文章目錄

• • 一、安裝 Detectron2
  • 二、軟連接 coco 數(shù)據(jù)集
  • 三、訓(xùn)練
  • 四、數(shù)據(jù)集相關(guān)參數(shù)
  • 五、輸出結(jié)果路徑
  • 六、COCO 數(shù)據(jù)集簡(jiǎn)介
  • 七、模型相關(guān)參數(shù)
  • 八、可視化結(jié)果

一、安裝 Detectron2

初次接觸 Detectron2 的話，可能安裝會(huì)遇到些坑，大家可以按下面的方式逐步安裝，基本不會(huì)有什么問題。如果用到別的數(shù)據(jù)庫(kù)的話，安裝對(duì)應(yīng)的api就可以。

# 使用 conda 創(chuàng)建虛擬環(huán)境 conda create -n detectron2 python=3.7 # 激活虛擬環(huán)境 conda activate detectron2 # 安裝pytorch，注意對(duì)應(yīng)的 cuda conda install pytorch=1.6 torchvision cudatoolkit=10.2 -c pytorch conda install opencv-python pip install cython # 安裝cocopai https://github.com/cocodataset/cocoapi.git cd cocoapi/PythonAPI/ make python setup.py install --user cd ../../ # 安裝 DCNv2 git clone https://github.com/CharlesShang/DCNv2.git cd DCNv2 export PATH=/usr/local/cuda/bin:$PATH export LD_LIBRARY_PATH=/usr/local/cuda/lib64:$LD_LIBRARY_PATH ./make.sh # 克隆detectron2包，并安裝 git clone https://github.com/facebookresearch/detectron2.git python setup.py build develop pip install -e .

二、軟連接 coco 數(shù)據(jù)集

克隆下來的 detectron2 是下面的結(jié)構(gòu)，為了不混淆，我自己命名成了 detectron2_test：

如果不想在 coco.py 中修改文件路徑的話，可以把現(xiàn)有的 coco 數(shù)據(jù)集軟連接到 detectron2_test/detectron2/data/datasets/ 中即可：

$ cd detectron2_test/detectron2/data/datasets/ $ ln -s xxx/coco .

三、訓(xùn)練

$ pwd detectron2_test $ ./tools/train_net.py --config-file configs/COCO-Detection/faster_rcnn_R_50_C4_1x.yaml

四、數(shù)據(jù)集相關(guān)參數(shù)

數(shù)據(jù)集的相關(guān)參數(shù)是模型訓(xùn)練的很重要的一部分，如果需要訓(xùn)練自己的數(shù)據(jù)集的話，需要在下面的三個(gè)文件中，修改成自己數(shù)據(jù)集中對(duì)應(yīng)的類別個(gè)數(shù)、類別名稱和 json 路徑等。

# 1 detectron2_test/detectron2/data/datasets/coco.py

# 2 detectron2_test/detectron2/data/datasets/builtin.py

# 3 detectron2_test/detectron2/data/datasets/builtin_meta.py

coco 數(shù)據(jù)集介紹：

coco 數(shù)據(jù)集每個(gè)類別數(shù)量：

五、輸出結(jié)果路徑

detectron2_test/configs/defaults.py

六、COCO 數(shù)據(jù)集簡(jiǎn)介

coco 數(shù)據(jù)集的結(jié)構(gòu)如下，共由5個(gè)關(guān)鍵字段構(gòu)成，每個(gè)字段的內(nèi)容如下面代碼打印所示：

