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
请问训练时,传入损失函数的ground truth的格式是单通道的,如 0, 1 ,2, 3, 4, 5, ....这样的格式么? 而不是one hot的 多通道的,如 0, 0, 1, 0, 0, .......这样的格式吧
detail_loss.py文件中的class DetailAggregateLoss的方法 def forward(self, boundary_logits, gtmasks) 这里的gtmasks也就是单通道的格式吧? 在此基础上进行laplacian_kernel 卷积计算?
同时loss.py文件的class OhemCELoss(nn.Module)的方法 def forward(self, logits, labels): 这里的labels也同样是单通道吧?
The text was updated successfully, but these errors were encountered:
还请教一个问题:
损失函数boundary_loss_func = DetailAggregateLoss() 调用boundary_loss_func(detail8, lb),其中作为ground truth的lb是包括,ignore_idx=255的,也就是包含了ignore_idx=255的轮廓信息;
而另一个损失函数criteria_p = OhemCELoss(thresh=score_thres, n_min=n_min, ignore_lb=ignore_idx),计算交叉熵的时候,忽略计算类别为ignore_lb=ignore_idx的损失, 请教在模型预测的时候,类别为ignore_idx(=255)的像素块,模型会预测成什么类别呢?
Sorry, something went wrong.
还请教一个问题,损失函数OhemCELoss,如果在单个gpu上训练,n_min应该设置为多少呢? 谢谢
No branches or pull requests
请问训练时,传入损失函数的ground truth的格式是单通道的,如 0, 1 ,2, 3, 4, 5, ....这样的格式么?
而不是one hot的 多通道的,如 0, 0, 1, 0, 0, .......这样的格式吧
detail_loss.py文件中的class DetailAggregateLoss的方法 def forward(self, boundary_logits, gtmasks)
这里的gtmasks也就是单通道的格式吧? 在此基础上进行laplacian_kernel 卷积计算?
同时loss.py文件的class OhemCELoss(nn.Module)的方法 def forward(self, logits, labels):
这里的labels也同样是单通道吧?
The text was updated successfully, but these errors were encountered: