RepViT
RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything
파일 탐색기
최종 버전 다운로드 (.zip)- __init__.py
- datasets.py
- samplers.py
- threeaugment.py
- cityscapes_detection.py
- cityscapes_instance.py
- coco_detection.py
- coco_instance.py
- coco_instance_semantic.py
- deepfashion.py
- lvis_v0.5_instance.py
- lvis_v1_instance.py
- voc0712.py
- wider_face.py
- cascade_mask_rcnn_pvtv2_b2_fpn.py
- cascade_mask_rcnn_r50_fpn.py
- cascade_rcnn_r50_fpn.py
- fast_rcnn_r50_fpn.py
- faster_rcnn_r50_caffe_c4.py
- faster_rcnn_r50_caffe_dc5.py
- faster_rcnn_r50_fpn.py
- mask_rcnn_r50_caffe_c4.py
- mask_rcnn_r50_fpn.py
- retinanet_r50_fpn.py
- rpn_r50_caffe_c4.py
- rpn_r50_fpn.py
- ssd300.py
- schedule_1x.py
- schedule_20e.py
- schedule_2x.py
- default_runtime.py
- mask_rcnn_repvit_m1_1_fpn_1x_coco.py
- mask_rcnn_repvit_m1_5_fpn_1x_coco.py
- mask_rcnn_repvit_m2_3_fpn_1x_coco.py
- repvit_m1_1_coco.json
- repvit_m1_5_coco.json
- repvit_m2_3_coco.json
- checkpoint.py
- epoch_based_runner.py
- optimizer.py
- train.py
- .gitignore
- checkpoint.py
- dist_test.sh
- dist_train.sh
- eval.sh
- README.md
- repvit.py
- slurm_train.sh
- test.py
- train.py
- train.sh
- latency.png
- repvit_m0_9_latency.png
- repvit_m0_9_distill_300e.txt
- repvit_m0_9_distill_450e.txt
- repvit_m1_0_distill_300e.txt
- repvit_m1_0_distill_450e.txt
- repvit_m1_1_distill_300e.txt
- repvit_m1_1_distill_450e.txt
- repvit_m1_5_distill_300e.txt
- repvit_m1_5_distill_450e.txt
- repvit_m2_3_distill_300e.txt
- repvit_m2_3_distill_450e.txt
- __init__.py
- repvit.py
- .DS_Store
- picture1.jpg
- picture2.jpg
- picture3.jpg
- picture4.jpg
- picture5.jpg
- picture6.jpg
- __init__.py
- tools.py
- tools_gradio.py
- .gitattributes
- app.py
- requirements.txt
- logo2.png
- mask_box.jpg
- mask_comparision.jpg
- mask_point.jpg
- model_diagram.jpg
- notebook1.png
- notebook2.png
- comparison.png
- picture1.jpg
- picture2.jpg
- automatic_mask_generator_example.ipynb
- coreml_example.ipynb
- predictor_example.ipynb
- __init__.py
- common.py
- image_encoder.py
- mask_decoder.py
- prompt_encoder.py
- repvit.py
- sam.py
- tiny_vit_sam.py
- transformer.py
- __init__.py
- amg.py
- coreml.py
- onnx.py
- transforms.py
- __init__.py
- automatic_mask_generator.py
- build_sam.py
- predictor.py
- amg.py
- export_coreml_decoder.py
- export_coreml_encoder.py
- export_onnx_model.py
- .gitignore
- CODE_OF_CONDUCT.md
- CONTRIBUTING.md
- LICENSE
- linter.sh
- README.md
- setup.cfg
- setup.py
- ade20k.py
- fpn_r50.py
- schedule_160k.py
- schedule_20k.py
- schedule_40k.py
- schedule_80k.py
- default_runtime.py
- fpn_repvit_m1_1_ade20k_40k.py
- fpn_repvit_m1_5_ade20k_40k.py
- fpn_repvit_m2_3_ade20k_40k.py
- repvit_m1_1_ade20k.json
- repvit_m1_5_ade20k.json
- repvit_m2_3_ade20k.json
- chase_db1.py
- cityscapes.py
- coco_stuff10k.py
- coco_stuff164k.py
- drive.py
- hrf.py
- pascal_context.py
- stare.py
- voc_aug.py
- mit2mmseg.py
- swin2mmseg.py
- vit2mmseg.py
- mmseg2torchserve.py
- mmseg_handler.py
- test_torchserve.py
- analyze_logs.py
- benchmark.py
- browse_dataset.py
- deploy_test.py
- dist_test.sh
- dist_train.sh
- get_flops.py
- onnx2tensorrt.py
- print_config.py
- publish_model.py
- pytorch2onnx.py
- pytorch2torchscript.py
- slurm_test.sh
- slurm_train.sh
- test.py
- train.py
- .gitignore
- align_resize.py
- eval.sh
- README.md
- repvit.py
- train.sh
- .gitignore
- engine.py
- eval.sh
- export_coreml.py
- flops.py
- LICENSE
- losses.py
- main.py
- README.md
- requirements.txt
- speed_gpu.py
- train.sh
- utils.py
# 설치 가이드
1. 코드 내려받기
git clone https://github.com/THU-MIG/RepViT
깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.
cd RepViT
방금 내려받은 프로젝트 폴더 안으로 이동합니다.
2. Python
쉬움 추천사전 준비물
pip install -r requirements.txt
requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.
python -m torch.distributed.launch --nproc_per_node=8 --master_port 12346 --use_env main.py --model repvit_m0_9 --data-path ~/imagenet --dist-eval
파이썬 스크립트(또는 모듈)를 실행합니다.
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)
