def _getgraph(self):
inferenceModel = hiai.AIModelDescription('matmul', self.model_path)
# init Graph
self.graph = self.model.CreateGraph(inferenceModel, self.graph_id,
self.model_engine_id)
if self.graph is None:
print("Init Graph failed")
def CreateGraph(self):
'''
Create graph
Returns:
graph
'''
path, filename = os.path.split(self.model_path)
nntensorlist_object = hiai.NNTensorList()
id = random.randint(1, 2**32 - 1)
graph = hiai.Graph(hiai.GraphConfig(graph_id=id))
with graph.as_default():
engine = hiai.Engine()
#resize_config = hiai.ResizeConfig(resize_width=300, resize_height = 300)
#nntensorlist_object = engine.resize(input_tensor_list=nntensorlist_object, config=resize_config)
ai_model_desc = hiai.AIModelDescription(name=filename,
path=self.model_path)
ai_config = hiai.AIConfig(
hiai.AIConfigItem("Inference", "item_value_2"))
final_result = engine.inference(
input_tensor_list=nntensorlist_object,
ai_model=ai_model_desc,
ai_config=ai_config)
ret = copy.deepcopy(graph.create_graph())
if ret != hiai.HiaiPythonStatust.HIAI_PYTHON_OK:
graph.destroy()
raise Exception("create graph failed, ret ", ret)
print("create graph successful")
return graph
def create_graph_with_dvpp(self, resize_cfg):
'''
Create graph with dvpp
Args:
resize_cfg: resize parameter, (resize_w, resize_h)
resize_w: width of the destination resolution
resize_h: height of the destination resolution
Returns:
graph: a graph configured with dvpp
Raises:
Exception("[create_graph_with_dvpp]: create graph failed, ret ", ret)
'''
nntensorlist_object =hiai.NNTensorList()
graph = hiai.Graph(hiai.GraphConfig(graph_id=65530))
with graph.as_default():
engine = hiai.Engine()
resize_config = hiai.ResizeConfig(resize_width=resize_cfg[0], resize_height = resize_cfg[1])
nntensorlist_object = engine.resize(input_tensor_list=nntensorlist_object, config=resize_config)
ai_model_desc = hiai.AIModelDescription(name=os.path.basename(self.model_path), path=self.model_path)
ai_config = hiai.AIConfig(hiai.AIConfigItem("Inference", "item_value_2"))
final_result = engine.inference(input_tensor_list=nntensorlist_object,
ai_model=ai_model_desc,
ai_config=ai_config)
ret = copy.deepcopy(graph.create_graph())
if ret != hiai.HiaiPythonStatust.HIAI_PYTHON_OK:
graph.destroy()
raise Exception("[create_graph_with_dvpp]: create graph failed, ret ", ret)
print("[create_graph_with_dvpp]: create graph successful")
return graph
def _getgraph(self):
# 描述推理模型
inferenceModel = hiai.AIModelDescription('face_detection', face_detection_model_path)
# 初始化Graph
self.graph = self.model.CreateGraph(inferenceModel,self.graph_id,self.model_engine_id)
if self.graph is None:
print "Init Graph failed"
def CreateGraph(self):
'''
Create graph
Returns:
graph
'''
nntensorlist_object = hiai.NNTensorList()
graph = hiai.Graph(hiai.GraphConfig(graph_id=65530))
with graph.as_default():
engine = hiai.Engine()
print(self.model_path, os.path.basename(self.model_path))
ai_model_desc = hiai.AIModelDescription(
name=os.path.basename(
self.model_path), path=self.model_path)
ai_config = hiai.AIConfig(
hiai.AIConfigItem(
"Inference", "item_value_2"))
final_result = engine.inference(
input_tensor_list=nntensorlist_object,
ai_model=ai_model_desc,
ai_config=ai_config)
ret = copy.deepcopy(graph.create_graph())
if ret != hiai.HiaiPythonStatust.HIAI_PYTHON_OK:
graph.destroy()
raise Exception("create graph failed, ret ", ret)
print("create graph successful")
return graph
def _getgraph(self):
# 描述推理模型
DescriptionInferenceModel = hiai.AIModelDescription(
'crowd_counting', crowd_counting_model_path)
# 初始化Graph
self.graph = self.model.CreateGraph(DescriptionInferenceModel)
if self.graph is None:
print("Init Graph failed")
def _getgraph(self):
# 描述推理模型
inferenceModel = hiai.AIModelDescription('Yolo3_Resnet18',
yolo3_resnet18_model_path)
# 初始化Graph
self.graph = self.model.CreateGraph(inferenceModel, self.graph_id,
self.model_engine_id)
if self.graph is None:
print("Init Graph failed")
def main():
inferenceModel = hiai.AIModelDescription('ShadowGAN', omModelName)
myGraph = CreateGraph(inferenceModel)
if myGraph is None:
exit(0)
if not osp.exists(outputDir):
os.makedirs(outputDir)
# Read images and corresponding masks
inputImage = ReadImage(osp.join(testDataDir, 'noshadow', 'demo.jpg'),
channels=3)
if inputImage is None:
print("[ERROR] No input image.")
