diff --git a/include/tkDNN/DarknetParser.h b/include/tkDNN/DarknetParser.h
index 29d1e8e..089c4d6 100644
--- a/include/tkDNN/DarknetParser.h
+++ b/include/tkDNN/DarknetParser.h
@@ -24,7 +24,10 @@ namespace tk { namespace dnn {
         int num = 1;
         int pad = 0;
         int coords = 4;
+        int nms_kind = 0;
+        int new_coords= 0;
         float scale_xy = 1;
+        float nms_thresh = 0.45;
         std::vector<int> layers;
         std::string activation = "linear";
 
diff --git a/include/tkDNN/Layer.h b/include/tkDNN/Layer.h
index 790a431..25c4565 100644
--- a/include/tkDNN/Layer.h
+++ b/include/tkDNN/Layer.h
@@ -610,24 +610,28 @@ public:
         int sort_class;
     };
 
-    Yolo(Network *net, int classes, int num, std::string fname_weights,int n_masks=3, float scale_xy=1);
+    enum nmsKind_t {GREEDY_NMS=0, DIOU_NMS=1};
+
+    Yolo(Network *net, int classes, int num, std::string fname_weights,int n_masks=3, float scale_xy=1, double nms_thresh=0.45, nmsKind_t nsm_kind=GREEDY_NMS, int new_coords=0);
     virtual ~Yolo();
     virtual layerType_t getLayerType() { return LAYER_YOLO; };
 
-    int classes, num, n_masks;
+    int classes, num, n_masks, new_coords;
     dnnType *mask_h, *mask_d; //anchors
     dnnType *bias_h, *bias_d; //anchors
     float scaleXY;
+    double nms_thresh;
+    nmsKind_t nsm_kind; 
     std::vector<std::string> classesNames;
 
     virtual dnnType* infer(dataDim_t &dim, dnnType* srcData);
-    int computeDetections(Yolo::detection *dets, int &ndets, int netw, int neth, float thresh);
+    int computeDetections(Yolo::detection *dets, int &ndets, int netw, int neth, float thresh, int new_coords=0);
 
     dnnType *predictions;
 
-    static const int MAX_DETECTIONS = 8192;
+    static const int MAX_DETECTIONS = 8192*2;
     static Yolo::detection *allocateDetections(int nboxes, int classes);
-    static void             mergeDetections(Yolo::detection *dets, int ndets, int classes);
+    static void             mergeDetections(Yolo::detection *dets, int ndets, int classes, double nms_thresh=0.45, nmsKind_t nsm_kind=GREEDY_NMS);
 };
 
 /**
diff --git a/include/tkDNN/pluginsRT/YoloRT.h b/include/tkDNN/pluginsRT/YoloRT.h
index f8e596c..9af8587 100644
--- a/include/tkDNN/pluginsRT/YoloRT.h
+++ b/include/tkDNN/pluginsRT/YoloRT.h
@@ -8,12 +8,15 @@ class YoloRT : public IPlugin {
 
 
 public:
-	YoloRT(int classes, int num, tk::dnn::Yolo *yolo = nullptr, int n_masks=3, float scale_xy=1) {
+	YoloRT(int classes, int num, tk::dnn::Yolo *yolo = nullptr, int n_masks=3, float scale_xy=1, float nms_thresh=0.45, int nms_kind=0, int new_coords=0) {
 
 		this->classes = classes;
 		this->num = num;
 		this->n_masks = n_masks;
 		this->scaleXY = scale_xy;
+		this->nms_thresh = nms_thresh;
+		this->nms_kind = nms_kind;
+		this->new_coords = new_coords;
 
         mask = new dnnType[n_masks];
         bias = new dnnType[num*n_masks*2];
@@ -64,7 +67,10 @@ public:
 		for (int b = 0; b < batchSize; ++b){
 			for(int n = 0; n < n_masks; ++n){
 				int index = entry_index(b, n*w*h, 0);
-				activationLOGISTICForward(srcData + index, dstData + index, 2*w*h, stream);
+				if (new_coords == 1)
+					activationLOGISTICForward(srcData + index, dstData + index, 4*w*h, stream); //x,y,w,h
+				else
+					activationLOGISTICForward(srcData + index, dstData + index, 2*w*h, stream); //x,y
 
 				if (this->scaleXY != 1) scalAdd(dstData + index, 2 * w*h, this->scaleXY, -0.5*(this->scaleXY - 1), 1);
 				
