當前位置: 首頁>>代碼示例>>Python>>正文


Python _C.sigmoid_focalloss_forward方法代碼示例

本文整理匯總了Python中maskrcnn_benchmark._C.sigmoid_focalloss_forward方法的典型用法代碼示例。如果您正苦於以下問題:Python _C.sigmoid_focalloss_forward方法的具體用法?Python _C.sigmoid_focalloss_forward怎麽用?Python _C.sigmoid_focalloss_forward使用的例子?那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在maskrcnn_benchmark._C的用法示例。


在下文中一共展示了_C.sigmoid_focalloss_forward方法的3個代碼示例,這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚,您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: forward

# 需要導入模塊: from maskrcnn_benchmark import _C [as 別名]
# 或者: from maskrcnn_benchmark._C import sigmoid_focalloss_forward [as 別名]
def forward(ctx, logits, targets, gamma, alpha):
        ctx.save_for_backward(logits, targets)
        num_classes = logits.shape[1]
        ctx.num_classes = num_classes
        ctx.gamma = gamma
        ctx.alpha = alpha

        losses = _C.sigmoid_focalloss_forward(
            logits, targets, num_classes, gamma, alpha
        )
        return losses 
開發者ID:Res2Net,項目名稱:Res2Net-maskrcnn,代碼行數:13,代碼來源:sigmoid_focal_loss.py

示例2: forward

# 需要導入模塊: from maskrcnn_benchmark import _C [as 別名]
# 或者: from maskrcnn_benchmark._C import sigmoid_focalloss_forward [as 別名]
def forward(ctx, logits, targets, num_classes, gamma, alpha):
        ctx.save_for_backward(logits, targets);
        ctx.num_classes = num_classes
        ctx.gamma = gamma
        ctx.alpha = alpha

        losses = _C.sigmoid_focalloss_forward(
            logits, targets, num_classes, gamma, alpha
        )
        return losses 
開發者ID:zhangxiaosong18,項目名稱:FreeAnchor,代碼行數:12,代碼來源:sigmoid_focal_loss.py

示例3: forward

# 需要導入模塊: from maskrcnn_benchmark import _C [as 別名]
# 或者: from maskrcnn_benchmark._C import sigmoid_focalloss_forward [as 別名]
def forward(ctx, logits, targets, gamma, alpha):
        ctx.save_for_backward(logits, targets)
        num_classes = logits.shape[1]
        ctx.num_classes = num_classes
        ctx.gamma = gamma
        ctx.alpha = alpha
        
        losses = _C.sigmoid_focalloss_forward(
            logits, targets, num_classes, gamma, alpha
        )
        return losses 
開發者ID:Lausannen,項目名稱:NAS-FCOS,代碼行數:13,代碼來源:sigmoid_focal_loss.py


注:本文中的maskrcnn_benchmark._C.sigmoid_focalloss_forward方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台,相關代碼片段篩選自各路編程大神貢獻的開源項目,源碼版權歸原作者所有,傳播和使用請參考對應項目的License;未經允許,請勿轉載。