Model save
Browse files- README.md +96 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: microsoft/swinv2-base-patch4-window8-256
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
datasets:
|
| 7 |
+
- generator
|
| 8 |
+
model-index:
|
| 9 |
+
- name: swinv2-base-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-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: 0.0282
|
| 21 |
+
- Srocc: 0.1570
|
| 22 |
+
- Lcc: 0.2257
|
| 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: 2e-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: linear
|
| 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 | 0.2656 | -0.1585 | -0.1388 |
|
| 57 |
+
| No log | 2.0 | 7 | 0.0658 | -0.1810 | -0.1277 |
|
| 58 |
+
| 0.2144 | 2.8571 | 10 | 0.1341 | -0.1684 | -0.1185 |
|
| 59 |
+
| 0.2144 | 4.0 | 14 | 0.0562 | -0.2382 | -0.1379 |
|
| 60 |
+
| 0.2144 | 4.8571 | 17 | 0.0616 | -0.1657 | -0.1428 |
|
| 61 |
+
| 0.0575 | 6.0 | 21 | 0.0594 | -0.1501 | -0.1185 |
|
| 62 |
+
| 0.0575 | 6.8571 | 24 | 0.0513 | -0.1204 | -0.1122 |
|
| 63 |
+
| 0.0575 | 8.0 | 28 | 0.0417 | -0.0693 | -0.0987 |
|
| 64 |
+
| 0.0201 | 8.8571 | 31 | 0.0406 | -0.0714 | -0.0813 |
|
| 65 |
+
| 0.0201 | 10.0 | 35 | 0.0343 | -0.0236 | -0.0385 |
|
| 66 |
+
| 0.0201 | 10.8571 | 38 | 0.0315 | 0.0074 | 0.0011 |
|
| 67 |
+
| 0.0142 | 12.0 | 42 | 0.0309 | 0.0218 | 0.0326 |
|
| 68 |
+
| 0.0142 | 12.8571 | 45 | 0.0310 | 0.0381 | 0.0466 |
|
| 69 |
+
| 0.0142 | 14.0 | 49 | 0.0299 | 0.0535 | 0.0681 |
|
| 70 |
+
| 0.0097 | 14.8571 | 52 | 0.0314 | 0.0604 | 0.0749 |
|
| 71 |
+
| 0.0097 | 16.0 | 56 | 0.0288 | 0.0785 | 0.1049 |
|
| 72 |
+
| 0.0097 | 16.8571 | 59 | 0.0283 | 0.0944 | 0.1269 |
|
| 73 |
+
| 0.0083 | 18.0 | 63 | 0.0298 | 0.1022 | 0.1448 |
|
| 74 |
+
| 0.0083 | 18.8571 | 66 | 0.0274 | 0.1118 | 0.1651 |
|
| 75 |
+
| 0.0063 | 20.0 | 70 | 0.0286 | 0.1224 | 0.1703 |
|
| 76 |
+
| 0.0063 | 20.8571 | 73 | 0.0283 | 0.1371 | 0.1833 |
|
| 77 |
+
| 0.0063 | 22.0 | 77 | 0.0282 | 0.1317 | 0.1944 |
|
| 78 |
+
| 0.0059 | 22.8571 | 80 | 0.0277 | 0.1382 | 0.2035 |
|
| 79 |
+
| 0.0059 | 24.0 | 84 | 0.0270 | 0.1479 | 0.2146 |
|
| 80 |
+
| 0.0059 | 24.8571 | 87 | 0.0263 | 0.1500 | 0.2197 |
|
| 81 |
+
| 0.0046 | 26.0 | 91 | 0.0269 | 0.1364 | 0.2199 |
|
| 82 |
+
| 0.0046 | 26.8571 | 94 | 0.0259 | 0.1406 | 0.2251 |
|
| 83 |
+
| 0.0046 | 28.0 | 98 | 0.0254 | 0.1552 | 0.2308 |
|
| 84 |
+
| 0.0039 | 28.8571 | 101 | 0.0267 | 0.1480 | 0.2261 |
|
| 85 |
+
| 0.0039 | 30.0 | 105 | 0.0270 | 0.1489 | 0.2247 |
|
| 86 |
+
| 0.0039 | 30.8571 | 108 | 0.0261 | 0.1576 | 0.2319 |
|
| 87 |
+
| 0.0041 | 32.0 | 112 | 0.0268 | 0.1630 | 0.2311 |
|
| 88 |
+
| 0.0041 | 32.8571 | 115 | 0.0282 | 0.1570 | 0.2257 |
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
### Framework versions
|
| 92 |
+
|
| 93 |
+
- Transformers 4.42.3
|
| 94 |
+
- Pytorch 2.1.2
|
| 95 |
+
- Datasets 2.20.0
|
| 96 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 347641380
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3096586ef5e0d5500244fc40de8a2d85fdf476086b99a316b5cbcb10048379e
|
| 3 |
size 347641380
|