本文将介绍基于OpenVINO的异步推理队列类 AyncInferQueue，启动多个(＞2)推理请求(infer request)，在硬件投入不变的情况下，进一步提升 AI 推理程序的吞吐量(Throughput)。
OpenVINO运行时(Runtime)用推理请求(infer request)来抽象在指定计算设备上运行已编译模型(Compiled_Model)。从编写程序的角度看，推理请求是一个类，封装了支持推理请求以同步或异步方式运行的属性和方法
OpenVINO运行时(Runtime)提供 AsyncInferQueue 类来抽象并管理异步推理请求池，其常用方法和属性有：
- init(self, compiled_model, jobs = 0)：创建AsyncInferQueue对象
- set_callback(func_name)：为推理请求池中所有的推理请求设置统一的回调函数
- start_async(inputs, userdata = None)：异步启动推理请求
- wait_all()：等待所有的推理请求执行完毕
基于 AsyncInferQueue 类 YOLOv5 模型的异步推理范例程序: yolov5_async_infer_queue.py
...
def preprocess(frame):
# Preprocess the frame
letterbox_im, _, _= letterbox(frame, auto=False) # preprocess frame by letterbox
im = letterbox_im.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
im = np.float32(im) / 255.0 # 0 - 255 to 0.0 - 1.0
blob = im[None] # expand for batch dim
return blob, letterbox_im.shape[:-1], frame.shape[:-1]
def postprocess(ireq: InferRequest, user_data: tuple):
result = ireq.results[ireq.model_outputs[0]]
dets = non_max_suppression(torch.tensor(result))[0].numpy()
bboxes, scores, class_ids= dets[:,:4], dets[:,4], dets[:,5]
# rescale the coordinates
bboxes = scale_coords(user_data[1], bboxes, user_data[2]).astype(int)
print(user_data[0],"\t"+f"{ireq.latency:.3f}"+"\t", class_ids)
return
# Step1：Initialize OpenVINO Runtime Core
core = Core()
# Step2: Build compiled model
device = device = ['GPU.0', 'GPU.1', 'CPU', 'AUTO', 'AUTO:GPU,-CPU'][0]
cfgs = {}
cfgs['PERFORMANCE_HINT'] = ['THROUGHPUT', 'LATENCY', 'CUMULATIVE_THROUGHPUT'][0]
net = core.compile_model("yolov5s.xml",device,cfgs)
output_node = net.outputs[0]
b,n,input_h,input_w = net.inputs[0].shape
# Step3: Initialize InferQueue
ireqs = AsyncInferQueue(net)
print('Number of infer requests in InferQueue:', len(ireqs))
# Step3.1: Set unified callback on all InferRequests from queue's pool
ireqs.set_callback(postprocess)
# Step4: Read the images
image_folder = "./data/images/"
image_files= os.listdir(image_folder)
print(image_files)
frames = []
for image_file in image_files:
frame = cv2.imread(os.path.join(image_folder, image_file))
frames.append(frame)
# 4.1 Warm up
for id, _ in enumerate(ireqs):
# Preprocess the frame
start = perf_counter()
blob, letterbox_shape, frame_shape = preprocess(frames[id % 4])
end = perf_counter()
print(f"Preprocess {id}: {(end-start):.4f}.")
# Run asynchronous inference using the next available InferRequest from the pool
ireqs.start_async({0:blob},(id, letterbox_shape, frame_shape))
ireqs.wait_all()
# Step5: Benchmark the Async Infer
start = perf_counter()
in_fly = set()
latencies = []
niter = 16
for i in range(niter):
# Preprocess the frame
blob, letterbox_shape, frame_shape = preprocess(frames[i % 4])
idle_id = ireqs.get_idle_request_id()
if idle_id in in_fly:
latencies.append(ireqs[idle_id].latency)
else:
in_fly.add(idle_id)
# Run asynchronous inference using the next available InferRequest from the pool
ireqs.start_async({0:blob},(i, letterbox_shape, frame_shape) )
ireqs.wait_all()
在蝰蛇峡谷NUC上运行结果：
结论：使用 OpenVINO™ Runtime 的 AsyncInferQueue 类，可以极大提升 AI 推理程序的吞出量。