上传图像分类题目

data/1.OpenCV初阶/7.OpenCV中的深度学习/1.图像分类/classification.md

+# 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。
+
+![](./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
+
+![](./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
+
+# 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()
+
+# TO-DO your code...
+
+# 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)
+
+```
+
+
+## 答案
+
+```python
+# output probability, find the right index
+out = out.flatten()
+classId = np.argmax(out)
+confidence = out[classId]
+
+```
+
+## 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
+
+```python
+# output probability, find the right index
+out = out.flatten()
+classId = np.argmax(out[1:])
+confidence = out[classId + 1]
+
+```
\ No newline at end of file

data/1.OpenCV初阶/7.OpenCV中的深度学习/1.图像分类/classification.py

+import cv2
+import numpy as np
+from labels import LABEL_MAP # 1000 labels in imagenet dataset
+
+# 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("MY_TEST/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()
+
+# output probability, find the right index
+out = out.flatten()
+classId = np.argmax(out)
+confidence = out[classId]
+
+# 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)
\ No newline at end of file