autodistill
Model distiller
Automatically trains models from large foundation models to perform specific tasks with minimal human intervention.
Images to inference with no labeling (use foundation models to train supervised models).
2k stars
21 watching
161 forks
Language: Python
last commit: over 1 year ago
Linked from 1 awesome list
auto-labelingcomputer-visiondeep-learningfoundation-modelsgrounding-dinoimage-annotationimage-classificationinstance-segmentationlabeling-toolmachine-learningmodel-distillationmultimodalobject-detectionpytorchsegment-anythingyolov5yolov8
amrzv/awesome-colab-notebooksRelated projects:
| Repository | Description | Stars |
|---|---|---|
 deepwisdom/autodl | Automated deep learning algorithm that performs feature engineering, model selection, and hyperparameter tuning without human intervention. | 1,140 |
| autodistill/autodistill-grounded-sam | An implementation of GroundedSAM as a Base Model for object detection in images given text captions. | 46 |
 auto1111sdk/auto1111sdk | A Python library for running state-of-the-art diffusion models, supporting text-to-image and image-to-image generation. | 399 |
 gudovskiy/autodo | Develops an automated machine learning framework to improve deep learning model performance on biased and noisy data | 24 |
 abbypa/nnproject_deepmask | A deep learning implementation of an object segmentation algorithm. | 187 |
 zfturbo/zf_unet_224_pretrained_model | A pre-trained convolutional neural network model for image segmentation tasks. | 214 |
 minimaxir/automl-gs | Automates machine learning model creation and optimization for complex datasets | 1,857 |
 elliottd/groundedtranslation | Trains multilingual image description models using neural sequence models and extracts hidden features from trained models. | 46 |
 deepseek-ai/deepseek-vl | A multimodal AI model that enables real-world vision-language understanding applications | 2,145 |
 dome272/wuerstchen | A framework that enables efficient training of text-to-image models by compressing the computationally expensive stage into a latent space | 531 |
 preritj/segmentation | Deep learning models for semantic segmentation of images | 101 |
 autoviml/auto_viml | Automatically builds multiple machine learning models using a single line of code. | 526 |
 zhengpeng7/birefnet | An open-source implementation of an image segmentation model that combines background removal and object detection capabilities. | 1,484 |
 fantasy-studio/paint-by-example | This project enables precise control over image editing by leveraging diffusion models and self-supervised training to disentangle source images from exemplars. | 1,124 |
 lge-arc-advancedai/auptimizer | Automates model building and deployment process by optimizing hyperparameters and compressing models for edge computing. | 200 |