@@ -79,7 +85,7 @@ public:
 
 
 	virtual size_t getSerializationSize() override {
-		return 6*sizeof(int) + sizeof(float)+ n_masks*sizeof(dnnType) + num*n_masks*2*sizeof(dnnType) + YOLORT_CLASSNAME_W*classes*sizeof(char);
+		return 8*sizeof(int) + 2*sizeof(float)+ n_masks*sizeof(dnnType) + num*n_masks*2*sizeof(dnnType) + YOLORT_CLASSNAME_W*classes*sizeof(char);
 	}
 
 	virtual void serialize(void* buffer) override {
@@ -87,10 +93,13 @@ public:
 		tk::dnn::writeBUF(buf, classes);
 		tk::dnn::writeBUF(buf, num);
 		tk::dnn::writeBUF(buf, n_masks);
+		tk::dnn::writeBUF(buf, scaleXY);
+		tk::dnn::writeBUF(buf, nms_thresh);
+		tk::dnn::writeBUF(buf, nms_kind);
+		tk::dnn::writeBUF(buf, new_coords);
 		tk::dnn::writeBUF(buf, c);
 		tk::dnn::writeBUF(buf, h);
 		tk::dnn::writeBUF(buf, w);
-		tk::dnn::writeBUF(buf, scaleXY);
         for(int i=0; i<n_masks; i++)
     		tk::dnn::writeBUF(buf, mask[i]);
         for(int i=0; i<n_masks*2*num; i++)
@@ -109,6 +118,9 @@ public:
 	int c, h, w;
     int classes, num, n_masks;
 	float scaleXY;
+	float nms_thresh;
+	int nms_kind;
+	int new_coords;
 	std::vector<std::string> classesNames;
 
     dnnType *mask;
diff --git a/scripts/test_all_tests.sh b/scripts/test_all_tests.sh
index 770aa22..af04aff 100644
--- a/scripts/test_all_tests.sh
+++ b/scripts/test_all_tests.sh
@@ -73,6 +73,7 @@ do
     print_output $? imuodom
 
     test_net yolo4
+    test_net yolo4x
     test_net yolo4_berkeley
     test_net yolo4tiny
     test_net yolo3
diff --git a/src/DarknetParser.cpp b/src/DarknetParser.cpp
index 7d7d989..7b5410c 100644
--- a/src/DarknetParser.cpp
+++ b/src/DarknetParser.cpp
@@ -37,7 +37,10 @@ namespace tk { namespace dnn {
         std::string name,value;
         if(!divideNameAndValue(line, name, value))
             return false;
-        if(name.find("width") !=  std::string::npos)
+
+        if(name.find("new_coords") !=  std::string::npos)
+            fields.new_coords = std::stoi(value);
+        else if(name.find("width") !=  std::string::npos)
             fields.width = std::stoi(value);
         else if(name.find("height") !=  std::string::npos)
             fields.height = std::stoi(value);
@@ -79,6 +82,13 @@ namespace tk { namespace dnn {
             fields.group_id = std::stoi(value);
         else if(name.find("scale_x_y") !=  std::string::npos)
             fields.scale_xy = std::stof(value);
+        else if(name.find("beta_nms") !=  std::string::npos)
+            fields.nms_thresh = std::stof(value);
+        else if(name.find("nms_kind") !=  std::string::npos){
+            if(value == "greedynms") fields.nms_kind = 0;
+            else if(value == "diounms") fields.nms_kind = 1;
+            else std::cout<<"Not supported nms_kind "<<value<<", setting to greedynms"<<std::endl;
+        }
         else if(name.find("from") !=  std::string::npos)
             fields.layers.push_back(std::stof(value));
         else if(name.find("mask") !=  std::string::npos){
@@ -161,7 +171,7 @@ namespace tk { namespace dnn {
         } else if(f.type == "yolo") {
             std::string wgs = wgs_path + "/g" + std::to_string(netLayers.size()) + ".bin";
             //printf("%d %d %s %d %f\n", f.classes, f.num/f.n_mask, wgs.c_str(), f.n_mask, f.scale_xy);
-            tk::dnn::Yolo *l = new tk::dnn::Yolo(net, f.classes, f.num/f.n_mask, wgs, f.n_mask, f.scale_xy);
+            tk::dnn::Yolo *l = new tk::dnn::Yolo(net, f.classes, f.num/f.n_mask, wgs, f.n_mask, f.scale_xy, f.nms_thresh, (tk::dnn::Yolo::nmsKind_t) f.nms_kind, f.new_coords);
             if(names.size() != f.classes)
                 FatalError("Mismatch between number of classes and names");
             l->classesNames = names;
diff --git a/src/NetworkRT.cpp b/src/NetworkRT.cpp
index 9d38440..501ade4 100644
--- a/src/NetworkRT.cpp
+++ b/src/NetworkRT.cpp
@@ -529,7 +529,7 @@ ILayer* NetworkRT::convert_layer(ITensor *input, Yolo *l) {
     //std::cout<<"convert Yolo\n";
 
