imageai的安装和简单使用

下载Imageai和依赖

!pip install --upgrade pip
!pip install opencv-python
!pip install https://github.com/OlafenwaMoses/ImageAI/releases/download/2.0.2/imageai-2.0.2-py3-none-any.whl
!pip install keras==2.2.4
!pip install 'h5py<3.0.0'
!pip install tensorflow==1.15.0
python3.6

下载网络参数

!wget https://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/yolo.h5
!wget https://github.com/OlafenwaMoses/ImageAI/releases/download/1.0/resnet50_coco_best_v2.0.1.h5

调用RetinaNet和yolov3

import warnings
warnings.filterwarnings('ignore')
#tensorflow 1.x
from imageai.Detection import ObjectDetection
from imutils import paths
detector = ObjectDetection()
detector.setModelTypeAsRetinaNet() #For YOLO model change to detector.setModelTypeAsYOLOv3()
detector.setModelPath('./data/resnet50_coco_best_v2.0.1.h5') #For YOLO model change to detector.setModelPath("yolo.h5")
detector.loadModel()

imagePaths = sorted(list(paths.list_images('./data/task1')))
#1
for image in imagePaths:
    list = detector.detectObjectsFromImage(
        input_image = image, # Specify the input file name
        output_image_path = './data/out/'+image.split('/')[-1], # Specify the output file name
        minimum_percentage_probability = 50 # Specify cutoof treshold
    )
#2
for image in imagePaths:
    list = detector.detectObjectsFromImage(
        input_image = image, # Specify the input file name
        output_image_path = './data/out/'+image.split('/')[-1], # Specify the output file name
        minimum_percentage_probability = 80 # Specify cutoof treshold
    )
#3
import warnings
warnings.filterwarnings('ignore')
#tensorflow 1.x
from imageai.Detection import ObjectDetection
from imutils import paths
detector = ObjectDetection()
detector.setModelTypeAsYOLOv3()
detector.setModelPath("./data/yolo.h5")
detector.loadModel()
imagePaths = sorted(list(paths.list_images('./data/task1')))
for image in imagePaths:
    list = detector.detectObjectsFromImage(
        input_image = image, # Specify the input file name
        output_image_path = './data/out/'+image.split('/')[-1], # Specify the output file name
        minimum_percentage_probability = 50 # Specify cutoof treshold
    )
#4
for image in imagePaths:
    list = detector.detectObjectsFromImage(
        input_image = image, # Specify the input file name
        output_image_path = './data/out/'+image.split('/')[-1], # Specify the output file name
        minimum_percentage_probability = 80 # Specify cutoof treshold
    )

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 打赏
    打赏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包

打赏作者

фора 快跑

你的鼓励将是我创作的最大动力

¥1 ¥2 ¥4 ¥6 ¥10 ¥20
扫码支付:¥1
获取中
扫码支付

您的余额不足,请更换扫码支付或充值

打赏作者

实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值