• info
• licenses
• images
• annotations
• categories

file = io.open('instances_val2017.json', 'r', encoding='utf-8') content = json.load(file) print(content.keys()) >>> dict_keys(['info', 'licenses', 'images', 'annotations', 'categories']) print(content['info']) >>> {'description': 'COCO 2017 Dataset', 'url': 'http://cocodataset.org', 'version': '1.0', 'year': 2017, 'contributor': 'COCO Consortium', 'date_created': '2017/09/01'} print(content['licenses']) >>>[ {'url': 'http://creativecommons.org/licenses/by-nc-sa/2.0/', 'id': 1, 'name': 'Attribution-NonCommercial-ShareAlike License'}, {'url': 'http://creativecommons.org/licenses/by-nc/2.0/', 'id': 2, 'name': 'Attribution-NonCommercial License'}, {'url': 'http://creativecommons.org/licenses/by-nc-nd/2.0/', 'id': 3, 'name': 'Attribution-NonCommercial-NoDerivs License'}, {'url': 'http://creativecommons.org/licenses/by/2.0/', 'id': 4, 'name': 'Attribution License'}, {'url': 'http://creativecommons.org/licenses/by-sa/2.0/', 'id': 5, 'name': 'Attribution-ShareAlike License'}, {'url': 'http://creativecommons.org/licenses/by-nd/2.0/', 'id': 6, 'name': 'Attribution-NoDerivs License'}, {'url': 'http://flickr.com/commons/usage/', 'id': 7, 'name': 'No known copyright restrictions'}, {'url': 'http://www.usa.gov/copyright.shtml', 'id': 8, 'name': 'United States Government Work'}] print(content['images']) >>>[ {'license': 1, 'file_name': '000000548246.jpg', 'coco_url': 'http://images.cocodataset.org/val2017/000000548246.jpg', 'height': 428, 'width': 640, 'date_captured': '2013-11-23 03:52:52', 'flickr_url': 'http://farm4.staticflickr.com/3115/2905881071_5b16058d7b_z.jpg', 'id': 548246}, ...] print(content['annotations'][0]) # type = list, len(content['annotations'])=36781 >>>{ 'segmentation': [[510.66, 423.01, 511.72, 420.03, 510.45, 416.0, 510.34, 413.02, 510.77, 410.26, 510.77, 407.5, 510.34, 405.16, 511.51, 402.83, 511.41, 400.49, 510.24, 398.16, 509.39, 397.31, 504.61, 399.22, 502.17, 399.64, 500.89, 401.66, 500.47, 402.08, 499.09, 401.87, 495.79, 401.98, 490.59, 401.77, 488.79, 401.77, 485.39, 398.58, 483.9, 397.31, 481.56, 396.35, 478.48, 395.93, 476.68, 396.03, 475.4, 396.77, 473.92, 398.79, 473.28, 399.96, 473.49, 401.87, 474.56, 403.47, 473.07, 405.59, 473.39, 407.71, 476.68, 409.41, 479.23, 409.73, 481.56, 410.69, 480.4, 411.85, 481.35, 414.93, 479.86, 418.65, 477.32, 420.03, 476.04, 422.58, 479.02, 422.58, 480.29, 423.01, 483.79, 419.93, 486.66, 416.21, 490.06, 415.57, 492.18, 416.85, 491.65, 420.24, 492.82, 422.9, 493.56, 424.39, 496.43, 424.6, 498.02, 423.01, 498.13, 421.31, 497.07, 420.03, 497.07, 415.15, 496.33, 414.51, 501.1, 411.96, 502.06, 411.32, 503.02, 415.04, 503.33, 418.12, 501.1, 420.24, 498.98, 421.63, 500.47, 424.39, 505.03, 423.32, 506.2, 421.31, 507.69, 419.5, 506.31, 423.32, 510.03, 423.01, 510.45, 423.01]], 'area': 702.1057499999998, 'iscrowd': 0, 'image_id': 289343, 'bbox': [473.07, 395.93, 38.65, 28.67], 'category_id': 18, 'id': 1768} print(content['categories']) # len(content['categories']=80) >>>[ {'supercategory': 'person', 'id': 1, 'name': 'person'}, {'supercategory': 'vehicle', 'id': 2, 'name': 'bicycle'}, {'supercategory': 'vehicle', 'id': 3, 'name': 'car'}, {'supercategory': 'vehicle', 'id': 4, 'name': 'motorcycle'}, {'supercategory': 'vehicle', 'id': 5, 'name': 'airplane'}, {'supercategory': 'vehicle', 'id': 6, 'name': 'bus'}, {'supercategory': 'vehicle', 'id': 7, 'name': 'train'}, {'supercategory': 'vehicle', 'id': 8, 'name': 'truck'}, {'supercategory': 'vehicle', 'id': 9, 'name': 'boat'}, {'supercategory': 'outdoor', 'id': 10, 'name': 'traffic light'}, {'supercategory': 'outdoor', 'id': 11, 'name': 'fire hydrant'}, {'supercategory': 'outdoor', 'id': 13, 'name': 'stop sign'}, {'supercategory': 'outdoor', 'id': 14, 'name': 'parking meter'}, {'supercategory': 'outdoor', 'id': 15, 'name': 'bench'}, {'supercategory': 