diff --git a/utils/metrics.py b/utils/metrics.py
index e17747b703fa..44b279d35c48 100644
--- a/utils/metrics.py
+++ b/utils/metrics.py
@@ -103,8 +103,8 @@ def compute_ap(recall, precision):
     """
 
     # Append sentinel values to beginning and end
-    mrec = np.concatenate(([0.0], recall, [1.0]))
-    mpre = np.concatenate(([1.0], precision, [0.0]))
+    mrec = recall
+    mpre = precision
 
     # Compute the precision envelope
     mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))
@@ -113,7 +113,7 @@ def compute_ap(recall, precision):
     method = 'interp'  # methods: 'continuous', 'interp'
     if method == 'interp':
         x = np.linspace(0, 1, 101)  # 101-point interp (COCO)
-        ap = np.trapz(np.interp(x, mrec, mpre), x)  # integrate
+        ap = np.interp(x, mrec, mpre, right=0).mean()  # integrate with rect
     else:  # 'continuous'
         i = np.where(mrec[1:] != mrec[:-1])[0]  # points where x axis (recall) changes
         ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1])  # area under curve
diff --git a/val.py b/val.py
index f4f4bab7e92d..68b40b645db6 100644
--- a/val.py
+++ b/val.py
@@ -214,7 +214,13 @@ def run(
         targets[:, 2:] *= torch.tensor((width, height, width, height), device=device)  # to pixels
         lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
         t3 = time_sync()
-        out = non_max_suppression(out, conf_thres, iou_thres, labels=lb, multi_label=True, agnostic=single_cls)
+        out = non_max_suppression(out,
+                                  conf_thres,
+                                  iou_thres,
+                                  labels=lb,
+                                  multi_label=True,
+                                  agnostic=single_cls,
+                                  max_det=100)
         dt[2] += time_sync() - t3
 
         # Metrics
@@ -227,7 +233,7 @@ def run(
 
             if npr == 0:
                 if nl:
-                    stats.append((correct, *torch.zeros((3, 0), device=device)))
+                    stats.append((correct, *torch.zeros((2, 0), device=device), labels[:, 0]))
                 continue
 
             # Predictions