Downloads · 30 days
15
4% of all-time downloads
swinv2-base-patch4-window8-256
jayanthspratap/swinv2-base-patch4-window8-256
swinv2-base-patch4-window8-256 is a machine learning model from jayanthspratap. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
404
Public
Parameters
86.9M
24.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors348 MB · 100%
At a glance
- License
- apache-2.0
- Model type
- swinv2
- Access
- Public
- Created
- Aug 10, 2024
- Updated
- Aug 16, 2024
- SHA
- 54364ac7
Base models
Datasets
Model card
From the Hugging Face model README
<!-- 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-base-patch4-window8-256
This model is a fine-tuned version of microsoft/swinv2-base-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6211
- Accuracy: 0.7241
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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5428 | 0.9912 | 28 | 0.6211 | 0.7241 |
| 0.6494 | 1.9823 | 56 | 0.6130 | 0.7241 |
| 0.5752 | 2.9735 | 84 | 0.6846 | 0.7241 |
| 0.7165 | 4.0 | 113 | 0.9642 | 0.7241 |
| 0.5699 | 4.9912 | 141 | 0.6072 | 0.7241 |
| 0.5517 | 5.9823 | 169 | 0.6231 | 0.7241 |
| 0.5268 | 6.9735 | 197 | 0.6098 | 0.7241 |
| 0.672 | 8.0 | 226 | 0.5891 | 0.7241 |
| 0.5448 | 8.9912 | 254 | 0.6023 | 0.7241 |
| 0.555 | 9.9823 | 282 | 0.5917 | 0.7241 |
| 0.5818 | 10.9735 | 310 | 0.5940 | 0.7241 |
| 0.6556 | 12.0 | 339 | 0.5966 | 0.7241 |
| 0.716 | 12.9912 | 367 | 0.5904 | 0.7241 |
| 0.6104 | 13.9823 | 395 | 0.5938 | 0.7241 |
| 0.5046 | 14.9735 | 423 | 0.5921 | 0.7241 |
| 0.5871 | 16.0 | 452 | 0.6027 | 0.7241 |
| 0.5222 | 16.9912 | 480 | 0.5921 | 0.7241 |
| 0.5511 | 17.9823 | 508 | 0.5948 | 0.7241 |
| 0.6394 | 18.9735 | 536 | 0.5969 | 0.7241 |
| 0.566 | 20.0 | 565 | 0.6005 | 0.7241 |
| 0.6032 | 20.9912 | 593 | 0.5968 | 0.7241 |
| 0.4824 | 21.9823 | 621 | 0.5934 | 0.7241 |
| 0.4975 | 22.9735 | 649 | 0.5979 | 0.7241 |
| 0.4976 | 24.0 | 678 | 0.6034 | 0.7241 |
| 0.5355 | 24.9912 | 706 | 0.6033 | 0.7241 |
| 0.4323 | 25.9823 | 734 | 0.6015 | 0.7241 |
| 0.5579 | 26.9735 | 762 | 0.6043 | 0.7241 |
| 0.5639 | 28.0 | 791 | 0.6023 | 0.7241 |
| 0.5595 | 28.9912 | 819 | 0.5996 | 0.7241 |
| 0.4372 | 29.7345 | 840 | 0.5995 | 0.7241 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Type
- swinv2
- License
- apache-2.0
- Created
- Aug 10, 2024
- Updated
- Aug 16, 2024