'animal', 'id': 16, 'name': 'bird'}, {'supercategory': 'animal', 'id': 17, 'name': 'cat'}, {'supercategory': 'animal', 'id': 18, 'name': 'dog'}, {'supercategory': 'animal', 'id': 19, 'name': 'horse'}, {'supercategory': 'animal', 'id': 20, 'name': 'sheep'}, {'supercategory': 'animal', 'id': 21, 'name': 'cow'}, {'supercategory': 'animal', 'id': 22, 'name': 'elephant'}, {'supercategory': 'animal', 'id': 23, 'name': 'bear'}, {'supercategory': 'animal', 'id': 24, 'name': 'zebra'}, {'supercategory': 'animal', 'id': 25, 'name': 'giraffe'}, {'supercategory': 'accessory', 'id': 27, 'name': 'backpack'}, {'supercategory': 'accessory', 'id': 28, 'name': 'umbrella'}, {'supercategory': 'accessory', 'id': 31, 'name': 'handbag'}, {'supercategory': 'accessory', 'id': 32, 'name': 'tie'}, {'supercategory': 'accessory', 'id': 33, 'name': 'suitcase'}, {'supercategory': 'sports', 'id': 34, 'name': 'frisbee'}, {'supercategory': 'sports', 'id': 35, 'name': 'skis'}, {'supercategory': 'sports', 'id': 36, 'name': 'snowboard'}, {'supercategory': 'sports', 'id': 37, 'name': 'sports ball'}, {'supercategory': 'sports', 'id': 38, 'name': 'kite'}, {'supercategory': 'sports', 'id': 39, 'name': 'baseball bat'}, {'supercategory': 'sports', 'id': 40, 'name': 'baseball glove'}, {'supercategory': 'sports', 'id': 41, 'name': 'skateboard'}, {'supercategory': 'sports', 'id': 42, 'name': 'surfboard'}, {'supercategory': 'sports', 'id': 43, 'name': 'tennis racket'}, {'supercategory': 'kitchen', 'id': 44, 'name': 'bottle'}, {'supercategory': 'kitchen', 'id': 46, 'name': 'wine glass'}, {'supercategory': 'kitchen', 'id': 47, 'name': 'cup'}, {'supercategory': 'kitchen', 'id': 48, 'name': 'fork'}, {'supercategory': 'kitchen', 'id': 49, 'name': 'knife'}, {'supercategory': 'kitchen', 'id': 50, 'name': 'spoon'}, {'supercategory': 'kitchen', 'id': 51, 'name': 'bowl'}, {'supercategory': 'food', 'id': 52, 'name': 'banana'}, {'supercategory': 'food', 'id': 53, 'name': 'apple'}, {'supercategory': 'food', 'id': 54, 'name': 'sandwich'}, {'supercategory': 'food', 'id': 55, 'name': 'orange'}, {'supercategory': 'food', 'id': 56, 'name': 'broccoli'}, {'supercategory': 'food', 'id': 57, 'name': 'carrot'}, {'supercategory': 'food', 'id': 58, 'name': 'hot dog'}, {'supercategory': 'food', 'id': 59, 'name': 'pizza'}, {'supercategory': 'food', 'id': 60, 'name': 'donut'}, {'supercategory': 'food', 'id': 61, 'name': 'cake'}, {'supercategory': 'furniture', 'id': 62, 'name': 'chair'}, {'supercategory': 'furniture', 'id': 63, 'name': 'couch'}, {'supercategory': 'furniture', 'id': 64, 'name': 'potted plant'}, {'supercategory': 'furniture', 'id': 65, 'name': 'bed'}, {'supercategory': 'furniture', 'id': 67, 'name': 'dining table'}, {'supercategory': 'furniture', 'id': 70, 'name': 'toilet'}, {'supercategory': 'electronic', 'id': 72, 'name': 'tv'}, {'supercategory': 'electronic', 'id': 73, 'name': 'laptop'}, {'supercategory': 'electronic', 'id': 74, 'name': 'mouse'}, {'supercategory': 'electronic', 'id': 75, 'name': 'remote'}, {'supercategory': 'electronic', 'id': 76, 'name': 'keyboard'}, {'supercategory': 'electronic', 'id': 77, 'name': 'cell phone'}, {'supercategory': 'appliance', 'id': 78, 'name': 'microwave'}, {'supercategory': 'appliance', 'id': 79, 'name': 'oven'}, {'supercategory': 'appliance', 'id': 80, 'name': 'toaster'}, {'supercategory': 'appliance', 'id': 81, 'name': 'sink'}, {'supercategory': 'appliance', 'id': 82, 'name': 'refrigerator'}, {'supercategory': 'indoor', 'id': 84, 'name': 'book'}, {'supercategory': 'indoor', 'id': 85, 'name': 'clock'}, {'supercategory': 'indoor', 'id': 86, 'name': 'vase'}, {'supercategory': 'indoor', 'id': 87, 'name': 'scissors'}, {'supercategory': 'indoor', 'id': 88, 'name': 'teddy bear'}, {'supercategory': 'indoor', 'id': 89, 'name': 'hair drier'}, {'supercategory': 'indoor', 'id': 90, 'name': 'toothbrush'}]

