diff --git a/train.py b/train.py
index cb0a15d7..12fec636 100644
--- a/train.py
+++ b/train.py
@@ -27,6 +27,7 @@ hyp = {'giou': 1.582,  # giou loss gain
        'lrf': -4.,  # final LambdaLR learning rate = lr0 * (10 ** lrf)
        'momentum': 0.97,  # SGD momentum
        'weight_decay': 0.0004569,  # optimizer weight decay
+       'fl_gamma': 0.5,  # focal loss gamma
        'hsv_s': 0.5703,  # image HSV-Saturation augmentation (fraction)
        'hsv_v': 0.3174,  # image HSV-Value augmentation (fraction)
        'degrees': 1.113,  # image rotation (+/- deg)
@@ -420,14 +421,14 @@ if __name__ == '__main__':
 
                 # Mutate
                 init_seeds(seed=int(time.time()))
-                s = [.15, .15, .15, .15, .15, .15, .15, .00, .02, .20, .20, .20, .20, .20, .20, .20]  # sigmas
+                s = [.15, .15, .15, .15, .15, .15, .15, .00, .02, .20, .15, .20, .20, .20, .20, .20, .20]  # sigmas
                 for i, k in enumerate(hyp.keys()):
                     x = (np.random.randn(1) * s[i] + 1) ** 2.0  # plt.hist(x.ravel(), 300)
                     hyp[k] *= float(x)  # vary by sigmas
 
             # Clip to limits
-            keys = ['lr0', 'iou_t', 'momentum', 'weight_decay', 'hsv_s', 'hsv_v', 'translate', 'scale']
-            limits = [(1e-4, 1e-2), (0.00, 0.70), (0.60, 0.98), (0, 0.001), (0, .9), (0, .9), (0, .9), (0, .9)]
+            keys = ['lr0', 'iou_t', 'momentum', 'weight_decay', 'hsv_s', 'hsv_v', 'translate', 'scale', 'fl_gamma']
+            limits = [(1e-4, 1e-2), (0.00, 0.70), (0.60, 0.98), (0, 0.001), (0, .9), (0, .9), (0, .9), (0, .9), (0, 3)]
             for k, v in zip(keys, limits):
                 hyp[k] = np.clip(hyp[k], v[0], v[1])
 
diff --git a/utils/utils.py b/utils/utils.py
index 3ffc5272..08f3ffd1 100755
--- a/utils/utils.py
+++ b/utils/utils.py
@@ -291,12 +291,12 @@ def wh_iou(box1, box2):
 class FocalLoss(nn.Module):
     # Wraps focal loss around existing loss_fcn() https://arxiv.org/pdf/1708.02002.pdf
     # i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=2.5)
-    def __init__(self, loss_fcn, alpha=1, gamma=0.5, reduction='mean'):
+    def __init__(self, loss_fcn, gamma=0.5, alpha=1, reduction='mean'):
         super(FocalLoss, self).__init__()
         loss_fcn.reduction = 'none'  # required to apply FL to each element
         self.loss_fcn = loss_fcn
-        self.alpha = alpha
         self.gamma = gamma
+        self.alpha = alpha
         self.reduction = reduction
 
     def forward(self, input, target):
@@ -325,7 +325,8 @@ def compute_loss(p, targets, model):  # predictions, targets, model
     CE = nn.CrossEntropyLoss()  # weight=model.class_weights
 
     if 'F' in arc:  # add focal loss
-        BCEcls, BCEobj, BCE, CE = FocalLoss(BCEcls), FocalLoss(BCEobj), FocalLoss(BCE), FocalLoss(CE)
+        g = h['fl_gamma']
+        BCEcls, BCEobj, BCE, CE = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g), FocalLoss(BCE, g), FocalLoss(CE, g)
 
     # Compute losses
     for i, pi in enumerate(p):  # layer index, layer predictions