Downloads · 30 days
7
1% of all-time downloads
detr
jbossenk/detr
detr is a object detection model from jbossenk. Use it when you need objects located in 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
505
Public
Parameters
41.6M
167 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors167 MB · 100%
At a glance
- Task
- Object Detection
- Library
- transformers
- License
- apache-2.0
- Model type
- detr
- Access
- Public
- Created
- Apr 21, 2024
- Updated
- Apr 21, 2024
- SHA
- 260f4765
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. -->
detr
This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9448
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: 64
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.6853 | 0.32 | 50 | 1.8717 |
| 1.6419 | 0.64 | 100 | 1.4752 |
| 1.4029 | 0.96 | 150 | 1.2728 |
| 1.2596 | 1.27 | 200 | 1.1683 |
| 1.1761 | 1.59 | 250 | 1.0847 |
| 1.106 | 1.91 | 300 | 1.0396 |
| 1.0586 | 2.23 | 350 | 0.9886 |
| 1.0258 | 2.55 | 400 | 0.9653 |
| 1.0151 | 2.87 | 450 | 0.9448 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Task
- Object Detection
- Library
- transformers
- Type
- detr
- License
- apache-2.0
- Created
- Apr 21, 2024
- Updated
- Apr 21, 2024