DestroyGraph()
exit(0)
inputMask = ReadImage(osp.join(testDataDir, 'mask', 'demo.jpg'),
channels=1)
if inputMask is None:
print("[ERROR] No input mask.")
DestroyGraph()
exit(0)
# Normalize to [-1.0, 1.0]
inputImage = inputImage / 127.5 - 1.0
inputMask = 1.0 - inputMask / 127.5
# Convert HWC format to CHW
# Note: hiai.NNTensor() only takes NCHW data as input.
# [https://ascend.huawei.com/doc/Atlas200DK/1.3.0.0/zh/zh-cn_topic_0161025273.html]
inputImage = inputImage.transpose([2, 0, 1]).copy()
inputMask = inputMask.transpose([2, 0, 1]).copy()
inputImageTensor = hiai.NNTensor(inputImage, inputWidth, inputHeight, 3,
'input_image', DataType.FLOAT32_T,
inputWidth * inputHeight * 3)
inputMaskTensor = hiai.NNTensor(inputMask, inputWidth, inputHeight, 1,
'input_mask', DataType.FLOAT32_T,
inputWidth * inputHeight * 1)
nntensorList = hiai.NNTensorList([inputImageTensor, inputMaskTensor])
print("Inference start...")
startTime = time.time()
resultList = GraphInference(myGraph, nntensorList)
if resultList is None:
print("[ERROR] Inference failed.")
DestroyGraph()
exit(0)
endTime = time.time()
inferenceTime = endTime - startTime
SaveResult(resultList, 'demo.jpg')
DestroyGraph()
print("Inference finished. Inference time: %.3fms" %
(inferenceTime * 1000))
def main():
inferenceModel = hiai.AIModelDescription('faster-rcnn', omFileName)
print omFileName
print inferenceModel
# we will resize the jpeg to 896*608 to meet faster-rcnn requirement via opencv,
# so DVPP resizing is not needed
myGraph = CreateGraphWithoutDVPP(inferenceModel)
if myGraph is None:
print "CreateGraph failed"
return None
# in this sample demo, the faster-rcnn model requires 896*608 images
dvppInWidth = 896
dvppInHeight = 608
start = time.time()
index = 0
pathDir = os.listdir(srcFileDir)
for allDir in pathDir:
child = os.path.join('%s%s' % (srcFileDir, allDir))
if (not jpegHandler.is_img(child)):
print '[info] file : ' + child + ' is not image !'
continue
# read the jpeg file and resize it to required w&h, than change it to YUV format.
input_image = jpegHandler.jpeg2yuv(child, dvppInWidth, dvppInHeight)
inputImageTensor = hiai.NNTensor(input_image, dvppInWidth,
dvppInHeight, 3, 'testImage',
DataType.UINT8_T,
dvppInWidth * dvppInHeight * 3 / 2)
imageinfo = np.array([896, 608, 3]).astype(np.float32)
imageinfo = np.reshape(imageinfo, (1, 3))
infoTensor = hiai.NNTensor(imageinfo, 1, 3, 1, 'testinfo',
DataType.FLOAT32_T, imageinfo.size)
datalist = [inputImageTensor, infoTensor]
nntensorList = hiai.NNTensorList(datalist)
if not nntensorList:
print "nntensorList is null"
break
resultList = GraphInference(myGraph, nntensorList)
if resultList is None:
print "graph inference failed"
continue
print resultList[1].shape
PostProcess(resultList, dstFileDir, child)
end = time.time()
print 'cost time ' + str((end - start) * 1000) + 'ms'
hiai.hiai._global_default_graph_stack.get_default_graph().destroy()
print '-------------------end'
def main():
inferenceModel = hiai.AIModelDescription('restnet18', resnet18OmFileName)
# we will resize the jpeg to 256*224 to meet resnet18 requirement via opencv,
# so DVPP resizing is not needed
myGraph = CreateGraphWithoutDVPP(inferenceModel)
if myGraph is None:
print "CreateGraph failed"
return None
# in this sample demo, the resnet18 model requires 256*224 images
dvppInWidth = 42
dvppInHeight = 42
start = time.time()
jpegHandler.mkdirown(dstFileDir)
pathDir = os.listdir(srcFileDir)
for allDir in pathDir:
child = os.path.join('%s%s' % (srcFileDir, allDir))
if (not jpegHandler.is_img(child)):
print '[info] file : ' + child + ' is not image !'