     //std::cout<<"New plugin YOLO\n";
-    IPlugin *plugin = new YoloRT(l->classes, l->num, l, l->n_masks, l->scaleXY);
+    IPlugin *plugin = new YoloRT(l->classes, l->num, l, l->n_masks, l->scaleXY, l->nms_thresh, l->nsm_kind, l->new_coords);
     IPluginLayer *lRT = networkRT->addPlugin(&input, 1, *plugin);
     checkNULL(lRT);
     return lRT;
@@ -739,12 +739,16 @@ IPlugin* PluginFactory::createPlugin(const char* layerName, const void* serialDa
     if(name.find("Yolo") == 0) {
         YoloRT *r = new YoloRT(readBUF<int>(buf),    //classes
                                 readBUF<int>(buf),   //num
-                                nullptr,
-                                readBUF<int>(buf));   //n_masks
+                                nullptr, //yolo
+                                readBUF<int>(buf), //n_masks
+                                readBUF<float>(buf), //scale_xy
+                                readBUF<float>(buf),  //nms_thresh 
+                                readBUF<int>(buf),  //nms_kind
+                                readBUF<int>(buf)  //new_coords
+                                );   
         r->c = readBUF<int>(buf);
         r->h = readBUF<int>(buf);
         r->w = readBUF<int>(buf);
-        r->scaleXY = readBUF<float>(buf);
         for(int i=0; i<r->n_masks; i++)
             r->mask[i] = readBUF<dnnType>(buf);
         for(int i=0; i<r->n_masks*2*r->num; i++)
diff --git a/src/Yolo.cpp b/src/Yolo.cpp
index a4416be..9737e74 100644
--- a/src/Yolo.cpp
+++ b/src/Yolo.cpp
@@ -11,7 +11,7 @@
 
 namespace tk { namespace dnn {
 
-Yolo::Yolo(Network *net, int classes, int num, std::string fname_weights, int n_masks, float scale_xy) : 
+Yolo::Yolo(Network *net, int classes, int num, std::string fname_weights, int n_masks, float scale_xy, double nms_thresh, nmsKind_t nsm_kind, int new_coords) : 
     Layer(net) {
     this->final = true;
 
@@ -19,6 +19,9 @@ Yolo::Yolo(Network *net, int classes, int num, std::string fname_weights, int n_
     this->num = num;
     this->n_masks = n_masks;
     this->scaleXY = scale_xy;
+    this->nms_thresh = nms_thresh;
+    this->nsm_kind = nsm_kind;
+    this->new_coords = new_coords;
 
     // load anchors
     if(fname_weights != "") {
@@ -59,12 +62,21 @@ int entry_index(int batch, int location, int entry,
            entry*input_dim.w*input_dim.h + loc;
 }
 
