LayoutGPT
Official repo for NeurIPS 2023 paper "LayoutGPT: Compositional Visual Planning and Generation with Large Language Models"
파일 탐색기
최종 버전 다운로드 (.zip)- 10043.gif
- 13439.gif
- 152170.gif
- 2050.gif
- 28445.gif
- 326.gif
- 863.gif
- 9583.gif
- teaser.jpg
- bedroom_threed_front_splits.csv
- bedroom_threed_front_splits_new.csv
- bedroom_threed_front_splits_regular.csv
- bedrooms_config.yaml
- bedrooms_eval_config.yaml
- black_list.txt
- dining_rooms_config.yaml
- dining_rooms_eval_config.yaml
- diningroom_threed_front_splits.csv
- invalid_threed_front_rooms.txt
- libraries_config.yaml
- libraries_eval_config.yaml
- library_threed_front_splits.csv
- living_rooms_config.yaml
- living_rooms_eval_config.yaml
- livingroom_threed_front_splits.csv
- livingroom_threed_front_splits_new.csv
- livingroom_threed_front_splits_regular.csv
- floor_00001.jpg
- floor_00002.jpg
- floor_00003.jpg
- floor_00004.jpg
- floor_00005.jpg
- floor_00006.jpg
- floor_00007.jpg
- floor_00003.jpg
- floor_plan_texture_images_references
- room_1.gif
- room_2.gif
- room_3.gif
- __init__.py
- base.py
- common.py
- splits_builder.py
- threed_front.py
- threed_front_dataset.py
- threed_front_scene.py
- threed_future_dataset.py
- utils.py
- __init__.py
- mmd.py
- __init__.py
- autoregressive_transformer.py
- base.py
- bbox_output.py
- feature_extractors.py
- frozen_batchnorm.py
- hidden_to_output.py
- __init__.py
- stats_logger.py
- utils.py
- compute_fid_scores.py
- evaluate_kl_divergence_object_category.py
- failure_correction.py
- generate_scenes.py
- object_suggestions.py
- pickle_threed_future_dataset.py
- preprocess_data.py
- render_from_files.py
- render_threedfront_scene.py
- render_with_blender.py
- scene_completion.py
- synthetic_vs_real_classifier.py
- train_network.py
- training_utils.py
- utils.py
- environment.yaml
- LICENSE
- README.md
- setup.py
- bedroom_splits.json
- livingroom_splits.json
- counting.train.json
- counting.val.json
- train.counting.vit-l-14.visual.npz
- spatial.train.json
- spatial.val.json
- train.spatial.vit-l-14.visual.npz
- test.yaml
- val.yaml
- minival.yaml
- val.yaml
- AerialMaritimeDrone_large.yaml
- Aquarium_Aquarium_Combined.v2-raw-1024.coco.yaml
- CottontailRabbits.yaml
- EgoHands_generic.yaml
- NorthAmericaMushrooms_North_American_Mushrooms.v1-416x416.coco.yaml
- Packages_Raw.yaml
- PascalVOC.yaml
- pistols_export.yaml
- pothole.yaml
- Raccoon_Raccoon.v2-raw.coco.yaml
- ShellfishOpenImages_raw.yaml
- thermalDogsAndPeople.yaml
- VehiclesOpenImages_416x416.yaml
- _all.json
- AerialMaritimeDrone_large.yaml
- AerialMaritimeDrone_tiled.yaml
- AmericanSignLanguageLetters_American_Sign_Language_Letters.v1-v1.coco.yaml
- Aquarium_Aquarium_Combined.v2-raw-1024.coco.yaml
- BCCD_BCCD.v3-raw.coco.yaml
- boggleBoards_416x416AutoOrient_export_.yaml
- brackishUnderwater_960x540.yaml
- ChessPieces_Chess_Pieces.v23-raw.coco.yaml
- CottontailRabbits.yaml
- dice_mediumColor_export.yaml
- DroneControl_Drone_Control.v3-raw.coco.yaml
- EgoHands_generic.yaml
- EgoHands_specific.yaml
- HardHatWorkers_raw.yaml
- MaskWearing_raw.yaml
- MountainDewCommercial.yaml
- NorthAmericaMushrooms_North_American_Mushrooms.v1-416x416.coco.yaml
- openPoetryVision_512x512.yaml
- OxfordPets_by-breed.yaml
- OxfordPets_by-species.yaml
- Packages_Raw.yaml
