C# CNTK层上的Python操作
我不是python爱好者,我试图理解如何将一些python代码转换为C代码: 此代码是此处的一个片段: 我的问题是,C# CNTK层上的Python操作,c#,python,bit-manipulation,C#,Python,Bit Manipulation,我不是python爱好者,我试图理解如何将一些python代码转换为C代码: 此代码是此处的一个片段: 我的问题是,>操作员实际上在做什么 是一个层,那么层发生了什么?这里有什么奇想吗?我以前从未见过,但模型实例化似乎是答案: Example: >>> model = Dense(500) >> Activation(C.relu) >> Dense(10) >>> # is the same as >>> mo
>
操作员实际上在做什么
是一个层,那么层发生了什么?这里有什么奇想吗?我以前从未见过,但模型实例化似乎是答案:
Example:
>>> model = Dense(500) >> Activation(C.relu) >> Dense(10)
>>> # is the same as
>>> model = Dense(500) >> C.relu >> Dense(10)
>>> # and also the same as
>>> model = Dense(500, activation=C.relu) >> Dense(10)
发件人:
其中:
发件人:
特别是模型中的序列
Example:
>>> model = Dense(500) >> Activation(C.relu) >> Dense(10)
>>> # is the same as
>>> model = Dense(500) >> C.relu >> Dense(10)
>>> # and also the same as
>>> model = Dense(500, activation=C.relu) >> Dense(10)
Another example is a GRU layer with projection, which could be realized as
``Recurrence(GRU(500) >> Dense(200))``,
where the projection is applied to the hidden state as fed back to the next
step.
``F>>G`` is a short-hand for ``Sequential([F, G])``.