diff --git a/yolov5/common.hpp b/yolov5/common.hpp
index 2e1a1e8..5e96563 100644
--- a/yolov5/common.hpp
+++ b/yolov5/common.hpp
@@ -156,9 +156,11 @@ IScaleLayer* addBatchNorm2d(INetworkDefinition *network, std::map<std::string, W
     return scale_1;
 }
 
+
+
 ILayer* convBlock(INetworkDefinition *network, std::map<std::string, Weights>& weightMap, ITensor& input, int outch, int ksize, int s, int g, std::string lname) {
     Weights emptywts{ DataType::kFLOAT, nullptr, 0 };
-    int p = ksize / 2;
+    int p = ksize / 3;
     IConvolutionLayer* conv1 = network->addConvolutionNd(input, outch, DimsHW{ ksize, ksize }, weightMap[lname + ".conv.weight"], emptywts);
     assert(conv1);
     conv1->setStrideNd(DimsHW{ s, s });
@@ -255,6 +257,31 @@ ILayer* SPP(INetworkDefinition *network, std::map<std::string, Weights>& weightM
     auto cv2 = convBlock(network, weightMap, *cat->getOutput(0), c2, 1, 1, 1, lname + ".cv2");
     return cv2;
 }
+// SPPF
+ILayer* SPPF(INetworkDefinition *network, std::map<std::string, Weights>& weightMap, ITensor& input, int c1, int c2, int k,  std::string lname) {
+    int c_ = c1 / 2;
+    auto cv1 = convBlock(network, weightMap, input, c_, 1, 1, 1, lname + ".cv1");
+
+    auto pool1 = network->addPoolingNd(*cv1->getOutput(0), PoolingType::kMAX, DimsHW{ k, k });
+    pool1->setPaddingNd(DimsHW{ k / 2, k / 2 });
+    pool1->setStrideNd(DimsHW{ 1, 1 });
+    auto pool2 = network->addPoolingNd(*pool1->getOutput(0), PoolingType::kMAX, DimsHW{ k, k });
+    pool2->setPaddingNd(DimsHW{ k / 2, k / 2 });
+    pool2->setStrideNd(DimsHW{ 1, 1 });
+    auto pool3 = network->addPoolingNd(*pool2->getOutput(0), PoolingType::kMAX, DimsHW{ k, k });
+    pool3->setPaddingNd(DimsHW{ k / 2, k / 2 });
+    pool3->setStrideNd(DimsHW{ 1, 1 });
+    ITensor* inputTensors[] = { cv1->getOutput(0), pool1->getOutput(0), pool2->getOutput(0), pool3->getOutput(0) };
+    auto cat = network->addConcatenation(inputTensors, 4);
+    auto cv2 = convBlock(network, weightMap, *cat->getOutput(0), c2, 1, 1, 1, lname + ".cv2");
+    return cv2;
+}
+
+// 
+
+
+
+
 
 std::vector<std::vector<float>> getAnchors(std::map<std::string, Weights>& weightMap, std::string lname) {
     std::vector<std::vector<float>> anchors;
diff --git a/yolov5/yolov5.cpp b/yolov5/yolov5.cpp
index f27e2af..c898363 100644
--- a/yolov5/yolov5.cpp
+++ b/yolov5/yolov5.cpp
@@ -6,8 +6,8 @@
 #include "common.hpp"
 #include "utils.h"
 #include "calibrator.h"
-
-#define USE_FP16  // set USE_INT8 or USE_FP16 or USE_FP32
+#include <typeinfo>
+#define USE_FP32  // set USE_INT8 or USE_FP16 or USE_FP32
 #define DEVICE 0  // GPU id
 #define NMS_THRESH 0.4
 #define CONF_THRESH 0.5
@@ -35,30 +35,29 @@ static int get_depth(int x, float gd) {
     return std::max<int>(r, 1);
 }
 
+
+
 ICudaEngine* build_engine(unsigned int maxBatchSize, IBuilder* builder, IBuilderConfig* config, DataType dt, float& gd, float& gw, std::string& wts_name) {
     INetworkDefinition* network = builder->createNetworkV2(0U);
 
     // Create input tensor of shape {3, INPUT_H, INPUT_W} with name INPUT_BLOB_NAME
     ITensor* data = network->addInput(INPUT_BLOB_NAME, dt, Dims3{ 3, INPUT_H, INPUT_W });
     assert(data);
-
     std::map<std::string, Weights> weightMap = loadWeights(wts_name);
-
     /* ------ yolov5 backbone------ */
-    auto focus0 = focus(network, weightMap, *data, 3, get_width(64, gw), 3, "model.0");
-    auto conv1 = convBlock(network, weightMap, *focus0->getOutput(0), get_width(128, gw), 3, 2, 1, "model.1");
+    auto conv0 = convBlock(network, weightMap, *data,  get_width(64, gw), 6, 2, 1,  "model.0");
+    assert(conv0);
