mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity

ResNet working

Browse Source
This commit is contained in:
Davide Sapienza
2019-10-29 17:21:31 +01:00
parent e9ec582223
commit 02936fa928
5 changed files with 242 additions and 317 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/tkDNN/Layer.h
+3 -2
View File
@@ -225,6 +225,7 @@ public:
int winH, winW;
int strideH, strideW;
int paddingH, paddingW;
tkdnnPoolingMode_t pool_mode;
Pooling(Network *net, int winH, int winW,
int strideH, int strideW,
@@ -238,7 +239,6 @@ public:
protected:
cudnnPoolingDescriptor_t poolingDesc;
tkdnnPoolingMode_t pool_mode;
dnnType *tmpInputData, *tmpOutputData;
bool poolOn3d;
};
@@ -270,7 +270,8 @@ public:
virtual dnnType* infer(dataDim_t &dim, dnnType* srcData);
public:
Layer **layers; //ids of layers to be merged
static const int MAX_INPUT_LAYERS = 16;
Layer *layers[MAX_INPUT_LAYERS]; //ids of layers to be merged
int layers_n; //number of layers
};
src/LayerWgs.cpp
-18
View File
@@ -20,13 +20,6 @@ LayerWgs::LayerWgs(Network *net, int inputs, int outputs,
seek += inputs*outputs*kh*kw*kl;
readBinaryFile(weights_path.c_str(), outputs, &bias_h, &bias_d, seek);
std::cout<<"w:\n";
printDeviceVector(64, data_d, true);
std::cout<<"b:\n";
printDeviceVector(64, bias_d, true);
std::cout<<"step----------------------------------------\n";
this->batchnorm = batchnorm;
if(batchnorm) {
seek += outputs;
@@ -36,17 +29,6 @@ std::cout<<"step----------------------------------------\n";
seek += outputs;
readBinaryFile(weights_path.c_str(), outputs, &variance_h, &variance_d, seek);
std::cout<<"s:\n";
printDeviceVector(64, scales_d, true);
std::cout<<"m:\n";
printDeviceVector(64, mean_d, true);
std::cout<<"v:\n";
printDeviceVector(64, variance_d, true);
std::cout<<"END----------------------------------------\n";
float eps = CUDNN_BN_MIN_EPSILON;
power_h = new dnnType[outputs];
src/NetworkRT.cpp
+7 -1
View File
@@ -263,10 +263,16 @@ ILayer* NetworkRT::convert_layer(ITensor *input, Conv2d *l) {
ILayer* NetworkRT::convert_layer(ITensor *input, Pooling *l) {
//std::cout<<"convert Pooling\n";
PoolingType ptype;
if(l->pool_mode == tkdnnPoolingMode_t::POOLING_MAX) ptype = PoolingType::kMAX;
if(l->pool_mode == tkdnnPoolingMode_t::POOLING_AVERAGE) ptype = PoolingType::kAVERAGE;
if(l->pool_mode == tkdnnPoolingMode_t::POOLING_AVERAGE_EXCLUDE_PADDING) ptype = PoolingType::kMAX_AVERAGE_BLEND;
IPoolingLayer *lRT = networkRT->addPooling(*input,
PoolingType::kMAX, DimsHW{l->winH, l->winW});
ptype, DimsHW{l->winH, l->winW});
checkNULL(lRT);
lRT->setStride(DimsHW{l->strideH, l->strideW});
lRT->setPadding(DimsHW{l->paddingH, l->paddingW});
return lRT;
}
src/Route.cpp
+5 -2
View File
@@ -7,9 +7,12 @@ namespace tk { namespace dnn {
Route::Route(Network *net, Layer **layers, int layers_n) : Layer(net) {
this->layers = layers;
this->layers_n = layers_n;
if(layers_n > MAX_INPUT_LAYERS)
FatalError("Route: MAX INPUT LAYERS overload");
for(int i=0; i<layers_n; i++)
this->layers[i] = layers[i];
//get dims
output_dim.l = 1;
output_dim.c = 0;
tests/resnet101/resnet101.cpp
+227 -294
View File
@@ -5,150 +5,155 @@ const char *input_bin = "../tests/resnet101/debug/input.bin";
const char *conv1_bin = "../tests/resnet101/layers/conv1.bin";
//layer1
const char *layer1_0_conv1_bin = "../tests/resnet101/layers/layer1-0-conv1.bin";
