引言 ·
前面说了OpenCV DNN不光支持图像分类与对象检测模型。此外还支持各种自定义的模型，deeplabv3模型是图像语义分割常用模型之一，本文我们演示OpenCV DNN如何调用Deeplabv3模型实现图像语义分割，支持的backbone网络分别为MobileNet与Inception。预训练模型下载地址如下：
代码语言：javascript复制https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md预训练的模型下载之后可以看到pb文件，ckpt文件，其中pb文件可以直接调用。
调用MobileNet的deeplabv3
下载MobileNet版本的deeplabv3模型，把mobilenetv2 ckpt转pb，脚本如下：
代码语言：javascript复制python deeplab/export_model.py
--logtostderr
--checkpoint_path="/home/lw/data/cityscapes/train/model.ckpt-2000"
--export_path="/home/lw/data/pb/frozen_inference_graph.pb"
--model_variant="mobilenet_v2"
#--atrous_rates=6
#--atrous_rates=12
#--atrous_rates=18
#--output_stride=16
--decoder_output_stride=4
--num_classes=6
--crop_size=513
--crop_size=513
--inference_scales=1.0接下来使用opencv加载mobilenetv2转换好的pb模型会报下面的错误：
使用mobilenetv2的解决办法:
代码语言：javascript复制import tensorflow as tf
from tensorflow.tools.graph_transforms import TransformGraph
from tensorflow.python.tools import optimize_for_inference_lib
graph = 'frozen_inference_graph.pb'
with tf.gfile.FastGFile(graph, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.summary.FileWriter('logs', graph_def)
inp_node = 'MobilenetV2/MobilenetV2/input'
out_node = 'logits/semantic/BiasAdd'
graph_def = optimize_for_inference_lib.optimize_for_inference(graph_def, [inp_node], [out_node],
tf.float32.as_datatype_enum)
graph_def = TransformGraph(graph_def, [inp_node], [out_node], ["sort_by_execution_order"])
with tf.gfile.FastGFile('frozen_inference_graph_opt.pb', 'wb') as f:
f.write(graph_def.SerializeToString())调用Inception的deeplabv3 接下来使用opencv加载xception转换好的pb模型
使用xception的解决办法
代码语言：javascript复制import tensorflow as tf
from tensorflow.tools.graph_transforms import TransformGraph
from tensorflow.python.tools import optimize_for_inference_lib
graph = 'frozen_inference_graph.pb'
with tf.gfile.FastGFile(graph, 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
tf.summary.FileWriter('logs', graph_def)
# inp_node = 'sub_2' # 起始地节点
# out_node = 'logits/semantic/BiasAdd' # 结束的节点
graph_def = optimize_for_inference_lib.optimize_for_inference(graph_def, [inp_node], [out_node],
tf.float32.as_datatype_enum)
graph_def = TransformGraph(graph_def, [inp_node], [out_node], ["sort_by_execution_order"])
with tf.gfile.FastGFile('frozen_inference_graph_opt.pb', 'wb') as f:
f.write(graph_def.SerializeToString())使用opencv进行推理（我用的是ADE20K预训练模型进行测试的）
代码语言：javascript复制import cv2
import numpy as np
np.random.seed(0)
color = np.random.randint(0, 255, size=[150, 3])
print(color)
# Load names of classes
#classes = None
#with open("labels.names", 'rt') as f:
# classes = f.read().rstrip('n').split('n')
#legend = None
#def showLegend(classes):
# global legend
# if not classes is None and legend is None:
# blockHeight = 30
# print(len(classes), len(colors))
# assert(len(classes) == len(colors))
# legend = np.zeros((blockHeight * len(colors), 200, 3), np.uint8)
# for i in range(len(classes)):
# block = legend[i * blockHeight:(i 1) * blockHeight]
# block[:, :] = colors[i]
# cv2.putText(block, classes[i], (0, blockHeight//2), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 255, 255))
# cv2.namedWindow('Legend', cv2.WINDOW_NORMAL)
# cv2.imshow('Legend', legend)
# cv2.waitKey()
# 读取图片
frame = cv2.imread("1.jpg")
frameHeight = frame.shape[0]
frameWidth = frame.shape[1]
# 加载模型
net = cv2.dnn.readNet("frozen_inference_graph_opt.pb")
blob = cv2.dnn.blobFromImage(frame, 0.007843, (513, 513), (127.5, 127.5, 127.5), swapRB=True)
net.setInput(blob)
score = net.forward()
numClasses = score.shape[1]
height = score.shape[2]
width = score.shape[3]
classIds = np.argmax(score[0], axis=0) # 在列上求最大的值的索引
segm = np.stack([color[idx] for idx in classIds.flatten()])
segm = segm.reshape(height, width, 3)
segm = cv2.resize(segm, (frameWidth, frameHeight), interpolation=cv2.INTER_NEAREST)
frame = (0.3*frame 0.8*segm).astype(np.uint8)
#showLegend(classes)
cv2.imshow("img", frame)
cv2.waitKey()