七、模型相關(guān)參數(shù)

MODEL:META_ARCHITECTURE: "GeneralizedRCNN"BACKBONE:NAME: "build_resnet_fpn_backbone"RESNETS:OUT_FEATURES: ["res2", "res3", "res4", "res5"]FPN:IN_FEATURES: ["res2", "res3", "res4", "res5"]ANCHOR_GENERATOR:SIZES: [[32], [64], [128], [256], [512]] # One size for each in feature mapASPECT_RATIOS: [[0.5, 1.0, 2.0]] # Three aspect ratios (same for all in feature maps)RPN:IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]PRE_NMS_TOPK_TRAIN: 2000 # Per FPN levelPRE_NMS_TOPK_TEST: 1000 # Per FPN level# Detectron1 uses 2000 proposals per-batch,# (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)# which is approximately 1000 proposals per-image since the default batch size for FPN is 2.POST_NMS_TOPK_TRAIN: 1000POST_NMS_TOPK_TEST: 1000ROI_HEADS:NAME: "StandardROIHeads"IN_FEATURES: ["p2", "p3", "p4", "p5"]ROI_BOX_HEAD:NAME: "FastRCNNConvFCHead"NUM_FC: 2POOLER_RESOLUTION: 7ROI_MASK_HEAD:NAME: "MaskRCNNConvUpsampleHead"NUM_CONV: 4POOLER_RESOLUTION: 14 DATASETS:TRAIN: ("coco_2017_train",)TEST: ("coco_2017_val",) SOLVER:IMS_PER_BATCH: 16BASE_LR: 0.02STEPS: (60000, 80000)MAX_ITER: 90000 INPUT:MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800) VERSION: 2

八、可視化結(jié)果

demo/demo.py python demo/demo.py --config-file configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml --input /mnt/nfs-storage/train_data/coco/val2017/*.jpg --output coco_val_test --opt MODEL.WEIGHTS output/model_0049999.pth

如果類別不是coco的80類的話，需要修改下面兩個(gè)地方為自己的類別數(shù)量：

detectron2_test/detectron2/configs/default.py

總結(jié)

以上是生活随笔為你收集整理的【Detectron2】使用 Detectron2 训练基于 coco 数据集的目标检测网络的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。