本文软硬件环境:
树莓派:3代 Model B V1.2,内存1GB
OS:Arch Linux ARM
在上一篇文章中,我写了在树莓派上用TensorFlow做的一个深度学习(图像识别)实验,但正如文中所说,50秒执行一次预测的实用性为0。因此,有必要采取一些措施来加快TensorFlow的执行速度,其中一个可行的方法就是“预热”(warm-up),把TensorFlow移植到树莓派上的作者Sam Abrahams已经比较详细地在GitHub上列出了性能测试的结果。依照作者的描述,我也测试了一下,看看那悲催的50秒时间能减少到多少秒。
『1』什么是预热(warm-up)
首先,本文还是对TensorFlow的Python图像分类程序 classify_image.py 来描述的。
预热就是指在真正执行一次预测之前,先执行若干次 Session.run() 方法,从而达到加快一次预测的执行速度的目的。
文章来源:http://www.codelast.com/
『2』代码修改
代码改起来其实很简单。为了能衡量程序运行时间,需要使用Python的time模块,因此在一开始需要import:
import time
然后对 run_inference_on_image 方法做一些修改,如下:
def run_inference_on_image(image):
"""Runs inference on an image.
Args:
image: Image file name.
Returns:
Nothing
"""
if not tf.gfile.Exists(image):
tf.logging.fatal('File does not exist %s', image)
image_data = tf.gfile.FastGFile(image, 'rb').read()
# the image used to warm-up TensorFlow model
warm_up_image_data = tf.gfile.FastGFile('/root/tensorflow-related/test-images/ubike.jpg', 'rb').read()
# Creates graph from saved GraphDef.
create_graph()
with tf.Session() as sess:
# Some useful tensors:
# 'softmax:0': A tensor containing the normalized prediction across
# 1000 labels.
# 'pool_3:0': A tensor containing the next-to-last layer containing 2048
# float description of the image.
# 'DecodeJpeg/contents:0': A tensor containing a string providing JPEG
# encoding of the image.
# Runs the softmax tensor by feeding the image_data as input to the graph.
softmax_tensor = sess.graph.get_tensor_by_name('softmax:0')
print("Warm-up start")
for i in range(10):
print("Warm-up for time {}".format(i))
predictions = sess.run(softmax_tensor,
{'DecodeJpeg/contents:0': warm_up_image_data})
print("Warm-up finished")
# record the start time of the actual prediction
start_time = time.time()
predictions = sess.run(softmax_tensor,
{'DecodeJpeg/contents:0': image_data})
predictions = np.squeeze(predictions)
# Creates node ID --> English string lookup.
node_lookup = NodeLookup()
top_k = predictions.argsort()[-FLAGS.num_top_predictions:][::-1]
for node_id in top_k:
human_string = node_lookup.id_to_string(node_id)
score = predictions[node_id]
print('%s (score = %.5f)' % (human_string, score))
print("Prediction used time:{} S".format(time.time() - start_time))
其中,我们自己添加的代码有如下几部分:
# the image used to warm-up TensorFlow model
warm_up_image_data = tf.gfile.FastGFile('/root/tensorflow-related/test-images/ubike.jpg', 'rb').read()
这里使用了另外一张图片来预热模型(和真正预测时使用的不是同一张图片),为了简单写死了路径。
print("Warm-up start")
for i in range(10):
print("Warm-up for time {}".format(i))
predictions = sess.run(softmax_tensor,
{'DecodeJpeg/contents:0': warm_up_image_data})
print("Warm-up finished")
这里循环10次来预热模型。
# record the start time of the actual prediction
start_time = time.time()
# (中间省略)
print("Prediction used time:{} S".format(time.time() - start_time))
这里打印出了真正预测一张图片的执行时间(秒数),这个时间就是我们真正需要关心的,看它能减少到多少秒。
文章来源:http://www.codelast.com/
『3』测试结果
执行和上一篇文章一样的命令,输出如下:
/usr/lib/python3.5/site-packages/tensorflow/python/ops/array_ops.py:1750: VisibleDeprecationWarning: converting an array with ndim > 0 to an index will result in an error in the futureresult_shape.insert(dim, 1)Warm-up startWarm-up for time 0W tensorflow/core/framework/op_def_util.cc:332] Op BatchNormWithGlobalNormalization is deprecated. It will cease to work in GraphDef version 9. Use tf.nn.batch_normalization().Warm-up for time 1Warm-up for time 2Warm-up for time 3Warm-up for time 4Warm-up for time 5Warm-up for time 6Warm-up for time 7Warm-up for time 8Warm-up for time 9Warm-up finishedmountain bike, all-terrain bike, off-roader (score = 0.56671)tricycle, trike, velocipede (score = 0.12035)bicycle-built-for-two, tandem bicycle, tandem (score = 0.08768)lawn mower, mower (score = 0.00651)alp (score = 0.00387)Prediction used time:4.141446590423584 Seconds
可见:在10次预热之后,一次预测消耗的时间是 4.14 秒,虽然4秒多还是没有达到我们心目中的理想速度,但这已经比之前的50秒强太多了。
此外,从测试结果我们可以体会到的是:预热(Session.run())的头几次特别慢,后面就快起来了,所以,预热次数太少是不行的。
文章来源:https://www.codelast.com/
➤➤ 版权声明 ➤➤
转载需注明出处:codelast.com
感谢关注我的微信公众号(微信扫一扫):