源码分析-demo-对象检测

python demo/demo.py --config-file

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml --input 001.jpg

--output results --opts MODEL.WEIGHTS

detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl

参数解释

demo/demo.py：demo文件

config-file：选择配置文件

output：输出位置（如果想直接查看，删除这个参数即可）

MODEL.WEIGHTS：预先训练好的模型

调用关系

基本流程是先下载pkl模型文件，再解析参数，加载配置文件（default的和参数的，再合并）。

然后读image文件，这里使用实例分割算法处理数据。

获取到预测的box等信息后，调用Visualizer的相关函数将检测结果绘制出来。

调用的log信息如下。

[32m[05/14 15:39:49 detectron2]:[0mArguments: Namespace(confidence_threshold=0.5, config_file='configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml', input=['001.jpg'], opts=['MODEL.WEIGHTS', 'detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl'], output='results', video_input=None, webcam=False)

sxia: cpu_device= cpu

[32m[05/14 15:39:51 fvcore.common.checkpoint]:[0mLoading checkpoint from detectron2://COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl

[32m[05/14 15:39:51 fvcore.common.file_io]:[0mURL https://dl.fbaipublicfiles.com/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl cached in /home/lappai/.torch/fvcore_cache/detectron2/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x/137849600/model_final_f10217.pkl

[32m[05/14 15:39:51 fvcore.common.checkpoint]:[0mReading a file from 'Detectron2 Model Zoo'

sxia: args.input= ['001.jpg']

sxia __call__:

sxia: run_on_image predictions= {'instances': Instances(num_instances=16, image_height=342, image_width=512, fields=[pred_boxes: Boxes(tensor([[8.4740e+00, 4.6892e+01, 1.4996e+02, 3.3636e+02],

[1.2094e+02, 2.8676e+01, 2.4164e+02, 3.4125e+02],

[3.9989e+02, 1.1977e+02, 5.0410e+02, 3.4135e+02],

[2.3525e+02, 5.9974e+01, 3.8057e+02, 3.4017e+02],

[3.5989e+02, 1.0638e+02, 4.3428e+02, 3.2155e+02],

[4.1590e+02, 1.0385e+02, 4.4406e+02, 1.5214e+02],

[2.7101e+02, 8.3826e+01, 3.0224e+02, 1.5380e+02],

[2.8008e+02, 1.1305e+02, 3.2311e+02, 1.8048e+02],

[3.1624e+02, 1.6404e+02, 4.0676e+02, 2.9497e+02],

[3.0986e+02, 5.6478e+01, 3.8312e+02, 2.0319e+02],

[1.1140e+00, 8.9818e+01, 6.5928e+01, 1.8706e+02],

[0.0000e+00, 1.0031e+02, 5.6573e+01, 3.3716e+02],

[1.3246e-01, 1.2312e+02, 6.7227e+01, 1.6550e+02],

[1.3788e-02, 8.6321e+01, 2.8173e+01, 1.4170e+02],

[4.8467e+02, 1.7300e+02, 5.1018e+02, 2.8373e+02],

[4.0865e+02, 9.6892e+01, 4.2856e+02, 1.4300e+02]], device='cuda:0')), scores: tensor([0.9969, 0.9952, 0.9943, 0.9886, 0.9663, 0.9632, 0.8624, 0.7518, 0.6952,

0.6793, 0.5957, 0.5795, 0.5773, 0.5474, 0.5355, 0.5209],

device='cuda:0'), pred_classes: tensor([ 0, 0, 0, 0, 0, 0, 0, 0, 26, 0, 0, 0, 0, 0, 26, 0],

device='cuda:0'), pred_masks: tensor([[[False, False, False, ..., False, False, False],