+    auto conv1 = convBlock(network, weightMap, *conv0->getOutput(0), get_width(128, gw), 3, 2, 1, "model.1");
     auto bottleneck_CSP2 = C3(network, weightMap, *conv1->getOutput(0), get_width(128, gw), get_width(128, gw), get_depth(3, gd), true, 1, 0.5, "model.2");
     auto conv3 = convBlock(network, weightMap, *bottleneck_CSP2->getOutput(0), get_width(256, gw), 3, 2, 1, "model.3");
-    auto bottleneck_csp4 = C3(network, weightMap, *conv3->getOutput(0), get_width(256, gw), get_width(256, gw), get_depth(9, gd), true, 1, 0.5, "model.4");
+    auto bottleneck_csp4 = C3(network, weightMap, *conv3->getOutput(0), get_width(256, gw), get_width(256, gw), get_depth(6, gd), true, 1, 0.5, "model.4");
     auto conv5 = convBlock(network, weightMap, *bottleneck_csp4->getOutput(0), get_width(512, gw), 3, 2, 1, "model.5");
     auto bottleneck_csp6 = C3(network, weightMap, *conv5->getOutput(0), get_width(512, gw), get_width(512, gw), get_depth(9, gd), true, 1, 0.5, "model.6");
     auto conv7 = convBlock(network, weightMap, *bottleneck_csp6->getOutput(0), get_width(1024, gw), 3, 2, 1, "model.7");
-    auto spp8 = SPP(network, weightMap, *conv7->getOutput(0), get_width(1024, gw), get_width(1024, gw), 5, 9, 13, "model.8");
-
+    auto bottleneck_csp8 = C3(network, weightMap, *conv7->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.8");
+    auto spp9 = SPPF(network, weightMap, *bottleneck_csp8->getOutput(0), get_width(1024, gw), get_width(1024, gw), 5, "model.9");
     /* ------ yolov5 head ------ */
-    auto bottleneck_csp9 = C3(network, weightMap, *spp8->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.9");
-    auto conv10 = convBlock(network, weightMap, *bottleneck_csp9->getOutput(0), get_width(512, gw), 1, 1, 1, "model.10");
-
+    auto conv10 = convBlock(network, weightMap, *spp9->getOutput(0), get_width(512, gw), 1, 1, 1, "model.10");
     auto upsample11 = network->addResize(*conv10->getOutput(0));
     assert(upsample11);
     upsample11->setResizeMode(ResizeMode::kNEAREST);
@@ -76,9 +75,7 @@ ICudaEngine* build_engine(unsigned int maxBatchSize, IBuilder* builder, IBuilder
 
     ITensor* inputTensors16[] = { upsample15->getOutput(0), bottleneck_csp4->getOutput(0) };
     auto cat16 = network->addConcatenation(inputTensors16, 2);
-
     auto bottleneck_csp17 = C3(network, weightMap, *cat16->getOutput(0), get_width(512, gw), get_width(256, gw), get_depth(3, gd), false, 1, 0.5, "model.17");
-
     /* ------ detect ------ */
     IConvolutionLayer* det0 = network->addConvolutionNd(*bottleneck_csp17->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.24.m.0.weight"], weightMap["model.24.m.0.bias"]);
     auto conv18 = convBlock(network, weightMap, *bottleneck_csp17->getOutput(0), get_width(256, gw), 3, 2, 1, "model.18");
@@ -91,11 +88,9 @@ ICudaEngine* build_engine(unsigned int maxBatchSize, IBuilder* builder, IBuilder
     auto cat22 = network->addConcatenation(inputTensors22, 2);
     auto bottleneck_csp23 = C3(network, weightMap, *cat22->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.23");
     IConvolutionLayer* det2 = network->addConvolutionNd(*bottleneck_csp23->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.24.m.2.weight"], weightMap["model.24.m.2.bias"]);
-
     auto yolo = addYoLoLayer(network, weightMap, "model.24", std::vector<IConvolutionLayer*>{det0, det1, det2});
     yolo->getOutput(0)->setName(OUTPUT_BLOB_NAME);
     network->markOutput(*yolo->getOutput(0));
-
     // Build engine
     builder->setMaxBatchSize(maxBatchSize);
     config->setMaxWorkspaceSize(16 * (1 << 20));  // 16MB
