tao-tutorials
Quick start scripts and tutorial notebooks to get started with TAO Toolkit
파일 탐색기
최종 버전 다운로드 (.zip)- blossom-ci.yml
- default.conf
- cleanup-seaweed-storage.sh
- config.env
- docker-compose.yml
- load-docker-images.sh
- nginx.conf
- README.md
- run.sh
- s3-config.json
- save-docker-images.sh
- secrets.json
- quickstart_launcher.sh
- post_train_cosmos3_aoi.md
- post_train_cosmos3_lora.md
- 3d_models.ipynb
- auto_labeling.ipynb
- classification.ipynb
- clip.ipynb
- data_services.ipynb
- foundation_model_finetuning.ipynb
- object_detection.ipynb
- purpose_built_models.ipynb
- segmentation.ipynb
- AppOFCuda
- bpnet_18joints.json
- coco_spec.json
- infer_spec.yaml
- prepare_centerpose_dataset.py
- dataset_split.py
- coco_to_contiguous.py
- coco_to_odvg.py
- download_coco.sh
- label_map.txt
- download_coco.sh
- extract_subset.py
- labelmap.json
- data.json
- data_utils.py
- download_hardhat.sh
- hardhat_detection_coco_dataset_format.ipynb
- kitti_to_coco.py
- download_and_prepare_data.sh
- preprocess_openalpr_benchmark.py
- extract_subset.py
- process_retail_product_checkout_dataset.py
- dataset_split.py
- mvtec_ad_classification_dataset_format.ipynb
- mvtec_ad_mgcn_dataset_format.ipynb
- preprocess_label.py
- calibration_kitti.py
- drop_class.py
- gen_lidar_labels.py
- gen_lidar_points.py
- kitti_split.py
- object3d_kitti.py
- obtain_subset.py
- val.txt
- select_subset_actions.py
- obtain_subset_data.py
- prepare_data.sh
- prepare_data_isbi.py
- auto_labeling.ipynb
- classification.ipynb
- data_generation.ipynb
- data_services.ipynb
- foundational_model_finetuning.ipynb
- object_detection.ipynb
- purpose_built_models.ipynb
- segmentation.ipynb
- finetuning_workflow.png
- sample_image_classification.jpg
- sample_object_detection.jpg
- sample_semantic_segmentation.jpg
- 3d_models.ipynb
- auto_labeling.ipynb
- classification.ipynb
- clip.ipynb
- data_services.ipynb
- foundation_model_finetuning.ipynb
- object_detection.ipynb
- purpose_built_models.ipynb
- segmentation.ipynb
- data_overview.png
- distillation_rtdetr_workflow_diagram.png
- finetuning_workflow_diagram.png
- ssl_mae_workflow_diagram.png
- stylegan_sdg.png
- detection_sample.jpg
- mask_auto_encoder.png
- sample_domain_adaptation.png
- cradio_mg_changenet.ipynb
- dino_automl_local_airgapped.ipynb
- get_bounds.py
- rtdetr_detection_distillation.ipynb
- ssl_mae_pretrain_finetune.ipynb
- vlm.ipynb
- analytics.yaml
- augment.yaml
- autolabel.yaml
- convert.yaml
- validate.yaml
- kitti.ipynb
- autolabel.yaml
- convert.yaml
- download_coco.sh
- segmentation_autolabel.yaml
- sample.jpg
- text2box.ipynb
- __init__.py
- analyze_gaps.py
- config.py
- config_fields.py
- data_mining.py
- history_aware_mining.py
- pairs_io.py
- pyproject.toml
- utils.py
- visualization.py
- sitecustomize.py
- deft_config.yaml
- image_embed_spec.yaml
- mining_spec.yaml
- tao_spec.yaml
- text_embed_spec.yaml
- pas_deft_mining.ipynb
- evaluate_of.yaml
- evaluate_rgb.yaml
- experiment_of_3d_finetune.yaml
- experiment_rgb_3d_finetune.yaml
- export_of.yaml
- export_rgb.yaml
- infer_of.yaml
- infer_rgb.yaml
- train_of_3d_finetune.yaml
- train_rgb_2d_finetune.yaml
- train_rgb_3d_finetune.yaml
- actionrecognitionnet.ipynb
- AppOFCuda
- aws_s3_mounting.ipynb
- export_cats_dogs.yaml
- test_cats_dogs.yaml
- train_cats_dogs.yaml
- classification.ipynb
- spec.yaml
- spec_direct_eval.yaml
- spec_retrain.yaml
- byom_classification.ipynb
- imagenet_classmap.json
- imagenet_valprep.txt
- prepare_imagenet.py
- prepare_voc.py
- spec.yaml
- spec_16bit_imgs.yaml
- spec_retrain.yaml
- spec_retrain_16bit_imgs.yaml
- spec_retrain_qat.yaml
- classification.ipynb
- classification_16bit.ipynb
- prepare_16bit.py
- prepare_voc.py
- experiment_radio-clip.yaml
- experiment_siglip2.yaml
- clip.ipynb
- evaluate.yaml
- export_hf.yaml
- export_onnx.yaml
- inference.yaml
- train.yaml
- train_lora.yaml
- finetuning_cosmos_embed1.ipynb
- classmap.txt
- download_coco.sh
- evaluate.yaml
- export.yaml
