diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ab2832a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +# .gitattributes + +# Source files +# ============ +*.pxd text diff=python +*.py text diff=python +*.py3 text diff=python +*.pyw text diff=python +*.pyx text diff=python +*.pyz text diff=python +*.pyi text diff=python + +# Binary files +# ============ +*.db binary +*.p binary +*.pkl binary +*.pickle binary +*.pyc binary export-ignore +*.pyo binary export-ignore +*.pyd binary + +# Jupyter notebook +*.ipynb text + +# Model files +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tar.gz filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..32030ff --- /dev/null +++ b/.gitignore @@ -0,0 +1,209 @@ +### Linux ### +*~ + +# temporary files which can be created if a process still has a handle open of a deleted file +.fuse_hidden* + +# KDE directory preferences +.directory + +# Linux trash folder which might appear on any partition or disk +.Trash-* + +# .nfs files are created when an open file is removed but is still being accessed +.nfs* + +### OSX ### +# General +.DS_Store +.AppleDouble +.LSOverride + +# Icon must end with two \r +Icon + + +# Thumbnails +._* + +# Files that might appear in the root of a volume +.DocumentRevisions-V100 +.fseventsd +.Spotlight-V100 +.TemporaryItems +.Trashes +.VolumeIcon.icns +.com.apple.timemachine.donotpresent + +# Directories potentially created on remote AFP share +.AppleDB +.AppleDesktop +Network Trash Folder +Temporary Items +.apdisk + +### Python ### +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[cod] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py,cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +#Pipfile.lock + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# SageMath parsed files +*.sage.py + +# Environments +.env +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +### Windows ### +# Windows thumbnail cache files +Thumbs.db +Thumbs.db:encryptable +ehthumbs.db +ehthumbs_vista.db + +# Dump file +*.stackdump + +# Folder config file +[Dd]esktop.ini + +# Recycle Bin used on file shares +$RECYCLE.BIN/ + +# Windows Installer files +*.cab +*.msi +*.msix +*.msm +*.msp + +# Windows shortcuts +*.lnk \ No newline at end of file diff --git a/README.md b/README.md index b1880ca..f184844 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,35 @@ # detectron2 -2 \ No newline at end of file + +# Object Detection using Detectron2 + +## Description + +This operator uses Facebook's [Detectron2](https://github.com/facebookresearch/detectron2) library to compute bounding boxes, class labels, and class scores for detected objects in a given image. + +## Code Example + +```python +import towhee + +towhee.glob('./towhee.jpg') \ + .image_decode.cv2() \ + .object_detection.detectron2(model_name='retinanet_resnet50') \ + .show() +``` + +## Factory Constructor + +Create the operator via the following factory method + +***object_detection.detectron2(model_name='retinanet_resnet50', thresh=0.5, num_classes=1000, skip_preprocess=False)*** + +**Parameters:** + +***model_name:*** *str* + +A string indicating which model to use. + +***thresh:*** *float* + +The threshold value for which an object is detected (default value: `0.5`). Set this value lower to detect more objects at the expense of accuracy, or higher to reduce the total number of detections but increase the quality of detected objects. diff --git a/__init__.py b/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/detectron2.py b/detectron2.py new file mode 100644 index 0000000..adc543f --- /dev/null +++ b/detectron2.py @@ -0,0 +1,57 @@ +from typing import List, Tuple + +from detectron2 import model_zoo +from detectron2.config import get_cfg +from detectron2.engine.defaults import DefaultPredictor +import numpy as np +import torch +from towhee._types import Image +from towhee.operator import NNOperator, OperatorFlag + + +CFG_YAMLS = { + 'faster_rcnn_resnet50_c4': 'COCO-Detection/faster_rcnn_R_50_C4_3x.yaml', + 'faster_rcnn_resnet50_dc5': 'COCO-Detection/faster_rcnn_R_50_DC5_3x.yaml', + 'faster_rcnn_resnet50_fpn': 'COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml', + 'faster_rcnn_resnet101_c4': 'COCO-Detection/faster_rcnn_R_101_C4_3x.yaml', + 'faster_rcnn_resnet101_dc5': 'COCO-Detection/faster_rcnn_R_101_DC5_3x.yaml', + 'faster_rcnn_resnet101_fpn': 'COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml', + 'faster_rcnn_resnext101': 'COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml', + 'retinanet_resnet50': 'COCO-Detection/retinanet_R_50_FPN_3x.yaml', + 'retinanet_resnet101': 'COCO-Detection/retinanet_R_101_FPN_3x.yaml' +} + + +@register(outputschema=['boxes', 'classes', 'scores'], + flag=OperatorFlag.STATELESS | OperatorFlag.REUSABLE) +class Detectron2ObjectDetection(NNOperator): + """ + This Operator implements object detection using the Detectron2 library. + + Args: + model_name (`str`): + Detectron2-based model to use. For a full list, see `CFG_YAMLS`. + """ + + def __init__(self, model_name: str = 'retinanet_resnet50', thresh: int = 0.5): + super().__init__() + + cfg = get_cfg() + cfg.merge_from_file(model_zoo.get_config_file(CFG_YAMLS[model_name])) + cfg.MODEL.DEVICE = 'cuda:0' if torch.cuda.is_available() else 'cpu' + cfg.MODEL.RETINANET.SCORE_THRESH_TEST = thresh + cfg.MODEL.ROI_HEADS.SCORE_THRESH_TEST = 0.5 + cfg.MODEL.PANOPTIC_FPN.COMBINE.INSTANCES_CONFIDENCE_THRESH = 0.5 + cfg.freeze() + + self._predictor = DefaultPredictor(cfg) + + def __call__(self, image: 'towhee._types.Image') -> Tuple[List]: + + # Detectron2 uses BGR-formatted images + res = self._predictor(image.to_ndarray()[:,:,::-1]) + boxes = res.get('pred_boxes').tensor.numpy() + classes = res.get('pred_classes').numpy() + scores = res.get('scores').numpy() + + return (boxes, classes, scores) diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..3b08d0f --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +torch >= 1.8 +torchvision >= 0.9.0 +https://github.com/facebookresearch/detectron2/archive/refs/tags/v0.6.tar.gz