continue
# read the jpeg file and resize it to required w&h, than change it to YUV format.
input_image = jpegHandler.jpeg2yuv(child, dvppInWidth, dvppInHeight)
inputImageTensor = hiai.NNTensor(input_image, dvppInWidth,
dvppInHeight, 3, 'testImage',
DataType.UINT8_T,
dvppInWidth * dvppInHeight)
nntensorList = hiai.NNTensorList(inputImageTensor)
resultList = GraphInference(myGraph, nntensorList)
if resultList is None:
print "graph inference failed"
continue
Resnet18PostProcess(resultList, srcFileDir, dstFileDir, allDir)
end = time.time()
print 'cost time ' + str((end - start) * 1000) + 'ms'
hiai.hiai._global_default_graph_stack.get_default_graph().destroy()
print '-------------------end'
def ExcuteInference(self, images):
result = []
for i in range(0, len(images)):
nArray = Yuv2Array(images[i])
ssd = {"name": "face_detection", "path": self.modelPath}
nntensor = hiai.NNTensor(nArray)
tensorList = hiai.NNTensorList(nntensor)
if self.first == True:
self.graph = hiai.Graph(hiai.GraphConfig(graph_id=2001))
with self.graph.as_default():
self.engine_config = hiai.EngineConfig(
engine_name="HIAIDvppInferenceEngine",
side=hiai.HiaiPythonSide.Device,
internal_so_name='/lib/libhiai_python_device2.7.so',
engine_id=2001)
self.engine = hiai.Engine(self.engine_config)
self.ai_model_desc = hiai.AIModelDescription(
name=ssd['name'], path=ssd['path'])
self.ai_config = hiai.AIConfig(
hiai.AIConfigItem("Inference", "item_value_2"))
final_result = self.engine.inference(
input_tensor_list=tensorList,
ai_model=self.ai_model_desc,
ai_config=self.ai_config)
ret = copy.deepcopy(self.graph.create_graph())
if ret != hiai.HiaiPythonStatust.HIAI_PYTHON_OK:
print("create graph failed, ret", ret)
d_ret = graph.destroy()
SetExitFlag(True)
return HIAI_APP_ERROR, None
self.first = False
else:
with self.graph.as_default():
final_result = self.engine.inference(
input_tensor_list=tensorList,
ai_model=self.ai_model_desc,
ai_config=self.ai_config)
resTensorList = self.graph.proc(input_nntensorlist=tensorList)
print("Inference result: ", resTensorList[0].shape)
result.append(resTensorList)
return HIAI_APP_OK, result
def main():
print "Start get data set"
# 输入音频为pcm格式，即直接读取开发板录制的pcm格式音频，如输入音频为wav格式，请使用下行代码
#Input_tensor, in_len = GetDataSet(speech_voice_path)
# 输入音频为wav格式，如输入音频为pcm，请注释上述代码
Input_tensor, in_len = GetDataSet2(speech_voice_path2)
# 判断Input_data是否正确获取
if (Input_tensor == None):
print 'Get input data failed'
# 加载语音识别的声学模型
print "Start load speech model"
inferenceModel = hiai.AIModelDescription('asr', speech_recog_model)
if inferenceModel is None:
print 'Load model failed'
return None
# 初始化Graph
print "Start init Graph"
myGraph = CreateGraph(inferenceModel)
# 开始模型推理
print "Start inference"
resultList = GraphInference(myGraph, Input_tensor)
list_shape = np.array(resultList).shape
if resultList is None:
print "Inference failed"
# 对结果进行后处理
final_result = SpeechPostProcess(resultList, in_len)
print '文本识别结果： ' + str(final_result)
hiai.hiai._global_default_graph_stack.get_default_graph().destroy()
print 'Speech Recognizition Finished !'
def main():
inferenceModel = hiai.AIModelDescription('segmentationDes', OmFileName)
myGraph = CreateGraph(inferenceModel)
if myGraph is None:
print("CreateGraph failed")
return None
start = time.time()
jpegHandler.mkdirown(dstFileDir)
pathDir = os.listdir(srcFileDir)
label_colours = cv.imread(colours, 1).astype(np.uint8)
#print label_colours
label_colours_bgr = label_colours[..., ::-1]
for allDir in pathDir:
child = os.path.join('%s%s' % (srcFileDir, allDir))
if (not jpegHandler.is_img(child)):
print('[info] file : ' + child + ' is not image !')
continue
print('[info] file : ' + child + ' begin process !')
