Downloads · 30 days
7
1% of all-time downloads
segformer-class-custom-train
usamaaleem99tech/segformer-class-custom-train
segformer-class-custom-train is a image classification model from usamaaleem99tech. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
543
Public
Repo size
1.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin110 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- swin
- Access
- Public
- Created
- Jun 30, 2023
- Updated
- Jun 30, 2023
- SHA
- 3d847962
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. -->
segformer-class-custom-train
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0588
- Accuracy: 0.9773
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: 5e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 40
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.96 | 6 | 0.9547 | 0.6364 |
| 1.0647 | 1.92 | 12 | 0.5731 | 0.8636 |
| 1.0647 | 2.88 | 18 | 0.3149 | 0.9091 |
| 0.5705 | 4.0 | 25 | 0.0585 | 0.9773 |
| 0.2274 | 4.96 | 31 | 0.0815 | 0.9773 |
| 0.2274 | 5.92 | 37 | 0.0824 | 0.9773 |
| 0.1822 | 6.88 | 43 | 0.1408 | 0.9773 |
| 0.1784 | 8.0 | 50 | 0.0778 | 0.9773 |
| 0.1784 | 8.96 | 56 | 0.0613 | 0.9773 |
| 0.117 | 9.6 | 60 | 0.0588 | 0.9773 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
- Task
- Image Classification
- Library
- transformers
- Type
- swin
- License
- apache-2.0
- Created
- Jun 30, 2023
- Updated
- Jun 30, 2023