|
--- |
|
license: apache-2.0 |
|
base_model: microsoft/swinv2-tiny-patch4-window8-256 |
|
tags: |
|
- image-classification |
|
- vision |
|
- generated_from_trainer |
|
datasets: |
|
- generator |
|
model-index: |
|
- name: swinv2-tiny-panorama-IQA |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# swinv2-tiny-panorama-IQA |
|
|
|
This model is a fine-tuned version of [microsoft/swinv2-tiny-patch4-window8-256](https://huggingface.co./microsoft/swinv2-tiny-patch4-window8-256) on the isiqa-2019-hf dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0175 |
|
- Srocc: 0.2288 |
|
- Lcc: 0.4304 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 10 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 50.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Srocc | Lcc | |
|
|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:| |
|
| No log | 0.8571 | 3 | 0.1484 | 0.1044 | 0.1970 | |
|
| No log | 2.0 | 7 | 0.0292 | 0.1107 | 0.1713 | |
|
| 0.1442 | 2.8571 | 10 | 0.0548 | 0.0279 | 0.1178 | |
|
| 0.1442 | 4.0 | 14 | 0.0310 | -0.0628 | 0.0689 | |
|
| 0.1442 | 4.8571 | 17 | 0.0476 | -0.0618 | 0.0550 | |
|
| 0.0425 | 6.0 | 21 | 0.0297 | -0.0978 | 0.0051 | |
|
| 0.0425 | 6.8571 | 24 | 0.0259 | -0.0906 | -0.0039 | |
|
| 0.0425 | 8.0 | 28 | 0.0294 | -0.0270 | 0.0079 | |
|
| 0.0242 | 8.8571 | 31 | 0.0237 | -0.0146 | 0.0323 | |
|
| 0.0242 | 10.0 | 35 | 0.0226 | 0.0152 | 0.0809 | |
|
| 0.0242 | 10.8571 | 38 | 0.0236 | 0.0339 | 0.1158 | |
|
| 0.0146 | 12.0 | 42 | 0.0213 | 0.0562 | 0.1753 | |
|
| 0.0146 | 12.8571 | 45 | 0.0199 | 0.0678 | 0.2241 | |
|
| 0.0146 | 14.0 | 49 | 0.0205 | 0.0981 | 0.2702 | |
|
| 0.0116 | 14.8571 | 52 | 0.0190 | 0.1245 | 0.3000 | |
|
| 0.0116 | 16.0 | 56 | 0.0195 | 0.1595 | 0.3511 | |
|
| 0.0116 | 16.8571 | 59 | 0.0194 | 0.1829 | 0.3804 | |
|
| 0.0096 | 18.0 | 63 | 0.0183 | 0.2144 | 0.4030 | |
|
| 0.0096 | 18.8571 | 66 | 0.0195 | 0.2120 | 0.4086 | |
|
| 0.0075 | 20.0 | 70 | 0.0188 | 0.2164 | 0.4127 | |
|
| 0.0075 | 20.8571 | 73 | 0.0209 | 0.2222 | 0.4224 | |
|
| 0.0075 | 22.0 | 77 | 0.0175 | 0.2288 | 0.4304 | |
|
| 0.0076 | 22.8571 | 80 | 0.0211 | 0.2432 | 0.4326 | |
|
| 0.0076 | 24.0 | 84 | 0.0189 | 0.2346 | 0.4327 | |
|
| 0.0076 | 24.8571 | 87 | 0.0188 | 0.2294 | 0.4313 | |
|
| 0.006 | 26.0 | 91 | 0.0223 | 0.2390 | 0.4343 | |
|
| 0.006 | 26.8571 | 94 | 0.0202 | 0.2511 | 0.4399 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
