Harshvardhan Chandirasekar
GitHub
@@ -203,6 +203,7 @@ All models from darknet are now parsed directly from cfg, you still need to expo
|
||||
relu
|
||||
leaky
|
||||
mish
|
||||
logistic
|
||||
</details>
|
||||
|
||||
## Run the demo
|
||||
@@ -225,7 +226,7 @@ Once you have successfully created your rt file, run the demo:
|
||||
```
|
||||
In general the demo program takes 7 parameters:
|
||||
```
|
||||
./demo <network-rt-file> <path-to-video> <kind-of-network> <number-of-classes> <n-batches> <show-flag>
|
||||
./demo <network-rt-file> <path-to-video> <kind-of-network> <number-of-classes> <n-batches> <show-flag> <conf-thresh>
|
||||
```
|
||||
where
|
||||
* ```<network-rt-file>``` is the rt file generated by a test
|
||||
@@ -361,7 +362,8 @@ This demo also creates a json file named ```net_name_COCO_res.json``` containing
|
||||
| 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 <sup>9</sup> | [COCO 2017](http://cocodataset.org/) | 80 | 416x416 | [weights](https://cloud.hipert.unimore.it/s/iRnc4pSqmx78gJs/download) |
|
||||
| yolo4x | Yolov4x-mish <sup>9</sup> | [COCO 2017](http://cocodataset.org/) | 80 | 672x672 | [weights](https://cloud.hipert.unimore.it/s/BLPpiAigZJLorQD/download) |
|
||||
| yolo4x | Yolov4x-mish <sup>9</sup> | [COCO 2017](http://cocodataset.org/) | 80 | 640x640 | [weights](https://cloud.hipert.unimore.it/s/5MFjtNtgbDGdJEo/download) |
|
||||
| yolo4x-cps | Scaled Yolov4 <sup>10</sup> | [COCO 2017](http://cocodataset.org/) | 80 | 512x512 | [weights](https://cloud.hipert.unimore.it/s/AfzHE4BfTeEm2gH/download) |
|
||||
|
||||
### tkDNN on Windows 10 (experimental)
|
||||
|
||||
@@ -463,3 +465,4 @@ It is recommended to use Nvidia Driver(465+),Cuda unknown errors have been obser
|
||||
7. Wang, Chien-Yao, et al. "CSPNet: A New Backbone that can Enhance Learning Capability of CNN." arXiv preprint arXiv:1911.11929 (2019).
|
||||
8. Bochkovskiy, Alexey, Chien-Yao Wang, and Hong-Yuan Mark Liao. "YOLOv4: Optimal Speed and Accuracy of Object Detection." arXiv preprint arXiv:2004.10934 (2020).
|
||||
9. Bochkovskiy, Alexey, "Yolo v4, v3 and v2 for Windows and Linux" (https://github.com/AlexeyAB/darknet)
|
||||
10. Wang, Chien-Yao, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. "Scaled-YOLOv4: Scaling Cross Stage Partial Network." arXiv preprint arXiv:2011.08036 (2020).