@@ -124,32 +119,28 @@ ICudaEngine* build_engine(unsigned int maxBatchSize, IBuilder* builder, IBuilder
 
     return engine;
 }
-
+//v6.0
 ICudaEngine* build_engine_p6(unsigned int maxBatchSize, IBuilder* builder, IBuilderConfig* config, DataType dt, float& gd, float& gw, std::string& wts_name) {
     INetworkDefinition* network = builder->createNetworkV2(0U);
-
     // Create input tensor of shape {3, INPUT_H, INPUT_W} with name INPUT_BLOB_NAME
     ITensor* data = network->addInput(INPUT_BLOB_NAME, dt, Dims3{ 3, INPUT_H, INPUT_W });
     assert(data);
-
     std::map<std::string, Weights> weightMap = loadWeights(wts_name);
-
     /* ------ yolov5 backbone------ */
-    auto focus0 = focus(network, weightMap, *data, 3, get_width(64, gw), 3, "model.0");
-    auto conv1 = convBlock(network, weightMap, *focus0->getOutput(0), get_width(128, gw), 3, 2, 1, "model.1");
+    auto conv0 = convBlock(network, weightMap, *data,  get_width(64, gw), 6, 2, 1,  "model.0");
+    auto conv1 = convBlock(network, weightMap, *conv0->getOutput(0), get_width(128, gw), 3, 2, 1, "model.1");
     auto c3_2 = C3(network, weightMap, *conv1->getOutput(0), get_width(128, gw), get_width(128, gw), get_depth(3, gd), true, 1, 0.5, "model.2");
     auto conv3 = convBlock(network, weightMap, *c3_2->getOutput(0), get_width(256, gw), 3, 2, 1, "model.3");
-    auto c3_4 = C3(network, weightMap, *conv3->getOutput(0), get_width(256, gw), get_width(256, gw), get_depth(9, gd), true, 1, 0.5, "model.4");
+    auto c3_4 = C3(network, weightMap, *conv3->getOutput(0), get_width(256, gw), get_width(256, gw), get_depth(6, gd), true, 1, 0.5, "model.4");
     auto conv5 = convBlock(network, weightMap, *c3_4->getOutput(0), get_width(512, gw), 3, 2, 1, "model.5");
     auto c3_6 = C3(network, weightMap, *conv5->getOutput(0), get_width(512, gw), get_width(512, gw), get_depth(9, gd), true, 1, 0.5, "model.6");
     auto conv7 = convBlock(network, weightMap, *c3_6->getOutput(0), get_width(768, gw), 3, 2, 1, "model.7");
     auto c3_8 = C3(network, weightMap, *conv7->getOutput(0), get_width(768, gw), get_width(768, gw), get_depth(3, gd), true, 1, 0.5, "model.8");
     auto conv9 = convBlock(network, weightMap, *c3_8->getOutput(0), get_width(1024, gw), 3, 2, 1, "model.9");
-    auto spp10 = SPP(network, weightMap, *conv9->getOutput(0), get_width(1024, gw), get_width(1024, gw), 3, 5, 7, "model.10");
-    auto c3_11 = C3(network, weightMap, *spp10->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.11");
-
+    auto c3_10 = C3(network, weightMap, *conv9->getOutput(0), get_width(1024, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.10");
+    auto sppf11 = SPPF(network, weightMap, *c3_10->getOutput(0), get_width(1024, gw), get_width(1024, gw), 5, "model.11");
     /* ------ yolov5 head ------ */
-    auto conv12 = convBlock(network, weightMap, *c3_11->getOutput(0), get_width(768, gw), 1, 1, 1, "model.12");
+    auto conv12 = convBlock(network, weightMap, *sppf11->getOutput(0), get_width(768, gw), 1, 1, 1, "model.12");
     auto upsample13 = network->addResize(*conv12->getOutput(0));
     assert(upsample13);
     upsample13->setResizeMode(ResizeMode::kNEAREST);
@@ -157,7 +148,6 @@ ICudaEngine* build_engine_p6(unsigned int maxBatchSize, IBuilder* builder, IBuil
     ITensor* inputTensors14[] = { upsample13->getOutput(0), c3_8->getOutput(0) };
     auto cat14 = network->addConcatenation(inputTensors14, 2);
     auto c3_15 = C3(network, weightMap, *cat14->getOutput(0), get_width(1536, gw), get_width(768, gw), get_depth(3, gd), false, 1, 0.5, "model.15");
-
     auto conv16 = convBlock(network, weightMap, *c3_15->getOutput(0), get_width(512, gw), 1, 1, 1, "model.16");
