def main():
config = Config()
# 关系图中包括(include)哪些函数名。
#如果是某一类的函数，例如类gobang，则可以直接写'gobang.*'，表示以gobang.开头的所有函数。（利用正则表达式）。
config.trace_filter = GlobbingFilter(include=[
'main',
'pycallgraph.*',
'*.secret_function',
])
graphviz = GraphvizOutput()
graphviz.output_file = 'basic.png' #图片名称
with PyCallGraph(output=graphviz):
# coco
modelpath = "model/"
start = time.time()
pose_model = general_coco_model(modelpath) # 1.加载模型
print("[INFO]Pose Model loads time: ", time.time() - start)
# yolo
start = time.time()
_yolo = YOLO() # 1.加载模型
print("[INFO]yolo Model loads time: ", time.time() - start)
img_path = 'D:/myworkspace/dataset/My_test/img/a_img/airplane_30.jpg'
getImgInfo(img_path, pose_model, _yolo)
def _learning_hand(self, event):
start = time.time()
info, lineimage = getImgInfo(self.orgin_img_show, self.pose_model,
self._yolo, '')
self.XX_test.append(info)
self.tips.AppendText(u"特征提取耗时:{:.2f} s".format(time.time() - start) +
"\n")
lineimage = cv2.resize(
lineimage,
(600, 500),
)
height, width = lineimage.shape[:2]
image1 = cv2.cvtColor(
lineimage, cv2.COLOR_BGR2RGB
) # opencv中imread的图片内部是BGR排序，wxPython的StaticBitmap需要的图片是RGB排序，不转换会出现颜色变换
pic = wx.Bitmap.FromBuffer(width, height, image1)
# 显示图片在panel上：
self.result_img.SetBitmap(pic)
self.tips.AppendText(u"数字特征:" + str(info) + "\n")
# ----------------------------------------------------------------------------------
# 第二步 识别infolist
# ----------------------------------------------------------------------------------
# coco
modelpath = "model/"
start = time.time()
pose_model = general_coco_model(modelpath) # 1.加载模型
print("[INFO]Pose Model loads time: ", time.time() - start)
# yolo
start = time.time()
_yolo = YOLO() # 1.加载模型
print("[INFO]yolo Model loads time: ", time.time() - start)
infolist = []
for i in X:
hist = getImgInfo(i, pose_model, _yolo) # 识别
infolist.append(hist)
# ----------------------------------------------------------------------------------
# 第三步 存储信息docs/feature/features_all.csv
# ----------------------------------------------------------------------------------
# 路径存储到txt
orb = open('D:/myworkspace/dataset/My_test/bagofwords/y_train.txt', 'w')
for i, img_path in enumerate(X):
orb.write(img_path)
#orb.write('\n'+str(info)+str(infolist[i]))
orb.close()
# 特征存储到 csv
with open("docs/feature/features_all.csv", "w", newline="") as csvfile:
writer = csv.writer(csvfile)
from pose.coco import general_coco_model
# coco
modelpath = "model/"
start = time.time()
pose_model = general_coco_model(modelpath) # 1.加载模型
print("[INFO]Pose Model loads time: ", time.time() - start)
# yolo
start = time.time()
_yolo = YOLO() # 1.加载模型
print("[INFO]yolo Model loads time: ", time.time() - start)
path = "D:/myworkspace/JupyterNotebook/hand-keras-yolo3-recognize/docs/wangyu_hand_img/"
X_test = [path + "movehouse_37.jpg", path + "movehouse_65.jpg"]
# 测试集
XX_test = []
for i in X_test:
image = cv2.imread(i)
hist, _ = getImgInfo(image, pose_model, _yolo)
XX_test.append(hist)
clf = joblib.load("model/train_model.pkl")
predictions_labels = clf.predict(XX_test)
# 使用测试集预测结果
print(u'预测结果:')
print(predictions_labels)