diff --git a/README.md b/README.md
index 19b98a2..3ff6fe7 100644
--- a/README.md
+++ b/README.md
@@ -317,6 +317,8 @@ This demo also creates a json file named ```net_name_COCO_res.json``` containing
 | resnet101_cnet    | Centernet (Resnet101 backend)<sup>4</sup>     | [COCO 2017](http://cocodataset.org/)                          | 80        | 512x512       | [weights](https://cloud.hipert.unimore.it/s/5BTjHMWBcJk8g3i/download)     |
 | csresnext50-panet-spp    | Cross Stage Partial Network <sup>7</sup>     | [COCO 2014](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/Kcs4xBozwY4wFx8/download)     |
 | yolo4             | Yolov4 <sup>8</sup>                           | [COCO 2017](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/d97CFzYqCPCp5Hg/download)     |
+| yolo4_berkeley             | Yolov4 <sup>8</sup>                           | [BDD100K  ](https://bair.berkeley.edu/blog/2018/05/30/bdd/)                          | 10        | 540x320       | [weights](https://cloud.hipert.unimore.it/s/nkWFa5fgb4NTdnB/download)     |
+| yolo4tiny             | Yolov4 tiny                           | [COCO 2017](http://cocodataset.org/)                          | 80        | 416x416       | [weights](https://cloud.hipert.unimore.it/s/iRnc4pSqmx78gJs/download)     |
 
 
 ## References
diff --git a/include/tkDNN/pluginsRT/RouteRT.h b/include/tkDNN/pluginsRT/RouteRT.h
index 263893f..23f30b7 100644
--- a/include/tkDNN/pluginsRT/RouteRT.h
+++ b/include/tkDNN/pluginsRT/RouteRT.h
@@ -52,16 +52,18 @@ public:
 	}
 
 	virtual int enqueue(int batchSize, const void*const * inputs, void** outputs, void* workspace, cudaStream_t stream) override {
-
+		
 		dnnType *dstData = reinterpret_cast<dnnType*>(outputs[0]);
 
-		int offset = 0;
-		for(int i=0; i<in; i++) {
-			dnnType *input = (dnnType*)reinterpret_cast<const dnnType*>(inputs[i]);
-			int in_dim = c_in[i]*h*w;
-			int part_in_dim = in_dim / this->groups;
-			checkCuda( cudaMemcpyAsync(dstData + offset, input + this->group_id*part_in_dim, part_in_dim*sizeof(dnnType), cudaMemcpyDeviceToDevice, stream) );
-			offset += part_in_dim;
+		for(int b=0; b<batchSize; b++) {
+			int offset = 0;
+			for(int i=0; i<in; i++) {
+				dnnType *input = (dnnType*)reinterpret_cast<const dnnType*>(inputs[i]);
+				int in_dim = c_in[i]*h*w;
+				int part_in_dim = in_dim / this->groups;
+				checkCuda( cudaMemcpyAsync(dstData + b*c*w*h + offset, input + b*c*w*h*groups + this->group_id*part_in_dim, part_in_dim*sizeof(dnnType), cudaMemcpyDeviceToDevice, stream) );
+				offset += part_in_dim;
+			}
 		}
 
 		return 0;
diff --git a/scripts/test_all_tests.sh b/scripts/test_all_tests.sh
index 193a90c..770aa22 100644
--- a/scripts/test_all_tests.sh
+++ b/scripts/test_all_tests.sh
@@ -74,6 +74,7 @@ do
 
     test_net yolo4
     test_net yolo4_berkeley
+    test_net yolo4tiny
     test_net yolo3
     test_net yolo3_berkeley
     test_net yolo3_coco4