# read the jpeg file and resize it to required w&h, than change it to YUV format.
input_image = jpegHandler.jpeg2yuv(child, InWidth, InHeight)
inputImageTensor = hiai.NNTensor(input_image, InWidth, InHeight, 3,
'testImage', DataType.UINT8_T,
InWidth * InHeight * 3 / 2)
nntensorList = hiai.NNTensorList(inputImageTensor)
resultList = GraphInference(myGraph, nntensorList)
if resultList is None:
print(child + "graph inference failed")
continue
resultArray = resultList[0]
resultArray = resultArray.reshape(19, InWidth, InHeight)
prediction = resultArray.argmax(axis=0)
#print prediction
prediction = np.squeeze(prediction)
prediction = np.resize(prediction, (3, InHeight, InWidth))
prediction = prediction.transpose(1, 2, 0).astype(np.uint8)
prediction_rgb = np.zeros(prediction.shape, dtype=np.uint8)
cv.LUT(prediction, label_colours_bgr, prediction_rgb)
input_path_ext = child.split(".")[-1]
input_image_name = child.split("/")[-1:][0].replace(
'.' + input_path_ext, '')
out_path_im = dstFileDir + input_image_name + '_erfnet' + '.' + input_path_ext
cv.imwrite(out_path_im,
prediction_rgb) # color images for visualization
print(input_image_name + ' process end ')
end = time.time()
print('cost time ' + str((end - start) * 1000) + 'ms')
hiai.hiai._global_default_graph_stack.get_default_graph().destroy()
print('-------------------end')
def _getgraph(self):
inferenceModel = hiai.AIModelDescription('faster_rcnn', detection_model_path)
#print inferenceModel
self.graph = self.model.CreateGraphWithoutDVPP(inferenceModel)
if self.graph is None:
print "CreateGraph failed"
def ExcuteInference(self, images):
result = []
for i in range(0, len(images)):
nArray = Yuv2Array(images[i])
ssd = {"name": "object_detection", "path": self.modelPath}
nntensor = hiai.NNTensor(nArray)
'''
gray = cv2.cvtColor(nArray, cv2.COLOR_YUV2GRAY_420)
blurred = cv2.GaussianBlur(gray, (5, 5), 0)
thresh = cv2.threshold(blurred, 60, 255, cv2.THRESH_BINARY)[1]
cnts = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
cnts=cnts[0]
#print("1111111")
j=0
for c in cnts:
M = cv2.moments(c)
c = c.astype("float")
c = c.astype("int")
shape = detect(c)
# cv2.drawContours(cv_image, [c], -1, (0, 255, 0), 2)
# image=cv2.cvtColor(cv_image, cv2.COLOR_YUV2RGB_I420)
# picpath='~/sample-objectdetection-python/picpath'+str(i)+'.jpg'
# cv2.imwrite(picpath,image)
# print("111111")
#BGR=cv2.cvtColor(nArray,cv2.COLOR_YUV2RGB)
#return BGR
# print(cv123_image)
# img_np = YUVtoRGB(nArray)
# cv2.imwrite("text4.jpg",img_np)
'''
tensorList = hiai.NNTensorList(nntensor)
if self.first == True:
self.graph = hiai.Graph(hiai.GraphConfig(graph_id=2001))
with self.graph.as_default():
self.engine_config = hiai.EngineConfig(
engine_name="HIAIDvppInferenceEngine",
side=hiai.HiaiPythonSide.Device,
internal_so_name='/lib/libhiai_python_device2.7.so',
engine_id=2001)
self.engine = hiai.Engine(self.engine_config)
self.ai_model_desc = hiai.AIModelDescription(
name=ssd['name'], path=ssd['path'])
self.ai_config = hiai.AIConfig(
hiai.AIConfigItem("Inference", "item_value_2"))
final_result = self.engine.inference(
input_tensor_list=tensorList,
ai_model=self.ai_model_desc,
ai_config=self.ai_config)
ret = copy.deepcopy(self.graph.create_graph())
if ret != hiai.HiaiPythonStatust.HIAI_PYTHON_OK:
print("create graph failed, ret", ret)
d_ret = graph.destroy()
SetExitFlag(True)
return HIAI_APP_ERROR, None
self.first = False
else:
with self.graph.as_default():
final_result = self.engine.inference(
input_tensor_list=tensorList,
ai_model=self.ai_model_desc,
ai_config=self.ai_config)
resTensorList = self.graph.proc(input_nntensorlist=tensorList)
# print("Inference result: ", resTensorList[0].shape)
result.append(resTensorList)
return HIAI_APP_OK, result