odin
Code for the paper: "ODIN: A Single Model for 2D and 3D Segmentation" (CVPR 2024)
파일 탐색기
최종 버전 다운로드 (.zip)- maskformer2_swin_base_384_bs16_50ep.yaml
- maskformer2_swin_base_IN21k_384_bs16_50ep.yaml
- maskformer2_swin_large_IN21k_384_bs16_100ep.yaml
- maskformer2_swin_small_bs16_50ep.yaml
- maskformer2_swin_tiny_bs16_50ep.yaml
- Base-COCO-InstanceSegmentation.yaml
- maskformer2_R50_bs16_50ep.yaml
- 2d.yaml
- 3d.yaml
- base.yaml
- swin_2d.yaml
- swin_3d.yaml
- swin_base.yaml
- video.yaml
- __init__.py
- ai2thor2coco.py
- ai2thor_datagen.py
- ai2thor_utils.py
- controller_custom.py
- globals_dirs.py
- README.md
- startx.py
- category_mapping.tsv
- generate_splits.py
- global_dirs.py
- m3d2coco.py
- process_matterport.py
- process_matterport_3d.py
- README.md
- convert_dataset.py
- convert_dataset_raw.py
- generate_s3dis_splits.py
- global_dirs.py
- README.md
- s3dis2coco.py
- s3dis_preprocessing.py
- download_scannet_files.py
- globals_dirs.py
- preprocess_sens.sh
- reader.py
- README.md
- scannet2coco.py
- scannet_preprocessing.py
- SensorData.py
- __init__.py
- base_preprocessing.py
- inpaint_depth.py
- __init__.py
- functions.py
- bfs_cluster.cpp
- bfs_cluster_kernel.cu
- setup.py
- __init__.py
- aggregation.py
- attention.py
- grouping.py
- interpolation.py
- query.py
- sampling.py
- subtraction.py
- utils.py
- aggregation_cuda.cpp
- aggregation_cuda_kernel.cu
- aggregation_cuda_kernel.h
- attention_cuda.cpp
- attention_cuda_kernel.cu
- attention_cuda_kernel.h
- ball_query_cuda.cpp
- ball_query_cuda_kernel.cu
- ball_query_cuda_kernel.h
- grouping_cuda.cpp
- grouping_cuda_kernel.cu
- grouping_cuda_kernel.h
- interpolation_cuda.cpp
- interpolation_cuda_kernel.cu
- interpolation_cuda_kernel.h
- knn_query_cuda.cpp
- knn_query_cuda_kernel.cu
- knn_query_cuda_kernel.h
- random_ball_query_cuda.cpp
- random_ball_query_cuda_kernel.cu
- random_ball_query_cuda_kernel.h
- sampling_cuda.cpp
- sampling_cuda_kernel.cu
- sampling_cuda_kernel.h
- subtraction_cuda.cpp
- subtraction_cuda_kernel.cu
- subtraction_cuda_kernel.h
- __init__.py
- cuda_utils.h
- pointops_api.cpp
- __init__.py
- setup.py
- __init__.py
- pointops.py
- pointops2.py
- pointops_ablation.py
- test_attention_op_step1.py
- test_attention_op_step1_v2.py
- test_attention_op_step2.py
- test_relative_pos_encoding_op_step1.py
- test_relative_pos_encoding_op_step1_v2.py
- test_relative_pos_encoding_op_step1_v3.py
- test_relative_pos_encoding_op_step2.py
- test_relative_pos_encoding_op_step2_v2.py
- aggregation_cuda.cpp
- aggregation_cuda_kernel.cu
- aggregation_cuda_kernel.h
- attention_cuda.cpp
- attention_cuda_kernel.cu
- attention_cuda_kernel.h
- attention_cuda_kernel_v2.cu
- attention_cuda_kernel_v2.h
- attention_cuda_v2.cpp
- grouping_cuda.cpp
- grouping_cuda_kernel.cu
- grouping_cuda_kernel.h
- interpolation_cuda.cpp
- interpolation_cuda_kernel.cu
- interpolation_cuda_kernel.h
- knnquery_cuda.cpp
- knnquery_cuda_kernel.cu
- knnquery_cuda_kernel.h
- relative_pos_encoding_cuda.cpp
- relative_pos_encoding_cuda_kernel.cu
- relative_pos_encoding_cuda_kernel.h
- relative_pos_encoding_cuda_kernel_v2.cu
- relative_pos_encoding_cuda_kernel_v2.h
- relative_pos_encoding_cuda_v2.cpp
- sampling_cuda.cpp
- sampling_cuda_kernel.cu
- sampling_cuda_kernel.h
- subtraction_cuda.cpp
- subtraction_cuda_kernel.cu
- subtraction_cuda_kernel.h
- __init__.py
- cuda_utils.h
- pointops_api.cpp
- __init__.py
- setup.py
- __init__.py
- builtin.py
- scannet_context.py
- __init__.py
- evaluate_semantic_instance.py