const char *layer1_0_conv2_bin = "../tests/resnet101/layers/layer1-0-conv2.bin";
const char *layer1_0_conv3_bin = "../tests/resnet101/layers/layer1-0-conv3.bin";
const char *layer1_0_downsample_0_bin = "../tests/resnet101/layers/layer1-0-downsample-0.bin";
const char *layer1_bin[]={
"../tests/resnet101/layers/layer1-0-conv1.bin",
"../tests/resnet101/layers/layer1-0-conv2.bin",
"../tests/resnet101/layers/layer1-0-conv3.bin",
"../tests/resnet101/layers/layer1-0-downsample-0.bin",
const char *layer1_1_conv1_bin = "../tests/resnet101/layers/layer1-1-conv1.bin";
const char *layer1_1_conv2_bin = "../tests/resnet101/layers/layer1-1-conv2.bin";
const char *layer1_1_conv3_bin = "../tests/resnet101/layers/layer1-1-conv3.bin";
"../tests/resnet101/layers/layer1-1-conv1.bin",
"../tests/resnet101/layers/layer1-1-conv2.bin",
"../tests/resnet101/layers/layer1-1-conv3.bin",
const char *layer1_2_conv1_bin = "../tests/resnet101/layers/layer1-2-conv1.bin";
const char *layer1_2_conv2_bin = "../tests/resnet101/layers/layer1-2-conv2.bin";
const char *layer1_2_conv3_bin = "../tests/resnet101/layers/layer1-2-conv3.bin";
"../tests/resnet101/layers/layer1-2-conv1.bin",
"../tests/resnet101/layers/layer1-2-conv2.bin",
"../tests/resnet101/layers/layer1-2-conv3.bin"};
//layer2
const char *layer2_0_conv1_bin = "../tests/resnet101/layers/layer2-0-conv1.bin";
const char *layer2_0_conv2_bin = "../tests/resnet101/layers/layer2-0-conv2.bin";
const char *layer2_0_conv3_bin = "../tests/resnet101/layers/layer2-0-conv3.bin";
const char *layer2_0_downsample_0_bin = "../tests/resnet101/layers/layer2-0-downsample-0.bin";
const char *layer2_bin[]={
"../tests/resnet101/layers/layer2-0-conv1.bin",
"../tests/resnet101/layers/layer2-0-conv2.bin",
"../tests/resnet101/layers/layer2-0-conv3.bin",
"../tests/resnet101/layers/layer2-0-downsample-0.bin",
const char *layer2_1_conv1_bin = "../tests/resnet101/layers/layer2-1-conv1.bin";
const char *layer2_1_conv2_bin = "../tests/resnet101/layers/layer2-1-conv2.bin";
const char *layer2_1_conv3_bin = "../tests/resnet101/layers/layer2-1-conv3.bin";
"../tests/resnet101/layers/layer2-1-conv1.bin",
"../tests/resnet101/layers/layer2-1-conv2.bin",
"../tests/resnet101/layers/layer2-1-conv3.bin",
const char *layer2_2_conv1_bin = "../tests/resnet101/layers/layer2-2-conv1.bin";
const char *layer2_2_conv2_bin = "../tests/resnet101/layers/layer2-2-conv2.bin";
const char *layer2_2_conv3_bin = "../tests/resnet101/layers/layer2-2-conv3.bin";
const char *layer2_3_conv1_bin = "../tests/resnet101/layers/layer2-3-conv1.bin";
const char *layer2_3_conv2_bin = "../tests/resnet101/layers/layer2-3-conv2.bin";
const char *layer2_3_conv3_bin = "../tests/resnet101/layers/layer2-3-conv3.bin";
"../tests/resnet101/layers/layer2-2-conv1.bin",
"../tests/resnet101/layers/layer2-2-conv2.bin",
"../tests/resnet101/layers/layer2-2-conv3.bin",
"../tests/resnet101/layers/layer2-3-conv1.bin",
"../tests/resnet101/layers/layer2-3-conv2.bin",
"../tests/resnet101/layers/layer2-3-conv3.bin"
};
//layer3
const char *layer3_0_conv1_bin = "../tests/resnet101/layers/layer3-0-conv1.bin";
const char *layer3_0_conv2_bin = "../tests/resnet101/layers/layer3-0-conv2.bin";
const char *layer3_0_conv3_bin = "../tests/resnet101/layers/layer3-0-conv3.bin";
const char *layer3_0_downsample_0_bin = "../tests/resnet101/layers/layer3-0-downsample-0.bin";