-Yolo::box get_yolo_box(float *x, float *biases, int n, int index, int i, int j, int lw, int lh, int w, int h, int stride) {
+Yolo::box get_yolo_box(float *x, float *biases, int n, int index, int i, int j, int lw, int lh, int w, int h, int stride, int new_coords) {
     Yolo::box b;
-    b.x = (i + x[index + 0*stride]) / lw;
-    b.y = (j + x[index + 1*stride]) / lh;
-    b.w = exp(x[index + 2*stride]) * biases[2*n]   / w;
-    b.h = exp(x[index + 3*stride]) * biases[2*n+1] / h;
+
+    if(new_coords == 0){
+        b.x = (i + x[index + 0*stride]) / lw;
+        b.y = (j + x[index + 1*stride]) / lh;
+        b.w = exp(x[index + 2*stride]) * biases[2*n]   / w;
+        b.h = exp(x[index + 3*stride]) * biases[2*n+1] / h;
+    }
+    else{
+        b.x = (i + x[index + 0 * stride] * 2 - 0.5) / lw;
+        b.y = (j + x[index + 1 * stride] * 2 - 0.5) / lh;
+        b.w = x[index + 2 * stride] * x[index + 2 * stride] * 4 * biases[2 * n] / w;
+        b.h = x[index + 3 * stride] * x[index + 3 * stride] * 4 * biases[2 * n + 1] / h;
+    }
     return b;
 }
 
@@ -75,7 +87,10 @@ dnnType* Yolo::infer(dataDim_t &dim, dnnType* srcData) {
     for (int b = 0; b < dim.n; ++b){
         for(int n = 0; n < n_masks; ++n){
             int index = entry_index(b, n*dim.w*dim.h, 0, classes, input_dim, output_dim);
-            activationLOGISTICForward(srcData + index, dstData + index, 2*dim.w*dim.h);
+            if (new_coords == 1)
+                activationLOGISTICForward(srcData + index, dstData + index, 4*dim.w*dim.h);
+            else
+                activationLOGISTICForward(srcData + index, dstData + index, 2*dim.w*dim.h);
 
             if (this->scaleXY != 1) scalAdd(dstData + index, 2 * dim.w*dim.h, this->scaleXY, -0.5*(this->scaleXY - 1), 1);
             
@@ -116,7 +131,7 @@ void correct_yolo_boxes(Yolo::detection *dets, int n, int w, int h, int netw, in
     }
 }
 
-int Yolo::computeDetections(Yolo::detection *dets, int &ndets, int netw, int neth, float thresh) {
+int Yolo::computeDetections(Yolo::detection *dets, int &ndets, int netw, int neth, float thresh, int new_coords) {
 
     if(predictions == nullptr)
         predictions = new dnnType[output_dim.tot()];
@@ -140,7 +155,7 @@ int Yolo::computeDetections(Yolo::detection *dets, int &ndets, int netw, int net
             if(objectness <= thresh) continue;
             int box_index  = entry_index(0, n*lw*lh + i, 0, classes, input_dim, output_dim);
             
-            dets[count].bbox = get_yolo_box(predictions, bias_h, mask_h[n], box_index, col, row, lw, lh, netw, neth, lw*lh);
+            dets[count].bbox = get_yolo_box(predictions, bias_h, mask_h[n], box_index, col, row, lw, lh, netw, neth, lw*lh, new_coords);
             dets[count].objectness = objectness;
             dets[count].classes = classes;
             for(j = 0; j < classes; ++j){
@@ -193,6 +208,32 @@ float yolo_box_iou(Yolo::box a, Yolo::box b)
     return yolo_box_intersection(a, b)/yolo_box_union(a, b);
 }
 
+void box_c(const Yolo::box a, const Yolo::box b, float& top, float& bot, float& left, float& right) {
+    top = std::min(a.y - a.h / 2, b.y - b.h / 2);
+    bot = std::max(a.y + a.h / 2, b.y + b.h / 2);
+    left = std::min(a.x - a.w / 2, b.x - b.w / 2);
+    right = std::max(a.x + a.w / 2, b.x + b.w / 2);
+}
+
+// https://github.com/Zzh-tju/DIoU-darknet
+// https://arxiv.org/abs/1911.08287
+float yolo_box_diou(const Yolo::box a, const Yolo::box b, const float nms_thresh=0.6)
+{
+    float top, bot, left, right;
+    box_c(a, b, top, bot, left, right);
+    float w = right - left;
+    float h = bot - top;
+    float c = w * w + h * h;
+    float iou = yolo_box_iou(a, b);
+    if (c == 0) 
+        return iou;
+    
+    float d = (a.x - b.x) * (a.x - b.x) + (a.y - b.y) * (a.y - b.y);
+    float u = pow(d / c, nms_thresh);
+    float diou_term = u;
+    return iou - diou_term;
+}
+
 int yolo_nms_comparator(const void *pa, const void *pb)
 {
     Yolo::detection a = *(Yolo::detection *)pa;
@@ -219,8 +260,7 @@ Yolo::detection *Yolo::allocateDetections(int nboxes, int classes) {
     return dets;
 }
 
