We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
paddle.distribution.Categorical 支持props输入
参考链接: https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/model_convert/convert_from_pytorch/api_difference/distributions/torch.distributions.categorical.Categorical.html
目前仿照torch进行替代实现:
eps = paddle.finfo(q_probs.dtype).eps q_logits = paddle.log(x=q_probs.clip(min=eps, max=1 - eps)) d1 = paddle.distribution.Categorical(logits=q_logits)
The text was updated successfully, but these errors were encountered:
打错字了,是probs参数 https://pytorch.org/docs/stable/distributions.html#categorical
Sorry, something went wrong.
结果paddle和torch下使用prob或者log_prob方法,结果还是不一样
wangguan1995
No branches or pull requests
需求描述 Feature Description
paddle.distribution.Categorical 支持props输入
参考链接:
https://www.paddlepaddle.org.cn/documentation/docs/zh/guides/model_convert/convert_from_pytorch/api_difference/distributions/torch.distributions.categorical.Categorical.html
替代实现 Alternatives
目前仿照torch进行替代实现:
The text was updated successfully, but these errors were encountered: