點選上方藍字關注我們
微信公衆号：OpenCV學堂
關注擷取更多計算機視覺與深度學習知識
作者:本文作者不願意留下署名
編輯：gloomyfish
引言 ·
前面說了OpenCV DNN不光支援圖像分類與對象檢測模型。此外還支援各種自定義的模型，deeplabv3模型是圖像語義分割常用模型之一，本文我們示範OpenCV DNN如何調用Deeplabv3模型實作圖像語義分割，支援的backbone網絡分别為MobileNet與Inception。預訓練模型下載下傳位址如下：
https://github.com/tensorflow/models/blob/master/research/deeplab/g3doc/model_zoo.md
預訓練的模型下載下傳之後可以看到pb檔案，ckpt檔案，其中pb檔案可以直接調用。
調用MobileNet的deeplabv3
下載下傳MobileNet版本的deeplabv3模型，把mobilenetv2 ckpt轉pb，腳本如下：
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
接下來使用opencv加載mobilenetv2轉換好的pb模型會報下面的錯誤：
使用mobilenetv2的解決辦法:
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())
調用Inception的deeplabv3
接下來使用opencv加載xception轉換好的pb模型
使用xception的解決辦法
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' # 起始地節點
# out_node = 'logits/semantic/BiasAdd' # 結束的節點
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進行推理(我用的是ADE20K預訓練模型進行測試的)
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()
# 讀取圖檔
frame = cv2.imread("1.jpg")
frameHeight = frame.shape[0]
frameWidth = frame.shape[1]
# 加載模型
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()
福利：免費送30課時OpenCV4 C++入門課程
掃碼即可開始觀看學習
因依老宿發心初
半學修心半讀書
推薦閱讀
OpenCV4系統化學習路線圖-視訊版本！
Tensorflow + OpenCV4 安全帽檢測模型訓練與推理
彙總 | OpenCV DNN子產品中支援的分類網絡
OpenCV中支援的人臉檢測方法整理與彙總
詳解ENet | CPU可以實時的道路分割網絡
從Pytorch 的ONNX到OpenVINO中IR中間層
OpenCV 基于Inception模型圖像分類
OpenCV4.4 + YOLOv4 真的可以運作了…..