- gen_trt_engine.yaml
- infer.yaml
- train.yaml
- deformable_detr.ipynb
- sample.jpg
- requirements-pip.txt
- classmap.txt
- distill.yaml
- download_coco.sh
- evaluate.yaml
- evaluate_distill.yaml
- export.yaml
- export_distill.yaml
- gen_trt_engine.yaml
- infer.yaml
- infer_distill.yaml
- train.yaml
- dino.ipynb
- dino_distillation.ipynb
- sample.jpg
- coco_labels.yaml
- download_coco.sh
- spec_retrain.yaml
- spec_retrain_qat.yaml
- spec_train.yaml
- efficientdet.ipynb
- export_imagenet_clip.yaml
- test_clip_imagenet.yaml
- train_imagenet_clip.yaml
- classification_pyt_fm_ft.ipynb
- __init__.py
- convert.yaml
- download_hardhat.sh
- evaluate.yaml
- export.yaml
- gen_trt_engine.yaml
- infer.yaml
- train.yaml
- finetune_grounding_dino.ipynb
- sample.jpg
- download_coco.sh
- spec.yaml
- mal.ipynb
- download_coco.sh
- labelmap.json
- labelmap_inst.json
- spec.yaml
- spec_inst.yaml
- mask2former.ipynb
- mask2former_inst.ipynb
- convert.yaml
- download_coco.sh
- evaluate.yaml
- export.yaml
- gen_trt_engine.yaml
- infer.yaml
- train.yaml
- mask_grounding_dino.ipynb
- sample.jpg
- evaluate.yaml
- export.yaml
- gen_trt_engine.yaml
- infer.yaml
- train.yaml
- metric_learning_recognition.ipynb
- process_retail_product_checkout_dataset.py
- export_spec.yaml
- inference_spec.yaml
- train_spec.yaml
- nvdinov2_cats.ipynb
- evaluate.yaml
- evaluate_ocdnet_vit.yaml
- export.yaml
- export_ocdnet_vit.yaml
- gen_trt_engine.yaml
- gen_trt_engine_ocdnet_vit.yaml
- inference.yaml
- inference_ocdnet_vit.yaml
- prune.yaml
- prune_ocdnet_vit.yaml
- train.yaml
- train_ocdnet_vit.yaml
- ocdnet.ipynb
- ocdnet_vit.ipynb
- offline_crop.py
- experiment-vit.yaml
- experiment.yaml
- ocrnet-vit.ipynb
- ocrnet.ipynb
- experiment.yaml
- OpticalInspection.ipynb
- drop_class.py
- gen_lidar_labels.py
- gen_lidar_points.py
- kitti_split.py
- pointpillars.yaml
- pointpillars_retrain.yaml
- val.txt
- pointpillars.ipynb
- experiment_kinetics.yaml
- experiment_nvidia.yaml
- poseclassificationnet.ipynb
- experiment_market1501_resnet.yaml
- experiment_market1501_swin.yaml
- reidentificationnet_resnet.ipynb
- reidentificationnet_swin.ipynb
- classmap.txt
- evaluate.yaml
- export.yaml
- gen_trt_engine.yaml
- infer.yaml
- train.yaml
- train_synthetic.yaml
- process_retail_data_labels.py
- retail_object_detection.ipynb
- sample.jpg
- sample2.jpg
- synthetic_object_detection.ipynb
- evaluate.yaml
- export.yaml
- gen_trt_engine.yaml
- infer.yaml
- train.yaml
- train_fan.yaml
- train_resnet.yaml
- process_retail_product_checkout_dataset.py
- retail_object_recognition.ipynb
- export_isbi.yaml
- test_isbi.yaml
- train_isbi.yaml
- AppOFCuda
- prepare_data_isbi.py
- segformer.ipynb
- vis_annotation_isbi.py
- convert.yaml
- experiment.yaml
- .gitattributes
- sparse4d.ipynb
- experiment.yaml
- experiment_classify.yaml
- visual_changenet_classification.ipynb
- visual_changenet_segmentation.ipynb
- visual_changenet_segmentation_MVTec.ipynb
- .DS_Store
- .gitignore
- LICENSE
- README.md
- SECURITY.md
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/NVIDIA-TAO/tao-tutorials
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd tao-tutorials
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. Docker
쉬움 추천사전 준비물
- Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
- Docker Desktop 컨테이너를 빌드하고 실행하려면 필요합니다. 설치 후 실행해서 백그라운드에 켜두세요.
⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.
docker compose -f setup/tao-docker-compose/docker-compose.yml up -d --build
compose 설정 파일에 정의된 서비스들을 대상으로 명령을 실행합니다.
터미널에 docker compose ps 를 입력해 컨테이너들이 Up 상태인지 확인하세요. README에 포트 번호가 적혀있다면 브라우저에서 http://localhost:포트번호 로 접속해보세요.
3. Python
쉬움사전 준비물
⚠️ 이 프로젝트는 규모가 큰 저장소라, 이 방법이 실제 핵심 제품이 아니라 내부 하위 패키지를 가리키는 것일 수 있습니다. README 전체를 함께 확인해보세요.
pip install .
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
jupyter notebook
브라우저에서 노트북(.ipynb) 파일들을 열람하고 실행할 수 있는 Jupyter 화면을 켭니다.
에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.
// repository documentation
Was this content helpful?
(0 ratings)