# opencv.dnn做图像分类 图像分类是基于深度学习的计算机视觉任务中最简单、也是最基础的一类,它其中用到的CNN特征提取技术也是目标检测、目标分割等视觉任务的基础。 ![](https://gitcode.net/csdn/skill_tree_opencv/-/raw/master/data/1.OpenCV初阶/7.OpenCV中的深度学习/1.图像分类/result.png) 具体到图像分类任务而言,其具体流程如下: 1. 输入指定大小RGB图像,1/3通道,宽高一般相等 2. 通过卷积神经网络进行多尺度特征提取,生成高维特征值 3. 利用全连接网络、或其他结构对高维特征进行分类,输出各目标分类的概率值(概率和为1) 4. 选择概率值最高的作为图像分类结果 ![](https://gitcode.net/csdn/skill_tree_opencv/-/raw/master/data/1.OpenCV初阶/7.OpenCV中的深度学习/1.图像分类/classification.png) `opencv.dnn`模块可以直接加载深度学习模型,并进行推理输出运行结果。下面是opencv.dnn模块加载googlenet caffe模型进行图片分类的代码,请你完善其中TO-DO部分的代码。 > 代码中LABEL_MAP是图像分类名称字典,给定索引得到具体分类名称(string)。 ```python import cv2 import numpy as np from labels import LABEL_MAP # 1000 labels in imagenet dataset if __name__=='__main__': # caffe model, googlenet aglo weights = "bvlc_googlenet.caffemodel" protxt = "bvlc_googlenet.prototxt" # read caffe model from disk net = cv2.dnn.readNetFromCaffe(protxt, weights) # create input image = cv2.imread("ocean-liner.jpg") blob = cv2.dnn.blobFromImage(image, 1.0, (224, 224), (104, 117, 123), False, crop=False) result = np.copy(image) # run! net.setInput(blob) out = net.forward() # TODO(You): 请在此实现代码 # time cost t, _ = net.getPerfProfile() label = 'cost time: %.2f ms' % (t * 1000.0 / cv2.getTickFrequency()) cv2.putText(result, label, (0, 20), cv2.FONT_HERSHEY_SIMPLEX, 0.8, (255, 255, 0), 2) # render on image label = '%s: %.4f' % (LABEL_MAP[classId] if LABEL_MAP else 'Class #%d' % classId, confidence) cv2.putText(result, label, (0, 60), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2) show_img = np.hstack((image, result)) # normal codes in opencv cv2.imshow("Image", show_img) cv2.waitKey(0) ``` 以下对TODO部分实现正确的是? ## 答案 ```python # output probability, find the right index out = out.flatten() classId = np.argmax(out) confidence = out[classId] ``` ## 选项 ### 输出理解错误 ```python # output probability, find the right index classId = out[0] confidence = out[1] ``` ### 输出维度理解错误 ```python # output probability, find the right index classId = np.argmax(out) confidence = out[classId] ``` ### 输出理解错误2 ```python # output probability, find the right index out = out.flatten() classId = np.argmax(out[1:]) confidence = out[classId + 1] ```