- util.py
- util_3d.py
- __init__.py
- build.py
- coco.py
- coco_evaluation.py
- cocoeval.py
- dataset_mapper_coco.py
- dataset_mapper_scannet.py
- fast_eval_api.py
- scannet_3d_eval.py
- scannet_3d_eval_semantic.py
- sentence_utils.py
- resnet.py
- swin.py
- __init__.py
- backproject.py
- __init__.py
- cross_view_attention.py
- language_encoder.py
- odin_head.py
- self_cross_attention_layers.py
- __init__.py
- ms_deform_attn_func.py
- __init__.py
- ms_deform_attn.py
- ms_deform_attn_cpu.cpp
- ms_deform_attn_cpu.h
- ms_deform_attn_cuda.cu
- ms_deform_attn_cuda.h
- ms_deform_im2col_cuda.cuh
- ms_deform_attn.h
- vision.cpp
- make.sh
- setup.py
- test.py
- __init__.py
- msdeformattn.py
- __init__.py
- odin_transformer_decoder.py
- position_encoding.py
- __init__.py
- criterion.py
- matcher.py
- __init__.py
- feature_vis.py
- inpaint_depth.py
- memory.py
- misc.py
- util_3d.py
- util_video_to_3d.py
- vis_utils.py
- __init__.py
- config.py
- global_vars.py
- odin_model.py
- scannet_frozen_backbone.sh
- scannet_frozen_backbone_swin.sh
- scannet_no_3d_fusion.sh
- scannet_no_interleave.sh
- scannet_no_pretrain.sh
- scannet_only_backbone_pretrain.sh
- ai2thor_resnet.sh
- ai2thor_swin.sh
- alfred_resnet.sh
- scannet_coco_resnet.sh
- matterport_resnet.sh
- matterport_swin.sh
- s3dis_resnet_finetuned.sh
- s3dis_resnet_scratch.sh
- s3dis_swin_finetuned.sh
- scannet_resnet.sh
- scannet_swin.sh
- scannet_swin_benchmark.sh
- scannet200_resnet.sh
- scannet200_swin.sh
- scannet200_swin_benchmark.sh
- ai2thor_train.txt
- ai2thor_val.txt
- ten_scene.txt
- two_scene.txt
- alfred_train.txt
- alfred_two_scene.txt
- alfred_valid_seen.txt
- alfred_valid_unseen.txt
- m3d_train.txt
- m3d_val.txt
- ten_m3d_scene.txt
- ten_scene.txt
- two_m3d_scene.txt
- two_scene.txt
- debug.txt
- s3dis_area_1_train.txt
- s3dis_area_1_val.txt
- s3dis_area_2_train.txt
- s3dis_area_2_val.txt
- s3dis_area_3_train.txt
- s3dis_area_3_val.txt
- s3dis_area_4_train.txt
- s3dis_area_4_val.txt
- s3dis_area_6_train.txt
- s3dis_area_6_val.txt
- s3dis_train.txt
- s3dis_val.txt
- ten_area_1_scene.txt
- ten_area_2_scene.txt
- ten_area_3_scene.txt
- ten_area_4_scene.txt
- ten_area_6_scene.txt
- ten_scene.txt
- two_area_1_scene.txt
- two_area_2_scene.txt
- two_area_3_scene.txt
- two_area_4_scene.txt
- two_area_6_scene.txt
- two_scene.txt
- scannetv2_test.txt
- scannetv2_train.txt
- scannetv2_trainval.txt
- scannetv2_val.txt
- ten_scene.txt
- two_scene.txt
- .gitignore
- init.sh
- LICENSE
- README.md
- requirements.txt
- train_odin.py
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/ayushjain1144/odin
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd odin
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. 공식 설치 스크립트
쉬움 추천사전 준비물
- Python 3 pip 명령어를 쓰려면 Python이 필요합니다.
pip install torch==2.2.0+cu118 torchvision==0.17.0+cu118 --extra-index-url https://download.pytorch.org/whl/cu118
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.2.0+cu118.html
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
설치 후 새 터미널을 열고, 프로그램의 버전 확인 명령(예: --version)으로 정상 설치됐는지 확인하세요.
이 레포의 README에 적힌 실제 명령어를 그대로 가져왔습니다.
3. Python
쉬움사전 준비물
pip install torch==2.2.0+cu118 torchvision==0.17.0+cu118 --extra-index-url https://download.pytorch.org/whl/cu118
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
pip install torch-scatter -f https://data.pyg.org/whl/torch-2.2.0+cu118.html
PyPI에 배포된 패키지를 바로 설치합니다. 소스 클론이 필요 없습니다.
pip install -r requirements.txt
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)