如何解决整体嵌套边缘检测OpenCv Python中的hed [0,0]是什么?
我对python也是openCv的新手。我正在尝试检测深度学习边缘的代码,并试图理解它。我在网站https://www.pyimagesearch.com
上找到了此代码# USAGE
# python detect_edges_image.py --edge-detector hed_model --image images/guitar.jpg
# import the necessary packages
import argparse
import cv2
import os
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-d","--edge-detector",type=str,required=True,help="path to OpenCV's deep learning edge detector")
ap.add_argument("-i","--image",help="path to input image")
args = vars(ap.parse_args())
class CropLayer(object):
def __init__(self,params,blobs):
# initialize our starting and ending (x,y)-coordinates of
# the crop
self.startX = 0
self.startY = 0
self.endX = 0
self.endY = 0
def getMemoryShapes(self,inputs):
# the crop layer will receive two inputs -- we need to crop
# the first input blob to match the shape of the second one,# keeping the batch size and number of channels
(inputShape,targetShape) = (inputs[0],inputs[1])
(batchSize,numChannels) = (inputShape[0],inputShape[1])
(H,W) = (targetShape[2],targetShape[3])
# compute the starting and ending crop coordinates
self.startX = int((inputShape[3] - targetShape[3]) / 2)
self.startY = int((inputShape[2] - targetShape[2]) / 2)
self.endX = self.startX + W
self.endY = self.startY + H
# return the shape of the volume (we'll perform the actual
# crop during the forward pass
return [[batchSize,numChannels,H,W]]
def forward(self,inputs):
# use the derived (x,y)-coordinates to perform the crop
return [inputs[0][:,:,self.startY:self.endY,self.startX:self.endX]]
# load our serialized edge detector from disk
print("[INFO] loading edge detector...")
protoPath = os.path.sep.join([args["edge_detector"],"deploy.prototxt"])
modelPath = os.path.sep.join([args["edge_detector"],"hed_pretrained_bsds.caffemodel"])
net = cv2.dnn.readNetFromCaffe(protoPath,modelPath)
# register our new layer with the model
cv2.dnn_registerLayer("Crop",CropLayer)
# load the input image and grab its dimensions
image = cv2.imread(args["image"])
(H,W) = image.shape[:2]
print("Height: ",H)
print("Width: ",W)
# convert the image to grayscale,blur it,and perform Canny
# edge detection
print("[INFO] performing Canny edge detection...")
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
blurred = cv2.GaussianBlur(gray,(5,5),0)
canny = cv2.Canny(blurred,30,150)
# construct a blob out of the input image for the Holistically-Nested
# Edge Detector
blob = cv2.dnn.blobFromImage(image,scalefactor=1.0,size=(W,H),mean=(104.00698793,116.66876762,122.67891434),swapRB=False,crop=False)
# set the blob as the input to the network and perform a forward pass
# to compute the edges
print("[INFO] performing holistically-nested edge detection...")
net.setInput(blob)
hed = net.forward()
print("before: ",hed)
hed = cv2.resize(hed[0,0],(W,H))
print("after:",hed)
hed = (255 * hed).astype("uint8")
# show the output edge detection results for Canny and
# Holistically-Nested Edge Detection
cv2.imshow("Input",image)
cv2.imshow("Canny",canny)
cv2.imshow("HED",hed)
cv2.waitKey(0)
有人可以解释hed[0,0]
返回什么,hed = cv2.resize(hed[0,H))
做什么吗?
另外hed = (255 * hed).astype("uint8")
如果可能的话,可以用JAVA或C ++等不同语言进行解释
解决方法
我发现的东西在这里
前馈过程后:
hed = net.forward()
print(hed.shape)
你的答案是: (1,1,2121,4148)
当你调整大小时:
hed = cv2.resize(hed[0,0],(W,H))
print (hed.shape)
你的答案变成了: (2121,4148)
所以您似乎正在减少数组 (hed) 的维度以适应原始图像的 H、W。
,嗯。我也有同样的问题。
但它似乎将 hed 图像的大小调整为新的 H 和 W 尺寸。
示例如下:
newwidth = 350
newheight = 450
dim = (width,height)
# resize image
resized = cv2.resize(img,dim,interpolation = cv2.INTER_AREA)
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。