     auto upsample17 = network->addResize(*conv16->getOutput(0));
     assert(upsample17);
@@ -166,7 +156,6 @@ ICudaEngine* build_engine_p6(unsigned int maxBatchSize, IBuilder* builder, IBuil
     ITensor* inputTensors18[] = { upsample17->getOutput(0), c3_6->getOutput(0) };
     auto cat18 = network->addConcatenation(inputTensors18, 2);
     auto c3_19 = C3(network, weightMap, *cat18->getOutput(0), get_width(1024, gw), get_width(512, gw), get_depth(3, gd), false, 1, 0.5, "model.19");
-
     auto conv20 = convBlock(network, weightMap, *c3_19->getOutput(0), get_width(256, gw), 1, 1, 1, "model.20");
     auto upsample21 = network->addResize(*conv20->getOutput(0));
     assert(upsample21);
@@ -175,22 +164,18 @@ ICudaEngine* build_engine_p6(unsigned int maxBatchSize, IBuilder* builder, IBuil
     ITensor* inputTensors21[] = { upsample21->getOutput(0), c3_4->getOutput(0) };
     auto cat22 = network->addConcatenation(inputTensors21, 2);
     auto c3_23 = C3(network, weightMap, *cat22->getOutput(0), get_width(512, gw), get_width(256, gw), get_depth(3, gd), false, 1, 0.5, "model.23");
-
     auto conv24 = convBlock(network, weightMap, *c3_23->getOutput(0), get_width(256, gw), 3, 2, 1, "model.24");
     ITensor* inputTensors25[] = { conv24->getOutput(0), conv20->getOutput(0) };
     auto cat25 = network->addConcatenation(inputTensors25, 2);
     auto c3_26 = C3(network, weightMap, *cat25->getOutput(0), get_width(1024, gw), get_width(512, gw), get_depth(3, gd), false, 1, 0.5, "model.26");
-
     auto conv27 = convBlock(network, weightMap, *c3_26->getOutput(0), get_width(512, gw), 3, 2, 1, "model.27");
     ITensor* inputTensors28[] = { conv27->getOutput(0), conv16->getOutput(0) };
     auto cat28 = network->addConcatenation(inputTensors28, 2);
     auto c3_29 = C3(network, weightMap, *cat28->getOutput(0), get_width(1536, gw), get_width(768, gw), get_depth(3, gd), false, 1, 0.5, "model.29");
-
     auto conv30 = convBlock(network, weightMap, *c3_29->getOutput(0), get_width(768, gw), 3, 2, 1, "model.30");
     ITensor* inputTensors31[] = { conv30->getOutput(0), conv12->getOutput(0) };
     auto cat31 = network->addConcatenation(inputTensors31, 2);
     auto c3_32 = C3(network, weightMap, *cat31->getOutput(0), get_width(2048, gw), get_width(1024, gw), get_depth(3, gd), false, 1, 0.5, "model.32");
-
     /* ------ detect ------ */
     IConvolutionLayer* det0 = network->addConvolutionNd(*c3_23->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.33.m.0.weight"], weightMap["model.33.m.0.bias"]);
     IConvolutionLayer* det1 = network->addConvolutionNd(*c3_26->getOutput(0), 3 * (Yolo::CLASS_NUM + 5), DimsHW{ 1, 1 }, weightMap["model.33.m.1.weight"], weightMap["model.33.m.1.bias"]);
@@ -200,7 +185,6 @@ ICudaEngine* build_engine_p6(unsigned int maxBatchSize, IBuilder* builder, IBuil
     auto yolo = addYoLoLayer(network, weightMap, "model.33", std::vector<IConvolutionLayer*>{det0, det1, det2, det3});
     yolo->getOutput(0)->setName(OUTPUT_BLOB_NAME);
     network->markOutput(*yolo->getOutput(0));
-
     // Build engine
     builder->setMaxBatchSize(maxBatchSize);
     config->setMaxWorkspaceSize(16 * (1 << 20));  // 16MB
@@ -217,10 +201,8 @@ ICudaEngine* build_engine_p6(unsigned int maxBatchSize, IBuilder* builder, IBuil
     std::cout << "Building engine, please wait for a while..." << std::endl;
     ICudaEngine* engine = builder->buildEngineWithConfig(*network, *config);
     std::cout << "Build engine successfully!" << std::endl;
-
     // Don't need the network any more
     network->destroy();
-
     // Release host memory
     for (auto& mem : weightMap)
     {