- PascalVOC.yaml
- pistols_export.yaml
- PKLot_640.yaml
- plantdoc_100x100.yaml
- plantdoc_416x416.yaml
- pothole.yaml
- Raccoon_Raccoon.v2-raw.coco.yaml
- selfdrivingCar_fixedLarge_export_.yaml
- ShellfishOpenImages_raw.yaml
- ThermalCheetah.yaml
- thermalDogsAndPeople.yaml
- UnoCards_raw.yaml
- VehiclesOpenImages_416x416.yaml
- websiteScreenshots.yaml
- WildfireSmoke.yaml
- _coco.yaml
- glip_A_Swin_T_O365.yaml
- glip_Swin_L.yaml
- glip_Swin_T_O365.yaml
- glip_Swin_T_O365_GoldG.yaml
- odinw_benchmark35_knowledge_and_gpt3.yaml
- odinw_knowledge.yaml
- odinw_knowledge_with_prompt.yaml
- run_inference_odinw_knowledge_benchmark35.yaml
- __init__.py
- defaults.py
- paths_catalog.py
- nms_cpu.cpp
- ROIAlign_cpu.cpp
- soft_nms.cpp
- vision.h
- deform_conv_cuda.cu
- deform_conv_kernel_cuda.cu
- deform_pool_cuda.cu
- deform_pool_kernel_cuda.cu
- ml_nms.cu
- nms.cu
- ROIAlign_cuda.cu
- ROIPool_cuda.cu
- SigmoidFocalLoss_cuda.cu
- vision.h
- deform_conv.h
- deform_pool.h
- ml_nms.h
- nms.h
- ROIAlign.h
- ROIPool.h
- SigmoidFocalLoss.h
- vision.cpp
- __init__.py
- coco_eval.py
- __init__.py
- flickr_eval.py
- _change_lvis_annotation.py
- lvis.py
- lvis_eval.py
- __init__.py
- od_eval.py
- __init__.py
- vg_eval.py
- __init__.py
- voc_eval.py
- __init__.py
- box_aug.py
- od_eval.py
- __init__.py
- background.py
- box_label_loader.py
- caption.py
- coco.py
- coco_dt.py
- concat_dataset.py
- custom_distributed_sampler.py
- duplicate_dataset.py
- flickr.py
- gqa.py
- imagenet.py
- list_dataset.py
- lvis.py
- mixed.py
- mixup.py
- modulated_coco.py
- object365.py
- od_to_grounding.py
- phrasecut.py
- pseudo_data.py
- refexp.py
- tsv.py
- vg.py
- voc.py
- __init__.py
- distributed.py
- grouped_batch_sampler.py
- iteration_based_batch_sampler.py
- __init__.py
- build.py
- transforms.py
- __init__.py
- build.py
- collate_batch.py
- __init__.py
- alter_trainer.py
- evolution.py
- inference.py
- predictor.py
- predictor_glip.py
- singlepath_trainer.py
- stage_trainer.py
- trainer.py
- __init__.py
- batch_norm.py
- deform_conv.py
- deform_pool.py
- dropblock.py
- dyhead.py
- dyrelu.py
- evonorm.py
- iou_loss.py
- misc.py
- nms.py
- roi_align.py
- roi_pool.py
- se.py
- set_loss.py
- sigmoid_focal_loss.py
- smooth_l1_loss.py
- __init__.py
- bifpn.py
- blocks.py
- efficientdet.py
- efficientnet.py
- fbnet.py
- fpn.py
- mixer.py
- ops.py
- resnet.py
- swint.py
- swint_v2.py
- swint_v2_vl.py
- swint_vl.py
- __init__.py
- generalized_rcnn.py
- generalized_vl_rcnn.py
- __init__.py
- backbone.py
- bert_model.py
- bpe_simple_vocab_16e6.txt.gz
- build.py
- clip_model.py
- hfpt_tokenizer.py
- rnn_model.py
- simple_tokenizer.py
- test_clip_tokenizer.py
- word_utils.py
- __init__.py
- box_head.py
- inference.py
- loss.py
- roi_box_feature_extractors.py
- roi_box_predictors.py
- inference.py
- keypoint_head.py
- loss.py
- roi_keypoint_feature_extractors.py
- roi_keypoint_predictors.py
- __init__.py
- hourglass.py
- inference.py
- loss.py
- mask_head.py
- roi_mask_feature_extractors.py
- roi_mask_predictors.py
- __init__.py
- __init__.py
- anchor_generator.py
- atss.py
- dyhead.py
- fcos.py
- inference.py
- loss.py
- modeling_bert.py
- retina.py
- rpn.py
- transformer.py
- vldyhead.py
- .DS_Store
- __init__.py
- balanced_positive_negative_sampler.py
- box_coder.py
