Inference time using of Tensorflow Object Detection

Question

I have deployed my object detection model to Google Kubernetes Engine. My model is trained using faster_rcnn_resnet101_pets configuration. The inference time of my model is very high (~10 seconds total time for prediction and ) even though I am using a Nvidia Tesla K80 GPU in my cluster node. I am using gRPC for getting predicitons from the model. The script for making prediciton requests is :

import argparse
import os
import time
import sys
import tensorflow as tf
from PIL import Image
import numpy as np
from grpc.beta import implementations
sys.path.append("..")
from object_detection.core.standard_fields import \
    DetectionResultFields as dt_fields
from object_detection.utils import label_map_util
from argparse import RawTextHelpFormatter
from tensorflow_serving.apis import predict_pb2
from tensorflow_serving.apis import prediction_service_pb2_grpc


tf.logging.set_verbosity(tf.logging.INFO)

WIDTH = 1024
HEIGHT = 768


def load_image_into_numpy_array(input_image):
    image = Image.open(input_image)
    image = image.resize((WIDTH, HEIGHT), Image.ANTIALIAS)
    (im_width, im_height) = image.size
    image_arr = np.array(image.getdata()).reshape(
        (im_height, im_width, 3)).astype(np.uint8)
    image.close()
    return image_arr


def load_input_tensor(input_image):

    image_np = load_image_into_numpy_array(input_image)
    image_np_expanded = np.expand_dims(image_np, axis=0).astype(np.uint8)
    tensor = tf.contrib.util.make_tensor_proto(image_np_expanded)
    return tensor


def main(args):
    start_main = time.time()

    host, port = args.server.split(':')

    channel = implementations.insecure_channel(host, int(port))._channel

    stub = prediction_service_pb2_grpc.PredictionServiceStub(channel)
    request = predict_pb2.PredictRequest()
    request.model_spec.name = args.model_name

    input_tensor = load_input_tensor(args.input_image)
    request.inputs['inputs'].CopyFrom(input_tensor)
    start = time.time()

    result = stub.Predict(request, 60.0)
    end = time.time()

    output_dict = {}

    output_dict[dt_fields.detection_classes] = np.squeeze(
        result.outputs[dt_fields.detection_classes].float_val).astype(np.uint8)
    output_dict[dt_fields.detection_boxes] = np.reshape(
        result.outputs[dt_fields.detection_boxes].float_val, (-1, 4))
    output_dict[dt_fields.detection_scores] = np.squeeze(
        result.outputs[dt_fields.detection_scores].float_val)
    category_index = label_map_util.create_category_index_from_labelmap(args.label_map,
                                                                        use_display_name=True)
    classes = output_dict[dt_fields.detection_classes]
    scores = output_dict[dt_fields.detection_scores]
    classes.shape = (1, 300)
    scores.shape = (1, 300)
    print("prediction time : " + str(end-start))
    objects = []

    threshold = 0.5  # in order to get higher percentages you need to lower this number; usually at 0.01 you get 100% predicted objects
    for index, value in enumerate(classes[0]):
        object_dict = {}
        if scores[0, index] > threshold:
            object_dict[(category_index.get(value)).get('name').encode('utf8')] = \
                scores[0, index]
            objects.append(object_dict)
    print(objects)
    end_main = time.time()

    print("Overall Time : " + str(end_main-start_main))


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description="Object detection grpc client.",
                                     formatter_class=RawTextHelpFormatter)
    parser.add_argument('--server',
                        type=str,
                        default='localhost:9000',
                        help='PredictionService host:port')
    parser.add_argument('--model_name',
                        type=str,
                        default="my-model",
                        help='Name of the model')
    parser.add_argument('--input_image',
                        type=str,
                        default='./test_images/123.jpg',
                        help='Path to input image')
    parser.add_argument('--output_directory',
                        type=str,
                        default='./',
                        help='Path to output directory')
    parser.add_argument('--label_map',
                        type=str,
                        default="./data/object_detection.pbtxt",
                        help='Path to label map file')

    args = parser.parse_args()
    main(args)

I have used kubectl port forwarding for testing purposes so the request port is set to localhost:9000.

The output is :

prediction time : 6.690936326980591
[{b'goi_logo': 0.9999970197677612}]
Overall Time : 10.25893259048462

我该怎么做才能加快推理速度？我已经看到推理时间约为毫秒，因此相比之下10秒钟的持续时间非常长，不适合生产环境。我了解端口转发速度很慢。我可以使用的另一种方法是什么？我需要将此客户端作为API端点提供给全世界。

Answer 1

正如前面的答案所述，您确实应该尝试执行多个请求，因为 tf-serving 第一次需要一些开销。您可以通过使用预热脚本来防止这种情况。

要添加一些额外的选项：

• 从 tf-serving v1.8 开始，您还可以使用 http Rest API 服务。然后，您可以从 Google 计算引擎调用您在 GKE 上创建的服务，以减少连接延迟。就我而言，它的速度有了很大的提高，因为我的本地连接充其量只是平庸。除了更易于调试的 http Rest api 之外，您还可以发送更大的请求。grpc 的限制似乎是 1.5 mb，而 http 的限制要高得多。

• 您正在发送 b64 编码的图像吗？发送图像本身比发送 b64 编码字符串慢很多。我处理此问题的方法是从图像发送 b64 编码的字符串，并在网络前面创建一些额外的层，将字符串再次转换为 jpeg 图像，然后通过模型对其进行处理。一些可以帮助您的代码：

from keras.applications.inception_v3 import InceptionV3, preprocess_input
from keras.models import Model
import numpy as np
import cv2
import tensorflow as tf
from keras.layers import Input, Lambda
from keras import backend as K

base_model = InceptionV3(
                weights='imagenet',
                include_top=True)

model = Model(
    inputs=base_model.input,
    outputs=base_model.get_layer('avg_pool').output)



def prepare_image(image_str_tensor):
            #image = tf.squeeze(tf.cast(image_str_tensor, tf.string), axis=[0])
            image_str_tensor = tf.cast(image_str_tensor, tf.string)
            image = tf.image.decode_jpeg(image_str_tensor,
                                        channels=3)
            #image = tf.divide(image, 255)
            #image = tf.expand_dims(image, 0)
            image = tf.image.convert_image_dtype(image, tf.float32)
            return image

def prepare_image_batch(image_str_tensor):
    return tf.map_fn(prepare_image, image_str_tensor, dtype=tf.float32)

# IF BYTE STR

model.layers.pop(0)
print(model.layers[0])

input_img = Input(dtype= tf.string,
            name ='string_input',
            shape = ()
            )
outputs = Lambda(prepare_image_batch)(input_img)
outputs = model(outputs)
inception_model = Model(input_img, outputs)
inception_model.compile(optimizer = "sgd", loss='categorical_crossentropy')
weights = inception_model.get_weights()

• 接下来，我会说使用更大的 GPU。我现在在 P100 上运行基本的 yolo（keras 实现），当从计算引擎调用时，延迟约为 0.4 秒。我们注意到，darknet 实现（用 C++ 实现）比 keras 实现快得多。