-void Yolo::mergeDetections(Yolo::detection *dets, int ndets, int classes) {
-    double nms_thresh = 0.45;
+void Yolo::mergeDetections(Yolo::detection *dets, int ndets, int classes, double nms_thresh, nmsKind_t nsm_kind) {
     int total = ndets;
 
     int i, j, k;
@@ -246,13 +286,13 @@ void Yolo::mergeDetections(Yolo::detection *dets, int ndets, int classes) {
             box a = dets[i].bbox;
             for(j = i+1; j < total; ++j){
                 box b = dets[j].bbox;
-                if (yolo_box_iou(a, b) > nms_thresh){
+                if (nsm_kind == GREEDY_NMS && yolo_box_iou(a, b) > nms_thresh)
+                    dets[j].prob[k] = 0;
+                else if (nsm_kind == DIOU_NMS && yolo_box_diou(a, b, nms_thresh) > nms_thresh)
                     dets[j].prob[k] = 0;
-                }
             }
         }
     }
-
 }
 
 }}
diff --git a/src/Yolo3Detection.cpp b/src/Yolo3Detection.cpp
index e9b0064..b94eea9 100644
--- a/src/Yolo3Detection.cpp
+++ b/src/Yolo3Detection.cpp
@@ -32,6 +32,9 @@ bool Yolo3Detection::init(const std::string& tensor_path, const int n_classes, c
         memcpy(yolo[i]->bias_h, yRT->bias, sizeof(dnnType)*num*nMasks*2);
         yolo[i]->input_dim = yolo[i]->output_dim = tk::dnn::dataDim_t(1, yRT->c, yRT->h, yRT->w);
         yolo[i]->classesNames = yRT->classesNames;
+        yolo[i]->nms_thresh = yRT->nms_thresh;
+        yolo[i]->nsm_kind = (tk::dnn::Yolo::nmsKind_t) yRT->nms_kind;
+        yolo[i]->new_coords = yRT->new_coords;
     }
 
     dets = tk::dnn::Yolo::allocateDetections(tk::dnn::Yolo::MAX_DETECTIONS, classes);
@@ -102,9 +105,9 @@ void Yolo3Detection::postprocess(const int bi, const bool mAP){
     nDets = 0;
     for(int i=0; i<netRT->pluginFactory->n_yolos; i++) {
         yolo[i]->dstData = rt_out[i];
-        yolo[i]->computeDetections(dets, nDets, netRT->input_dim.w, netRT->input_dim.h, confThreshold);
+        yolo[i]->computeDetections(dets, nDets, netRT->input_dim.w, netRT->input_dim.h, confThreshold, yolo[i]->new_coords);
     }
-    tk::dnn::Yolo::mergeDetections(dets, nDets, classes);
+    tk::dnn::Yolo::mergeDetections(dets, nDets, classes, yolo[0]->nms_thresh, yolo[0]->nsm_kind);
 
