 | 0.0112 |
70
+ | 0.0136 | 14.8148 | 50 | 0.0525 | -0.0501 | 0.0060 |
71
+ | 0.0136 | 16.0 | 54 | 0.0626 | -0.0178 | 0.0504 |
72
+ | 0.0136 | 16.8889 | 57 | 0.0438 | 0.0159 | 0.0827 |
73
+ | 0.0113 | 17.7778 | 60 | 0.0503 | 0.0741 | 0.1074 |
74
+ | 0.0113 | 18.9630 | 64 | 0.0429 | 0.0818 | 0.1129 |
75
+ | 0.0113 | 19.8519 | 67 | 0.0455 | 0.0874 | 0.1188 |
76
+ | 0.0097 | 20.7407 | 70 | 0.0597 | 0.0926 | 0.1316 |
77
+ | 0.0097 | 21.9259 | 74 | 0.0397 | 0.0614 | 0.1446 |
78
+ | 0.0097 | 22.8148 | 77 | 0.0529 | 0.0778 | 0.1637 |
79
+ | 0.0084 | 24.0 | 81 | 0.0366 | 0.0716 | 0.1761 |
80
+ | 0.0084 | 24.8889 | 84 | 0.0352 | 0.0683 | 0.1820 |
81
+ | 0.0084 | 25.7778 | 87 | 0.0491 | 0.0970 | 0.1848 |
82
+ | 0.0078 | 26.9630 | 91 | 0.0396 | 0.0984 | 0.1831 |
83
+ | 0.0078 | 27.8519 | 94 | 0.0395 | 0.1012 | 0.1856 |
84
+ | 0.0078 | 28.7407 | 97 | 0.0426 | 0.1097 | 0.1956 |
85
+ | 0.0063 | 29.9259 | 101 | 0.0370 | 0.1002 | 0.1984 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.42.3
91
+ - Pytorch 2.1.2
92
+ - Datasets 2.20.0
93
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d633a67e647e2a9f4217d407372d39fc181a762d8e9544a72d3c1faf0178adb8
3
  size 780880124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63d33fba1e6b1d51cf514c9ea477f31f9152c53d72e526e78c689000e76d867d
3
  size 780880124