Shulou(Shulou.com)06/01 Report--

This article mainly introduces the relevant knowledge of how to use the Parameter function in pytorch, the content is detailed and easy to understand, the operation is simple and fast, and has a certain reference value, I believe you will have something to gain after reading this article on how to use the Parameter function in pytorch. Let's take a look at it.

Introduction to usage

The Parameter function in pytorch can parameterize a tensor. It can transform the untrainable tensor into trainable parameter types, and bind the transformed tensor to the list of trainable parameters of the model, and update it when updating the parameters of the model.

Torch.nn.parameter.Parameter

Data (Tensor): represents a tensor that needs to be parameterized

Requires_grad (bool, optional): indicates whether the tensor needs a gradient. The default is True.

Code introduction

The specific code example of the Parameter function in   pytorch is as follows

Import torchimport torch.nn as nnclass NeuralNetwork (nn.Module): def _ init__ (self, input_dim, output_dim): super (NeuralNetwork, self). _ _ init__ () self.linear = nn.Linear (input_dim, output_dim) self.linear.weight = torch.nn.Parameter (torch.zeros (input_dim) Output_dim)) self.linear.bias = torch.nn.Parameter (torch.ones (output_dim)) def forward (self, input_array): output = self.linear (input_array) return outputif _ _ name__ ='_ main__': net = NeuralNetwork (4,6) for param in net.parameters (): print (param)

The result of the code is as follows:

When the parameters of the neural network are not parameterized by the Parameter function and directly assigned to the weight parameters, an error will be reported.

Import torchimport torch.nn as nnclass NeuralNetwork (nn.Module): def _ init__ (self, input_dim, output_dim): super (NeuralNetwork, self). _ _ init__ () self.linear = nn.Linear (input_dim, output_dim) self.linear.weight = torch.zeros (input_dim) Output_dim) self.linear.bias = torch.ones (output_dim) def forward (self, input_array): output = self.linear (input_array) return outputif _ _ name__ ='_ main__': net = NeuralNetwork (4,6) for param in net.parameters (): print (param)

The error result of running the code is as follows:

This is the end of the article on "how to use the Parameter function in pytorch". Thank you for reading! I believe you all have a certain understanding of the knowledge of "how to use the Parameter function in pytorch". If you want to learn more, you are welcome to follow the industry information channel.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.