(this issue is just for my personal self-learning ) imcomplete features of paddle.nn.initializer.TruncatedNormal (compared to torch.nn.init.trunc_normal_() )

[OccupyMars2025]

需求描述 Feature Description

objectives: complete the features of paddle.nn.initializer.TruncatedNormal
(compared to torch.nn.init.trunc_normal_() )

requirement scenarios:
in pytorch, If I want to create a parameter, I will do the following:
self.pos_embed = nn.Parameter(torch.zeros(1, num_patches, embed_dim)) trunc_normal_(self.pos_embed, std=.02)
while in paddlepaddle, if I want to do the same thing, I will do the following:
`
self.pos_embed = self.create_parameter(shape=[1, num_patches, embed_dim],
is_bias=False,
default_initializer=paddle.nn.initializer.TruncatedNormal(std=0.02))

`
but I found that paddle.nn.initializer.TruncatedNormal doesn't have lower and upper cutoff values
in its init method

替代实现 Alternatives

No response

[paddle-bot-old]

您好，我们已经收到了您的问题，会安排技术人员尽快解答您的问题，请耐心等待。请您再次检查是否提供了清晰的问题描述、复现代码、环境&版本、报错信息等。同时，您也可以通过查看官网API文档、常见问题、历史Issue、AI社区来寻求解答。祝您生活愉快～

Hi! We've received your issue and please be patient to get responded. We will arrange technicians to answer your questions as soon as possible. Please make sure that you have posted enough message to demo your request. You may also check out the API，FAQ，Github Issue and AI community to get the answer.Have a nice day!

[gongel]

Thank you for your attention. We are evaluating it internally and please look forward to it. At the same time, you can also implement it yourself through hacking.