-
Notifications
You must be signed in to change notification settings - Fork 474
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
定点量化技术 #78
定点量化技术 #78
Conversation
辛苦啦哈哈 |
校对认领 |
performance/quantization.md
Outdated
priority has been improving accuracy and speed during training. Using floating | ||
point arithmetic is an easy way to preserve accuracy and GPUs are designed to | ||
accelerate these calculations. | ||
由于现代神经网络的挑战之一是进行高精度的优化,其优先级已改善了训练期的精度和速度。使用浮点数运算是保持精度的简单方法之一,同时 GPU 也被设计为能为这些运算进行加速。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
『其优先级已改善了训练期的精度和速度』=>『首先要做的是改善训练期的精度和速度』
performance/quantization.md
Outdated
for *training* grows with the amount of models trained on different | ||
architectures, the computational demand for *inference* grows in proportion to | ||
the amount of users. | ||
然而,随着越来越多的机器学习模型需要被部署到移动设备上,推理的效率已经成为了一个关键性问题。训练期计算的需求随着不同训练模型的数量的增加而迅速增长,对于推理的计算需求也随着用户数量的增加而成比例的增加。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
『训练期计算的需求随着不同训练模型的数量的增加而迅速增长,对于推理的计算需求也随着用户数量的增加而成比例的增加。』=>『对于训练期的计算需求,随着在不同架构上训练的模型的数量增加而迅速增长;对于推理的计算需求,也随着用户数量的增加而成比例的增加。』
performance/quantization.md
Outdated
AlexNet requires over 200 MB for the float format—almost all of that for the | ||
model's millions of weights. Because the weights are slightly different | ||
floating point numbers, simple compression formats perform poorly (like zip). | ||
神经网络的模型需要消耗大量的磁盘空间。举个例子,原始的 AlexNet 需要至少 200MB 的空间来存储浮点格式的模型文件——几乎全部用于模型的百万权重。在权重间只有细微差异的表示中,简单的压缩格式效果不佳(如 Zip)。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
『原始的 AlexNet 需要至少 200MB 的空间来存储浮点格式的模型文件——几乎全部用于模型的百万权重』=>『原始的 AlexNet 需要至少 200 MB 的空间来存储浮点格式的模型文件 —— 几乎全部用于模型数百万的权重』
performance/quantization.md
Outdated
storing the minimum and maximum weight for each layer, then compress each | ||
weight's float value to an 8-bit integer representing the closest real number in | ||
a linear set of 256 within the range. | ||
权重在所有层中都以数值形式出现。对每一层而言,权重倾向于分布在一定范围内。量化技术则可以通过存储每层中的最大和最小的权重,然后压缩每层权重的浮点值转换为表示最接近真实实数的 8 位整数,从而达到压缩未文件大小的目的。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
『从而达到压缩未文件大小的目的。』=>『从而达到压缩文件大小的目的。』
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
『a linear set of 256 within the range.』漏译
performance/quantization.md
Outdated
a forward pass and a backward pass, while inference only uses a forward pass. | ||
When we train the model with quantization in the loop, we ensure that the forward | ||
pass matches precision for both training and inference. | ||
我们的目标要在训练和推断期间内使用相同的精度来使用权重和激活值,但是一个相当重要的区别是在前向和后向传播中,推断值使用了前向过程。所以当我们训练模型期间同时加入量化,就要确保前向过程的训练和推理的精度。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
『我们的目标要在训练和推断期间内使用相同的精度来使用权重和激活值,但是一个相当重要的区别是在前向和后向传播中,推断值使用了前向过程。所以当我们训练模型期间同时加入量化,就要确保前向过程的训练和推理的精度。』=>『我们的目标是要在训练和推断期间内,对于权重和激活值使用相同的精度,但是一个相当重要的区别是在前向和后向传播中,推断只使用了前向过程。所以当我们训练模型期间同时加入量化,就要确保前向过程的训练和推理的精度相匹配。』
performance/quantization.md
Outdated
and experimentation. Although rewrites and quantized training might not work or | ||
improve performance for all models, we are working to generalize these | ||
techniques. | ||
重写训练和评估图的方法是一个活跃的研究和实验领域。 尽管重写和量化训练可能无法奏效或者不能提高所有模型的性能,但我们正在努力推广这些技术。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
尽管前多了空格
@luochen1992 @leviding 修改完毕 |
resolve #58
@leviding 最诚挚的歉意……