const char *layer3_bin[]={
"../tests/resnet101/layers/layer3-0-conv1.bin",
"../tests/resnet101/layers/layer3-0-conv2.bin",
"../tests/resnet101/layers/layer3-0-conv3.bin",
"../tests/resnet101/layers/layer3-0-downsample-0.bin",
const char *layer3_1_conv1_bin = "../tests/resnet101/layers/layer3-1-conv1.bin";
const char *layer3_1_conv2_bin = "../tests/resnet101/layers/layer3-1-conv2.bin";
const char *layer3_1_conv3_bin = "../tests/resnet101/layers/layer3-1-conv3.bin";
"../tests/resnet101/layers/layer3-1-conv1.bin",
"../tests/resnet101/layers/layer3-1-conv2.bin",
"../tests/resnet101/layers/layer3-1-conv3.bin",
const char *layer3_2_conv1_bin = "../tests/resnet101/layers/layer3-2-conv1.bin";
const char *layer3_2_conv2_bin = "../tests/resnet101/layers/layer3-2-conv2.bin";
const char *layer3_2_conv3_bin = "../tests/resnet101/layers/layer3-2-conv3.bin";
"../tests/resnet101/layers/layer3-2-conv1.bin",
"../tests/resnet101/layers/layer3-2-conv2.bin",
"../tests/resnet101/layers/layer3-2-conv3.bin",
const char *layer3_3_conv1_bin = "../tests/resnet101/layers/layer3-3-conv1.bin";
const char *layer3_3_conv2_bin = "../tests/resnet101/layers/layer3-3-conv2.bin";
const char *layer3_3_conv3_bin = "../tests/resnet101/layers/layer3-3-conv3.bin";
"../tests/resnet101/layers/layer3-3-conv1.bin",
"../tests/resnet101/layers/layer3-3-conv2.bin",
"../tests/resnet101/layers/layer3-3-conv3.bin",
const char *layer3_4_conv1_bin = "../tests/resnet101/layers/layer3-4-conv1.bin";
const char *layer3_4_conv2_bin = "../tests/resnet101/layers/layer3-4-conv2.bin";
const char *layer3_4_conv3_bin = "../tests/resnet101/layers/layer3-4-conv3.bin";
"../tests/resnet101/layers/layer3-4-conv1.bin",
"../tests/resnet101/layers/layer3-4-conv2.bin",
"../tests/resnet101/layers/layer3-4-conv3.bin",
const char *layer3_5_conv1_bin = "../tests/resnet101/layers/layer3-5-conv1.bin";
const char *layer3_5_conv2_bin = "../tests/resnet101/layers/layer3-5-conv2.bin";
const char *layer3_5_conv3_bin = "../tests/resnet101/layers/layer3-5-conv3.bin";
"../tests/resnet101/layers/layer3-5-conv1.bin",
"../tests/resnet101/layers/layer3-5-conv2.bin",
"../tests/resnet101/layers/layer3-5-conv3.bin",
const char *layer3_6_conv1_bin = "../tests/resnet101/layers/layer3-6-conv1.bin";
const char *layer3_6_conv2_bin = "../tests/resnet101/layers/layer3-6-conv2.bin";
const char *layer3_6_conv3_bin = "../tests/resnet101/layers/layer3-6-conv3.bin";
"../tests/resnet101/layers/layer3-6-conv1.bin",
"../tests/resnet101/layers/layer3-6-conv2.bin",
"../tests/resnet101/layers/layer3-6-conv3.bin",
const char *layer3_7_conv1_bin = "../tests/resnet101/layers/layer3-7-conv1.bin";
const char *layer3_7_conv2_bin = "../tests/resnet101/layers/layer3-7-conv2.bin";
const char *layer3_7_conv3_bin = "../tests/resnet101/layers/layer3-7-conv3.bin";
"../tests/resnet101/layers/layer3-7-conv1.bin",
"../tests/resnet101/layers/layer3-7-conv2.bin",
"../tests/resnet101/layers/layer3-7-conv3.bin",
const char *layer3_8_conv1_bin = "../tests/resnet101/layers/layer3-8-conv1.bin";
const char *layer3_8_conv2_bin = "../tests/resnet101/layers/layer3-8-conv2.bin";
const char *layer3_8_conv3_bin = "../tests/resnet101/layers/layer3-8-conv3.bin";
"../tests/resnet101/layers/layer3-8-conv1.bin",
"../tests/resnet101/layers/layer3-8-conv2.bin",
