Downloads · 30 days
4
8% of all-time downloads
segformer-b2-finetuned-segments-SixrayGun8-15-2024
saad7489/segformer-b2-finetuned-segments-SixrayGun8-15-2024
segformer-b2-finetuned-segments-SixrayGun8-15-2024 is a image segmentation model from saad7489. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. The card lists the license as other.
should probably proofread and complete it, then remove this comment. --
All-time downloads
51
Public
Parameters
27.4M
110 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors109 MB · 100%
At a glance
- Task
- Image Segmentation
- License
- other
- Model type
- segformer
- Access
- Public
- Created
- Aug 19, 2024
- Updated
- Aug 19, 2024
- SHA
- 2c4c0853
Base models
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. -->
segformer-b2-finetuned-segments-SixrayGun8-15-2024
This model is a fine-tuned version of nvidia/mit-b2 on the saad7489/SIXray_Gun dataset. It achieves the following results on the evaluation set:
- Loss: 0.0404
- Mean Iou: 0.5806
- Mean Accuracy: 0.8934
- Overall Accuracy: 0.8890
- Accuracy No-label: nan
- Accuracy Object1: 0.8756
- Accuracy Object2: 0.9112
- Accuracy Object3: nan
- Accuracy Object4: nan
- Accuracy Object5: nan
- Accuracy Object6: nan
- Iou No-label: 0.0
- Iou Object1: 0.8624
- Iou Object2: 0.8795
- Iou Object3: nan
- Iou Object4: nan
- Iou Object5: nan
- Iou Object6: nan
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: 6e-05
- train_batch_size: 20
- eval_batch_size: 20
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60
Training results
| Training Loss | Epoch | Step | Validation Loss | Mean Iou | Mean Accuracy | Overall Accuracy | Accuracy No-label | Accuracy Object1 | Accuracy Object2 | Accuracy Object3 | Accuracy Object4 | Accuracy Object5 | Accuracy Object6 | Iou No-label | Iou Object1 | Iou Object2 | Iou Object3 | Iou Object4 | Iou Object5 | Iou Object6 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.9839 | 3.3333 | 20 | 1.1748 | 0.2064 | 0.6978 | 0.6660 | nan | 0.5695 | 0.8261 | nan | nan | nan | nan | 0.0 | 0.5204 | 0.5115 | 0.0 | nan | nan | 0.0 |
| 0.3693 | 6.6667 | 40 | 0.2452 | 0.4796 | 0.7757 | 0.7861 | nan | 0.8178 | 0.7336 | nan | nan | nan | nan | 0.0 | 0.7380 | 0.7007 | nan | nan | nan | nan |
| 0.1373 | 10.0 | 60 | 0.1276 | 0.5223 | 0.8244 | 0.8300 | nan | 0.8471 | 0.8017 | nan | nan | nan | nan | 0.0 | 0.7908 | 0.7761 | nan | nan | nan | nan |
| 0.072 | 13.3333 | 80 | 0.0732 | 0.5281 | 0.8149 | 0.8097 | nan | 0.7937 | 0.8360 | nan | nan | nan | nan | 0.0 | 0.7729 | 0.8113 | nan | nan | nan | nan |
| 0.0488 | 16.6667 | 100 | 0.0609 | 0.4191 | 0.8643 | 0.8619 | nan | 0.8546 | 0.8739 | nan | nan | nan | nan | 0.0 | 0.8313 | 0.8450 | 0.0 | nan | nan | nan |
| 0.0408 | 20.0 | 120 | 0.0539 | 0.5675 | 0.8731 | 0.8666 | nan | 0.8468 | 0.8993 | nan | nan | nan | nan | 0.0 | 0.8358 | 0.8668 | nan | nan | nan | nan |
| 0.039 | 23.3333 | 140 | 0.0491 | 0.5618 | 0.8647 | 0.8590 | nan | 0.8414 | 0.8881 | nan | nan | nan | nan | 0.0 | 0.8264 | 0.8590 | nan | nan | nan | nan |
| 0.0365 | 26.6667 | 160 | 0.0484 | 0.4312 | 0.8834 | 0.8773 | nan | 0.8588 | 0.9081 | nan | nan | nan | nan | 0.0 | 0.8494 | 0.8753 | 0.0 | nan | nan | nan |
| 0.0721 | 30.0 | 180 | 0.0486 | 0.4383 | 0.9014 | 0.8957 | nan | 0.8783 | 0.9245 | nan | nan | nan | nan | 0.0 | 0.8673 | 0.8861 | 0.0 | nan | nan | nan |
| 0.0311 | 33.3333 | 200 | 0.0446 | 0.5701 | 0.8758 | 0.8697 | nan | 0.8509 | 0.9007 | nan | nan | nan | nan | 0.0 | 0.8400 | 0.8704 | nan | nan | nan | nan |
| 0.0404 | 36.6667 | 220 | 0.0431 | 0.5719 | 0.8794 | 0.8748 | nan | 0.8609 | 0.8978 | nan | nan | nan | nan | 0.0 | 0.8472 | 0.8686 | nan | nan | nan | nan |
| 0.0284 | 40.0 | 240 | 0.0441 | 0.5852 | 0.9034 | 0.8989 | nan | 0.8852 | 0.9216 | nan | nan | nan | nan | 0.0 | 0.8701 | 0.8855 | nan | nan | nan | nan |
| 0.0302 | 43.3333 | 260 | 0.0424 | 0.4372 | 0.8979 | 0.8935 | nan | 0.8799 | 0.9159 | nan | nan | nan | nan | 0.0 | 0.8668 | 0.8819 | 0.0 | nan | nan | nan |
| 0.0283 | 46.6667 | 280 | 0.0429 | 0.5891 | 0.9094 | 0.9046 | nan | 0.8899 | 0.9290 | nan | nan | nan | nan | 0.0 | 0.8762 | 0.8910 | nan | nan | nan | nan |
| 0.0261 | 50.0 | 300 | 0.0413 | 0.5813 | 0.8950 | 0.8904 | nan | 0.8765 | 0.9135 | nan | nan | nan | nan | 0.0 | 0.8632 | 0.8808 | nan | nan | nan | nan |
| 0.023 | 53.3333 | 320 | 0.0404 | 0.5822 | 0.8966 | 0.8910 | nan | 0.8742 | 0.9190 | nan | nan | nan | nan | 0.0 | 0.8620 | 0.8845 | nan | nan | nan | nan |
| 0.0241 | 56.6667 | 340 | 0.0407 | 0.5848 | 0.9011 | 0.8969 | nan | 0.8839 | 0.9184 | nan | nan | nan | nan | 0.0 | 0.8700 | 0.8844 | nan | nan | nan | nan |
| 0.0527 | 60.0 | 360 | 0.0404 | 0.5806 | 0.8934 | 0.8890 | nan | 0.8756 | 0.9112 | nan | nan | nan | nan | 0.0 | 0.8624 | 0.8795 | nan | nan | nan | nan |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Image Segmentation
- Type
- segformer
- License
- other
- Created
- Aug 19, 2024
- Updated
- Aug 19, 2024