ReusJeffery
ReusJeffery
Hello,did you solve the NaN probelm?
> Oh, I haven't tried PolyIoULoss in Oriented RPN. Let me do some research. Hello,did you solve the NaN probelm?
I found something wrong in gmm = torch.distributions.MultivariateNormal(loc=classwise_mean_features, covariance_matrix=(classwise_cov_features + jitter)) ValueError: Expected parameter covariance_matrix (Tensor of shape (10, 2048, 2048)) of distribution MultivariateNormal(loc: torch.Size([10, 2048]), covariance_matrix: torch.Size([10, 2048, 2048]))...
> I have the same question,in paper Eq.8 > > > ". In the following experiments, we empirically set C to the average absolute size of AI-TOD and achieve the...
Thank you for your replying ------------------ 原始邮件 ------------------ 发件人: "LiWentomng/OrientedRepPoints" ***@***.***>; 发送时间: 2022年11月23日(星期三) 下午3:13 ***@***.***>; ***@***.******@***.***>; 主题: Re: [LiWentomng/OrientedRepPoints] RuntimeError: cuda runtime error (700) : an illegal memory access was encountered at mmdet/ops/iou/src/convex_giou_kernel.cu:853 (Issue...