"../tests/resnet101/layers/layer3-8-conv3.bin",
const char *layer3_9_conv1_bin = "../tests/resnet101/layers/layer3-9-conv1.bin";
const char *layer3_9_conv2_bin = "../tests/resnet101/layers/layer3-9-conv2.bin";
const char *layer3_9_conv3_bin = "../tests/resnet101/layers/layer3-9-conv3.bin";
"../tests/resnet101/layers/layer3-9-conv1.bin",
"../tests/resnet101/layers/layer3-9-conv2.bin",
"../tests/resnet101/layers/layer3-9-conv3.bin",
const char *layer3_10_conv1_bin = "../tests/resnet101/layers/layer3-10-conv1.bin";
const char *layer3_10_conv2_bin = "../tests/resnet101/layers/layer3-10-conv2.bin";
const char *layer3_10_conv3_bin = "../tests/resnet101/layers/layer3-10-conv3.bin";
"../tests/resnet101/layers/layer3-10-conv1.bin",
"../tests/resnet101/layers/layer3-10-conv2.bin",
"../tests/resnet101/layers/layer3-10-conv3.bin",
const char *layer3_11_conv1_bin = "../tests/resnet101/layers/layer3-11-conv1.bin";
const char *layer3_11_conv2_bin = "../tests/resnet101/layers/layer3-11-conv2.bin";
const char *layer3_11_conv3_bin = "../tests/resnet101/layers/layer3-11-conv3.bin";
"../tests/resnet101/layers/layer3-11-conv1.bin",
"../tests/resnet101/layers/layer3-11-conv2.bin",
"../tests/resnet101/layers/layer3-11-conv3.bin",
const char *layer3_12_conv1_bin = "../tests/resnet101/layers/layer3-12-conv1.bin";
const char *layer3_12_conv2_bin = "../tests/resnet101/layers/layer3-12-conv2.bin";
const char *layer3_12_conv3_bin = "../tests/resnet101/layers/layer3-12-conv3.bin";
"../tests/resnet101/layers/layer3-12-conv1.bin",
"../tests/resnet101/layers/layer3-12-conv2.bin",
"../tests/resnet101/layers/layer3-12-conv3.bin",
const char *layer3_13_conv1_bin = "../tests/resnet101/layers/layer3-13-conv1.bin";
const char *layer3_13_conv2_bin = "../tests/resnet101/layers/layer3-13-conv2.bin";
const char *layer3_13_conv3_bin = "../tests/resnet101/layers/layer3-13-conv3.bin";
"../tests/resnet101/layers/layer3-13-conv1.bin",
"../tests/resnet101/layers/layer3-13-conv2.bin",
"../tests/resnet101/layers/layer3-13-conv3.bin",
const char *layer3_14_conv1_bin = "../tests/resnet101/layers/layer3-14-conv1.bin";
const char *layer3_14_conv2_bin = "../tests/resnet101/layers/layer3-14-conv2.bin";
const char *layer3_14_conv3_bin = "../tests/resnet101/layers/layer3-14-conv3.bin";
"../tests/resnet101/layers/layer3-14-conv1.bin",
"../tests/resnet101/layers/layer3-14-conv2.bin",
"../tests/resnet101/layers/layer3-14-conv3.bin",
const char *layer3_15_conv1_bin = "../tests/resnet101/layers/layer3-15-conv1.bin";
const char *layer3_15_conv2_bin = "../tests/resnet101/layers/layer3-15-conv2.bin";
const char *layer3_15_conv3_bin = "../tests/resnet101/layers/layer3-15-conv3.bin";
"../tests/resnet101/layers/layer3-15-conv1.bin",
"../tests/resnet101/layers/layer3-15-conv2.bin",
"../tests/resnet101/layers/layer3-15-conv3.bin",
const char *layer3_16_conv1_bin = "../tests/resnet101/layers/layer3-16-conv1.bin";
const char *layer3_16_conv2_bin = "../tests/resnet101/layers/layer3-16-conv2.bin";
const char *layer3_16_conv3_bin = "../tests/resnet101/layers/layer3-16-conv3.bin";
"../tests/resnet101/layers/layer3-16-conv1.bin",
"../tests/resnet101/layers/layer3-16-conv2.bin",
"../tests/resnet101/layers/layer3-16-conv3.bin",
const char *layer3_17_conv1_bin = "../tests/resnet101/layers/layer3-17-conv1.bin";
