贴一下opencv加载pb的方法，跟加载其他模型没有区别。
def main(argv=None):
# import the necessary packages
from imutils.object_detection import non_max_suppression
import numpy as np
import argparse
import time
import cv2
# construct the argument parser and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", type=str,
help="D:/work/video/EAST/tmp/frame_74.jpg")
ap.add_argument("-east", "--east", type=str,
help="D:/work/video/hand_tracking_no_op/hand_tracking/EAST/east_icdar2015_resnet_v1_50_rbox/out.pb")
ap.add_argument("-c", "--min-confidence", type=float, default=0.5,
help="minimum probability required to inspect a region")
ap.add_argument("-w", "--width", type=int, default=320,
help="resized image width (should be multiple of 32)")
ap.add_argument("-e", "--height", type=int, default=320,
help="resized image height (should be multiple of 32)")
args = vars(ap.parse_args())
layerNames = [
"feature_fusion/Conv_7/Sigmoid",
"feature_fusion/concat_3"]
# load the pre-trained EAST text detector
print("[INFO] loading EAST text detector...")
# net = cv2.dnn.readNet(args["east"])
pbtxt_path='D:/work/video/EAST/protobuf.pbtxt'
net = cv2.dnn.readNetFromTensorflow(args["east"])
# load the input image and grab the image dimensions
for i in range(15):
image = cv2.imread(args["image"])
orig = image.copy()
(H, W) = image.shape[:2]
# set the new width and height and then determine the ratio in change
# for both the width and height
# resize the image and grab the new image dimensions
# construct a blob from the image and then perform a forward pass of
# the model to obtain the two output layer sets
blob = cv2.dnn.blobFromImage(image, 1.0, (W,H), swapRB=True, crop=False)
net.setInput(blob)
start = time.time()
(scores, geometry) = net.forward(layerNames)
#geometry = net.forward()
end = time.time()
# show timing information on text prediction
print("[INFO] text detection took {:.6f} seconds".format(end - start))
# grab the number of rows and columns from the scores volume, then
# initialize our set of bounding box rectangles and corresponding
# confidence scores
(numRows, numCols) = scores.shape[2:4]
print('numRows, numCols:',numRows, numCols)
rects = []
confidences = []
# loop over the number of rows
for y in range(0, numRows):
# extract the scores (probabilities), followed by the geometrical
# data used to derive potential bounding box coordinates that
# surround text
scoresData = scores[0, 0, y]
xData0 = geometry[0, 0, y]
xData1 = geometry[0, 1, y]
xData2 = geometry[0, 2, y]
xData3 = geometry[0, 3, y]
anglesData = geometry[0, 4, y]
# loop over the number of columns
for x in range(0, numCols):
# if our score does not have sufficient probability, ignore it
if scoresData[x] < args["min_confidence"]:
continue
(offsetX, offsetY) = (x * 4.0, y * 4.0)
# extract the rotation angle for the prediction and then
# compute the sin and cosine
angle = anglesData[x]
cos = np.cos(angle)
sin = np.sin(angle)
# use the geometry volume to derive the width and height of
# the bounding box
h = xData0[x] + xData2[x]
w = xData1[x] + xData3[x]
# compute both the starting and ending (x, y)-coordinates for
# the text prediction bounding box
endX = int(offsetX + (cos * xData1[x]) + (sin * xData2[x]))
endY = int(offsetY - (sin * xData1[x]) + (cos * xData2[x]))
startX = int(endX - w)
startY = int(endY - h)
# add the bounding box coordinates and probability score to
# our respective lists
rects.append((startX, startY, endX, endY))
confidences.append(scoresData[x])
# apply non-maxima suppression to suppress weak, overlapping bounding
# boxes
boxes = non_max_suppression(np.array(rects), probs=confidences)
print(confidences,boxes)
# loop over the bounding boxes
for (startX, startY, endX, endY) in boxes:
# scale the bounding box coordinates based on the respective
# ratios
startX = startX
startY = startY
endX = endX
endY = endY
print(startX, startY, endX, endY)
# draw the bounding box on the image
cv2.rectangle(orig, (startX, startY), (endX, endY), (0, 255, 0), 1)
# show the output image
cv2.imwrite('D:/work/video/EAST/tmp/0424.jpg',orig)
cv2.imshow("Text Detection", orig)
cv2.waitKey(0)
cv2.destroyAllWindows()
由于opencv加载和tf加载的输出是不一样的，所以预测之后的数据处理也是不一样的，但是都要用nms来找到最终的box。
用opencv加载时间上并没有明显的提速，个人认为是opencv dnn没有支持该框架加速，
