paddlepaddle实现gru

paddlepaddle实现gru

最近用用paddlepaddle实现了一下grucell，这里分享一下代码：

import paddleimport paddle.nn as nnimport paddle.nn.functional as Fclass GRUCell(nn.Layer): def __init__(self, input_size, hidden_size): super(GRUCell, self).__init__() # 输入单元的大小 self.input_size = input_size # 隐藏单元的大小 self.hidden_size = hidden_size # 输入单元映射的权重 weight_attr1 = paddle.ParamAttr(name="weight1",initializer=paddle.nn.initializer.Constant(value=0.5)) # 输入单元映射的偏置 bias_attr1= paddle.ParamAttr(name="bias1",initializer=paddle.nn.initializer.Constant(value=1.0)) # 隐藏单元映射的权重 weight_attr2 = paddle.ParamAttr(name="weight2",initializer=paddle.nn.initializer.Constant(value=0.5)) # 隐藏单元映射的偏置 bias_attr2 = paddle.ParamAttr(name="bias2",initializer=paddle.nn.initializer.Constant(value=1.0)) # 输入映射 w*x+b self.x2h = nn.Linear(input_size, 3 * hidden_size, weight_attr=weight_attr1,bias_attr=bias_attr1) # 隐藏映射 w*h+b self.h2h = nn.Linear(hidden_size, 3 * hidden_size, weight_attr=weight_attr2,bias_attr=bias_attr2) def forward(self, x, hidden): # 用全连接层给x乘上w，加上bias x_t = self.x2h(x) # 用全连接层给h_t乘上w，加上bias h_t = self.h2h(hidden) # 将输入x_t分割成3个子Tensor x_reset, x_update, x_new = x_t.chunk(3, 1) # 将输入h_t分割成3个子Tensor h_reset, h_update, h_new = h_t.chunk(3, 1) # 重置门 r_t = F.sigmoid(x_reset + h_reset) # 更新门 z_t = F.sigmoid(x_update + h_update) # 当前记忆内容 new_gate = F.tanh(x_new + (r_t * h_new)) # 当前时间步的最终记忆 h_t =(1-z_t)*hidden+z_t*new_gate return h_tif __name__=="__main__": model=GRUCell(16,16) x = paddle.randn((1, 16)) hidden=paddle.randn((1,16)) res=model(x,hidden) print(res)

如果有问题，可以和我交流哈。

参考文献

[1].https://github.com/georgeyiasemis/Recurrent-Neural-Networks-from-scratch-using-PyTorch/blob/main/rnncells.py

版权声明：本文内容由网络用户投稿，版权归原作者所有，本站不拥有其著作权，亦不承担相应法律责任。如果您发现本站中有涉嫌抄袭或描述失实的内容，请联系我们jiasou666@gmail.com 处理，核实后本网站将在24小时内删除侵权内容。