     // fill detected
     detected.clear();
diff --git a/tests/darknet/cfg/yolo4x.cfg b/tests/darknet/cfg/yolo4x.cfg
new file mode 100644
index 0000000..89f2564
--- /dev/null
+++ b/tests/darknet/cfg/yolo4x.cfg
@@ -0,0 +1,1427 @@
+[net]
+# Testing
+#batch=1
+#subdivisions=1
+# Training
+batch=64
+subdivisions=8
+width=672
+height=672
+channels=3
+momentum=0.949
+decay=0.0005
+angle=0
+saturation = 1.5
+exposure = 1.5
+hue=.1
+
+learning_rate=0.00261
+burn_in=1000
+max_batches = 500500
+policy=steps
+steps=400000,450000
+scales=.1,.1
+
+mosaic=1
+
+letter_box=1
+
+[convolutional]
+batch_normalize=1
+filters=32
+size=3
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=40
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=80
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-13
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-34
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-34
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+# Downsample
+
+[convolutional]
+batch_normalize=1
+filters=1280
+size=3
+stride=2
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=3
+stride=1
+pad=1
+activation=mish
+
+[shortcut]
+from=-3
+activation=linear
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1,-19
+
+[convolutional]
+batch_normalize=1
+filters=1280
+size=1
+stride=1
+pad=1
+activation=mish
+
+########################## 6 0 6 6 3
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+### SPP ###
+[maxpool]
+stride=1
+size=5
+
+[route]
+layers=-2
+
+[maxpool]
+stride=1
+size=9
+
+[route]
+layers=-4
+
+[maxpool]
+stride=1
+size=13
+
+[route]
+layers=-1,-3,-5,-6
+### End SPP ###
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[route]
+layers = -1, -15
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[upsample]
+stride=2
+
+[route]
+layers = 94
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1, -3
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[route]
+layers = -1, -8
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[upsample]
+stride=2
+
+[route]
+layers = 57
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -1, -3
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=160
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=160
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=160
+activation=mish
+
+[route]
+layers = -1, -8
+
+[convolutional]
+batch_normalize=1
+filters=160
+size=1
+stride=1
+pad=1
+activation=mish
+
+##########################
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 0,1,2
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=80
+num=9
+jitter=.1
+objectness_smooth=0
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=4.0
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=2
+pad=1
+filters=320
+activation=mish
+
+[route]
+layers = -1, -22
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=320
+activation=mish
+
+[route]
+layers = -1,-8
+
+[convolutional]
+batch_normalize=1
+filters=320
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 3,4,5
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=80
+num=9
+jitter=.1
+objectness_smooth=1
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=1.0
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
+
+[route]
+layers = -4
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=2
+pad=1
+filters=640
+activation=mish
+
+[route]
+layers = -1, -55
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[route]
+layers = -2
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=640
+activation=mish
+
+[route]
+layers = -1,-8
+
+[convolutional]
+batch_normalize=1
+filters=640
+size=1
+stride=1
+pad=1
+activation=mish
+
+[convolutional]
+batch_normalize=1
+size=3
+stride=1
+pad=1
+filters=1280
+activation=mish
+
+[convolutional]
+size=1
+stride=1
+pad=1
+filters=255
+activation=linear
+
+
+[yolo]
+mask = 6,7,8
+anchors = 12, 16, 19, 36, 40, 28, 36, 75, 76, 55, 72, 146, 142, 110, 192, 243, 459, 401
+classes=80
+num=9
+jitter=.1
+objectness_smooth=1
+ignore_thresh = .7
+truth_thresh = 1
+#random=1
+resize=1.5
+iou_thresh=0.2
+iou_normalizer=0.05
+cls_normalizer=0.5
+obj_normalizer=0.4
+iou_loss=ciou
+nms_kind=diounms
+beta_nms=0.6
+new_coords=1
diff --git a/tests/darknet/yolo4x.cpp b/tests/darknet/yolo4x.cpp
new file mode 100644
index 0000000..b9ad003
--- /dev/null
+++ b/tests/darknet/yolo4x.cpp
@@ -0,0 +1,36 @@
+#include<iostream>
+#include<vector>
+#include "tkdnn.h"
+#include "test.h"
+#include "DarknetParser.h"
+
+int main() {
+    std::string bin_path  = "yolo4x";
+    std::vector<std::string> input_bins = { 
+        bin_path + "/layers/input.bin"
+    };
+    std::vector<std::string> output_bins = {
+        bin_path + "/debug/layer168_out.bin",
+        bin_path + "/debug/layer185_out.bin",
+        bin_path + "/debug/layer202_out.bin"
+    };
+    std::string wgs_path  = bin_path + "/layers";
+    std::string cfg_path  = std::string(TKDNN_PATH) + "/tests/darknet/cfg/yolo4x.cfg";
+    std::string name_path = std::string(TKDNN_PATH) + "/tests/darknet/names/coco.names";
+    downloadWeightsifDoNotExist(input_bins[0], bin_path, "https://cloud.hipert.unimore.it/s/BLPpiAigZJLorQD/download");
+
+
+
+    // parse darknet network
+    tk::dnn::Network *net = tk::dnn::darknetParser(cfg_path, wgs_path, name_path);
+    net->print();
+
+    //convert network to tensorRT
+    tk::dnn::NetworkRT *netRT = new tk::dnn::NetworkRT(net, net->getNetworkRTName(bin_path.c_str()));
+    
+    int ret = testInference(input_bins, output_bins, net, netRT);
+    net->releaseLayers();
+    delete net;
+    delete netRT;
+    return ret;
+}