Add RTDETR Trainer (#2745)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: Laughing-q <1185102784@qq.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>

ultralytics/yolo/utils/loss.py

@@ -24,10 +24,34 @@ class VarifocalLoss(nn.Module):
         weight = alpha * pred_score.sigmoid().pow(gamma) * (1 - label) + gt_score * label
         with torch.cuda.amp.autocast(enabled=False):
             loss = (F.binary_cross_entropy_with_logits(pred_score.float(), gt_score.float(), reduction='none') *
-                    weight).sum()
+                    weight).mean(1).sum()
         return loss
 
 
+# Losses
+class FocalLoss(nn.Module):
+    """Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)."""
+
+    def __init__(self, ):
+        super().__init__()
+
+    def forward(self, pred, label, gamma=1.5, alpha=0.25):
+        """Calculates and updates confusion matrix for object detection/classification tasks."""
+        loss = F.binary_cross_entropy_with_logits(pred, label, reduction='none')
+        # p_t = torch.exp(-loss)
+        # loss *= self.alpha * (1.000001 - p_t) ** self.gamma  # non-zero power for gradient stability
+
+        # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
+        pred_prob = pred.sigmoid()  # prob from logits
+        p_t = label * pred_prob + (1 - label) * (1 - pred_prob)
+        modulating_factor = (1.0 - p_t) ** gamma
+        loss *= modulating_factor
+        if alpha > 0:
+            alpha_factor = label * alpha + (1 - label) * (1 - alpha)
+            loss *= alpha_factor
+        return loss.mean(1).sum()
+
+
 class BboxLoss(nn.Module):
 
     def __init__(self, reg_max, use_dfl=False):