其他分享
首页 > 其他分享> > 深度学习词汇 Developing Our Own Deep Learning Toolset

深度学习词汇 Developing Our Own Deep Learning Toolset

作者:互联网

pick up:挑出选出
a copy of :一本
configure配置
acount :账户
computer vision:机器视觉
utilizing:利用
image classification, object detection, training
networks on large-scale datasets, and much more.图像分类,目标检测,大规模数据集的训练网络,等等。
mxnet libraries: mxnet库
strives: 努力奋斗,争吵
theory taught in a classroom/textbook and the actual hands-on knowledge you’ll need to be
successful in the real world./;在课堂/教科书中教授的理论和实际的动手知识,你将需要在现实世界中取得成功。
leverage your newly gained knowledge :利用你新获得的知识
So grab your highlighter.:抓住你的荧光笔。
dissertation:n. 专题论文;学位论文
regulations, :条例,我
hang around" for before I could officially defend my dissertation and graduate:在我正式为我的论文辩护和毕业之前,先四处闲逛
semester :n. (尤指美国的大专院校的)学期;半学年
publications:publications出版物
Frustrated with my failed attempts at implementation对我在实施方面的失败尝试感到沮丧
tutorials,:辅导书
lightbulb:灯泡
perseverance. ;坚持不懈
between these two styles of learning, a gap that I want
to help fill so you can learn in a better, more efficient way在这两种学习方式之间,我想帮助填补一个空白,这样你就可以以更好、更有效的方式学习
proficient熟练
won’t get bogged down by tons of theory and complex equations不会被大量的理论和复杂的方程所困扰
demonstrate :演示
, including age + gender prediction, vehicle make + model
identification, facial expression recognition, and much more.:,包括年龄性别预测、车辆模型识别、面部表情识别等。
specializes in distributed, :专门从事分布式,
combined tighter create a powerful deep
learning development environment that you can use to master deep learning for visual recognition.:结合紧密,创造一个强大的深度学习开发环境,您可以用来掌握深度学习的视觉识别。
Think of a computational backend as an engine that runs in your car计算引擎。 把计算后端看作是在你的车里运行的引擎。
would be akin to utilizing strictly NumPy to build a machine learning classifier.神经网络类似于严格利用NumPy来构建机器学习分类器。
dedicated to machine learning, such as
scikit-learn [5], rather than reinvent the wheel with NumPy (and at the expense of an order of
magnitude more code).致力于机器学习,如Scikit学习[5],而不是用NumPy重新发明车轮(并以牺牲更多代码的数量级为代s integrate TensorFlow code directly into our Keras models if we so wish. In many ways, we
are getting the best of both worlds by using Keras.价)。如果我们愿意,可以直接将传感器流代码输入到我们的Keras模型中。 在许多方面,我们通过使用Keras获得了两个世界中最好的。
round out your knowledge总结你的知识
or write them to an optimized database
format.或者将它们写入优化的数据库格式。
Create a blueprint class that can be used to build our own custom implementations of
Convolutional Neural Networks.创建一个蓝图类,可用于构建我们自己的卷积神经网络自定义实现。
at our disposable在我们的一次性衣服上
modular libraries, and
unbridled, intelligent researchers, we’re seeing new publications that push the state-of-the-art
coming on a monthly basis.模块化库,和肆无忌惮的智能研究人员,我们看到新的出版物,推动最先进的基础上每月。
Don’t miss out on this time in history – not only should you be a part of deep learning, but
those who capitalize early are sure to see immenseadj. 极大的;巨大的 returns on their investment of time, resources,
and creativity.不要错过历史上的这一次——你不仅应该成为深度学习的一部分,而且那些早期投资的人肯定会看到他们在时间、资源和创造力方面的巨大回报。

标签:Own,Keras,Developing,学习,learning,Toolset,NumPy,your,more
来源: https://blog.csdn.net/qq_43543515/article/details/113536381