# transformers-notebooks
**Repository Path**: mirrors_qubvel/transformers-notebooks
## Basic Information
- **Project Name**: transformers-notebooks
- **Description**: Inference and fine-tuning examples for vision models from 🤗 Transformers
- **Primary Language**: Unknown
- **License**: Apache-2.0
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No
## Statistics
- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-02-16
- **Last Updated**: 2026-03-07
## Categories & Tags
**Categories**: Uncategorized
**Tags**: None
## README
# Example notebooks for vision model of 🤗 Transformers
| Model | Task | Notebooks | Open in Colab |
|------------|--------------------|-----------|---------------|
| RT-DETRv2 | Object Detection | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/RT_DETR_v2_inference.ipynb)
[Fine-tuning](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/RT_DETR_v2_finetune_on_a_custom_dataset.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/RT_DETR_v2_inference.ipynb)
[](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/RT_DETR_v2_finetune_on_a_custom_dataset.ipynb) |
| DAB-DETR | Object Detection | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DAB_DETR_inference.ipynb)
[Fine-tuning](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DAB_DETR_finetune_on_a_custom_dataset.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/DAB_DETR_inference.ipynb)
[](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/DAB_DETR_finetune_on_a_custom_dataset.ipynb) |
| D-Fine | Object Detection | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb)
[Fine-tuning](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb)
[Tracking](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb)
[](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb)
[](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb)|
| DepthPro | Depth Estimation | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DepthPro_inference.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/DepthPro_inference.ipynb) |
| PromptDepth | Depth Estimation | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/PromptDepthAnything_inference.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/PromptDepthAnything_inference.ipynb) |
| DistillAnyDepth | Depth Estimation | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DistillAnyDepth_inference.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/DistillAnyDepth_inference.ipynb) |
| SuperGlue | Keypoint Matching | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/SuperGlue_inference.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/SuperGlue_inference.ipynb) |
| ViTPose | Pose Estimation | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/ViTPose_inference.ipynb)
[Inference (rt-pose)](https://github.com/qubvel/rt-pose/blob/main/notebooks/video_inference.ipynb)
[Optimization](https://github.com/qubvel/rt-pose/blob/main/notebooks/optimizing_pose_estimation_pipeline.ipynb)| [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/ViTPose_inference.ipynb)
[](https://colab.research.google.com/github/qubvel/rt-pose/blob/main/notebooks/video_inference.ipynb)
[](https://colab.research.google.com/github/qubvel/rt-pose/blob/main/notebooks/optimizing_pose_estimation_pipeline.ipynb) |
| SigLIP 2 | Zero-shot image classification | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/SigLIP2_inference.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/SigLIP2_inference.ipynb) |
| MM Grounding DINO | Zero-shot object detection | [Inference](https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/MM_Grounding_DINO_inference.ipynb) | [](https://colab.research.google.com/github/qubvel/transformers-notebooks/blob/main/notebooks/MM_Grounding_DINO_inference.ipynb) |