- make_layers.py
- matcher.py
- poolers.py
- registry.py
- utils.py
- __init__.py
- build.py
- lr_scheduler.py
- __init__.py
- bounding_box.py
- boxlist_ops.py
- image_list.py
- keypoint.py
- segmentation_mask.py
- __init__.py
- amp.py
- big_model_loading.py
- c2_model_loading.py
- checkpoint.py
- collect_env.py
- comm.py
- cv2_util.py
- dist.py
- ema.py
- env.py
- flops.py
- fuse_helper.py
- imports.py
- logger.py
- mdetr_dist.py
- metric_logger.py
- miscellaneous.py
- model_serialization.py
- model_zoo.py
- pretrain_model_loading.py
- README.md
- registry.py
- shallow_contrastive_loss_helper.py
- stats.py
- __init__.py
- convert_cityscapes_to_coco.py
- instances2dict_with_polygons.py
- eval_all.py
- finetune.py
- test_grounding_net.py
- test_net.py
- train_net.py
- visualize_grounding_net.py
- CODE_OF_CONDUCT.md
- DATA.md
- eval_counting.py
- eval_spatial.py
- LICENSE
- README.md
- SECURITY.md
- setup.py
- SUPPORT.md
- coco2017K.yaml
- flickr_text.yaml
- flickr_text_image.yaml
- __init__.py
- base_dataset.py
- base_dataset_kp.py
- catalog.py
- concat_dataset.py
- dataset_kp.py
- tsv.py
- tsv_dataset.py
- utils.py
- Dockerfile
- __init__.py
- keypoint_grounding_tokinzer_input.py
- text_grounding_tokinzer_input.py
- text_image_grounding_tokinzer_input.py
- __init__.py
- base.py
- imagenet.py
- imagenet_clsidx_to_label.txt
- imagenet_train_hr_indices.p
- imagenet_val_hr_indices.p
- index_synset.yaml
- lsun.py
- __init__.py
- classifier.py
- ddim.py
- ddpm.py
- ldm.py
- plms.py
- autoencoder.py
- __init__.py
- keypoint_grounding_net.py
- model.py
- openaimodel.py
- text_grounding_net.py
- text_image_grounding_net.py
- util.py
- __init__.py
- distributions.py
- __init__.py
- modules.py
- modules_backup.py
- __init__.py
- bsrgan.py
- bsrgan_light.py
- utils_image.py
- __init__.py
- contperceptual.py
- vqperceptual.py
- attention.py
- ema.py
- x_transformer.py
- lr_scheduler.py
- util.py
- distributed.py
- gligen_inference.py
- gligen_layout_counting.py
- gligen_layout_spatial.py
- inpaint_mask_func.py
- main.py
- projection_matrix
- trainer.py
- gpt4.bedroom.k-similar.k_8.px_regular.json
- gpt4.livingroom.k-similar.k_4.px_regular.json
- gpt4.counting.k-similar.k_8.px_64.json
- llama-13b.counting.k-similar.k_8.px_256.json
- gpt4.spatial.k-similar.k_8.px_64.json
- llama-13b.spatial.k-similar.k_8.px_256.json
- .gitignore
- environment.yml
- eval_counting_layout.py
- eval_scene_layout.py
- eval_spatial_layout.py
- LICENSE
- parse_llm_output.py
- README.md
- requirements.txt
- run_layoutgpt_2d.py
- run_layoutgpt_3d.py
- utils.py
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/UCSB-AI/LayoutGPT
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd LayoutGPT
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 build -f gligen/env_docker/Dockerfile -t layoutgpt .
Dockerfile을 기반으로 실행 가능한 이미지를 빌드합니다.
docker run -p 8080:80 layoutgpt
빌드된 이미지를 실제 컨테이너로 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
pip install -r requirements.txt
requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.
pip install -e .
requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.
에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.
이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.
// repository documentation
Was this content helpful?
(0 ratings)