|
||||
|
||||
@@ -25,9 +25,9 @@ template<typename T> T readBUF(const char*& buffer)
|
||||
|
||||
using namespace nvinfer1;
|
||||
#include "pluginsRT/ActivationLeakyRT.h"
|
||||
#include "pluginsRT/ActivationLogisticRT.h"
|
||||
#include "pluginsRT/ActivationReLUCeilingRT.h"
|
||||
#include "pluginsRT/ActivationMishRT.h"
|
||||
#include "pluginsRT/ActivationLogisticRT.h"
|
||||
#include "pluginsRT/ReorgRT.h"
|
||||
#include "pluginsRT/RegionRT.h"
|
||||
#include "pluginsRT/RouteRT.h"
|
||||
|
||||
@@ -57,4 +57,4 @@ public:
|
||||
}
|
||||
|
||||
int size;
|
||||
};
|
||||
};
|
||||
|
||||
@@ -69,10 +69,11 @@ do
|
||||
echo -e "${ORANGE}Batch $TKDNN_BATCHSIZE ${NC}"
|
||||
|
||||
test_net mnist
|
||||
./test_imuodom &>> $out_file
|
||||
print_output $? imuodom
|
||||
# ./test_imuodom &>> $out_file
|
||||
# print_output $? imuodom
|
||||
|
||||
test_net yolo4
|
||||
test_net yolo4-csp
|
||||
test_net yolo4x
|
||||
test_net yolo4_berkeley
|
||||
test_net yolo4tiny
|
||||
|
||||
+1
-1
@@ -56,7 +56,7 @@ dnnType* Activation::infer(dataDim_t &dim, dnnType* srcData) {
|
||||
else if(act_mode == ACTIVATION_LOGISTIC) {
|
||||
activationLOGISTICForward(srcData, dstData, dim.tot());
|
||||
|
||||
}else {
|
||||
} else {
|
||||
dnnType alpha = dnnType(1);
|
||||
dnnType beta = dnnType(0);
|
||||
checkCUDNN( cudnnActivationForward(net->cudnnHandle,
|
||||
|
||||
@@ -667,6 +667,11 @@ IPlugin* PluginFactory::createPlugin(const char* layerName, const void* serialDa
|
||||
a->size = readBUF<int>(buf);
|
||||
return a;
|
||||
}
|
||||
if(name.find("ActivationLogistic") == 0) {
|
||||
ActivationLogisticRT *a = new ActivationLogisticRT();
|
||||
a->size = readBUF<int>(buf);
|
||||
return a;
|
||||
}
|
||||
if(name.find("ActivationCReLU") == 0) {
|
||||
float activationReluTemp = readBUF<float>(buf);
|
||||
ActivationReLUCeiling* a = new ActivationReLUCeiling(activationReluTemp);
|
||||
|
||||
@@ -96,7 +96,6 @@ dnnType* Yolo::infer(dataDim_t &dim, dnnType* srcData) {
|
||||
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);
|
||||
|
||||
index = entry_index(b, n*dim.w*dim.h, 4, classes, input_dim, output_dim);
|
||||
activationLOGISTICForward(srcData + index, dstData + index, (1+classes)*dim.w*dim.h);
|
||||
}
|
||||
|
||||
@@ -1276,4 +1276,4 @@ iou_loss=ciou
|
||||
nms_kind=diounms
|
||||
beta_nms=0.6
|
||||
new_coords=1
|
||||
max_delta=2
|
||||
max_delta=2
|
||||
|
||||
@@ -1433,4 +1433,4 @@ iou_loss=ciou
|
||||
nms_kind=diounms
|
||||
beta_nms=0.6
|
||||
new_coords=1
|
||||
max_delta=2
|
||||
max_delta=2
|
||||
|
||||
@@ -6,28 +6,26 @@
|
||||
|
||||
int main() {
|
||||
std::string bin_path = "yolo4-csp";
|
||||
std::vector<std::string> input_bins = {
|
||||
bin_path + "/layers/input.bin"
|
||||
std::vector<std::string> input_bins = {
|
||||
bin_path + "/layers/input.bin"
|
||||
};
|
||||
std::vector<std::string> output_bins = {
|
||||
bin_path + "/debug/layer144_out.bin",
|
||||
bin_path + "/debug/layer159_out.bin",
|
||||
bin_path + "/debug/layer174_out.bin"
|
||||
bin_path + "/debug/layer144_out.bin",
|
||||
bin_path + "/debug/layer159_out.bin",
|
||||
bin_path + "/debug/layer174_out.bin"
|
||||
};
|
||||
std::string wgs_path = bin_path + "/layers";
|
||||
std::string cfg_path = std::string(TKDNN_PATH) + "/tests/darknet/cfg/yolo4-csp.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/AfzHE4BfTeEm2gH/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;
|
||||
|
||||
Reference in New Issue
Block a user