const char *layer3_17_conv2_bin = "../tests/resnet101/layers/layer3-17-conv2.bin";
const char *layer3_17_conv3_bin = "../tests/resnet101/layers/layer3-17-conv3.bin";
"../tests/resnet101/layers/layer3-17-conv1.bin",
"../tests/resnet101/layers/layer3-17-conv2.bin",
"../tests/resnet101/layers/layer3-17-conv3.bin",
const char *layer3_18_conv1_bin = "../tests/resnet101/layers/layer3-18-conv1.bin";
const char *layer3_18_conv2_bin = "../tests/resnet101/layers/layer3-18-conv2.bin";
const char *layer3_18_conv3_bin = "../tests/resnet101/layers/layer3-18-conv3.bin";
"../tests/resnet101/layers/layer3-18-conv1.bin",
"../tests/resnet101/layers/layer3-18-conv2.bin",
"../tests/resnet101/layers/layer3-18-conv3.bin",
const char *layer3_19_conv1_bin = "../tests/resnet101/layers/layer3-19-conv1.bin";
const char *layer3_19_conv2_bin = "../tests/resnet101/layers/layer3-19-conv2.bin";
const char *layer3_19_conv3_bin = "../tests/resnet101/layers/layer3-19-conv3.bin";
"../tests/resnet101/layers/layer3-19-conv1.bin",
"../tests/resnet101/layers/layer3-19-conv2.bin",
"../tests/resnet101/layers/layer3-19-conv3.bin",
const char *layer3_20_conv1_bin = "../tests/resnet101/layers/layer3-20-conv1.bin";
const char *layer3_20_conv2_bin = "../tests/resnet101/layers/layer3-20-conv2.bin";
const char *layer3_20_conv3_bin = "../tests/resnet101/layers/layer3-20-conv3.bin";
"../tests/resnet101/layers/layer3-20-conv1.bin",
"../tests/resnet101/layers/layer3-20-conv2.bin",
"../tests/resnet101/layers/layer3-20-conv3.bin",
const char *layer3_21_conv1_bin = "../tests/resnet101/layers/layer3-21-conv1.bin";
const char *layer3_21_conv2_bin = "../tests/resnet101/layers/layer3-21-conv2.bin";
const char *layer3_21_conv3_bin = "../tests/resnet101/layers/layer3-21-conv3.bin";
"../tests/resnet101/layers/layer3-21-conv1.bin",
"../tests/resnet101/layers/layer3-21-conv2.bin",
"../tests/resnet101/layers/layer3-21-conv3.bin",
const char *layer3_22_conv1_bin = "../tests/resnet101/layers/layer3-22-conv1.bin";
const char *layer3_22_conv2_bin = "../tests/resnet101/layers/layer3-22-conv2.bin";
const char *layer3_22_conv3_bin = "../tests/resnet101/layers/layer3-22-conv3.bin";
"../tests/resnet101/layers/layer3-22-conv1.bin",
"../tests/resnet101/layers/layer3-22-conv2.bin",
"../tests/resnet101/layers/layer3-22-conv3.bin"};
//layer4
const char *layer4_0_conv1_bin = "../tests/resnet101/layers/layer4-0-conv1.bin";
const char *layer4_0_conv2_bin = "../tests/resnet101/layers/layer4-0-conv2.bin";
const char *layer4_0_conv3_bin = "../tests/resnet101/layers/layer4-0-conv3.bin";
const char *layer4_0_downsample_0_bin = "../tests/resnet101/layers/layer4-0-downsample-0.bin";
const char *layer4_bin[]={
"../tests/resnet101/layers/layer4-0-conv1.bin",
"../tests/resnet101/layers/layer4-0-conv2.bin",
"../tests/resnet101/layers/layer4-0-conv3.bin",
"../tests/resnet101/layers/layer4-0-downsample-0.bin",
const char *layer4_1_conv1_bin = "../tests/resnet101/layers/layer4-1-conv1.bin";
const char *layer4_1_conv2_bin = "../tests/resnet101/layers/layer4-1-conv2.bin";
const char *layer4_1_conv3_bin = "../tests/resnet101/layers/layer4-1-conv3.bin";
"../tests/resnet101/layers/layer4-1-conv1.bin",
"../tests/resnet101/layers/layer4-1-conv2.bin",
"../tests/resnet101/layers/layer4-1-conv3.bin",
const char *layer4_2_conv1_bin = "../tests/resnet101/layers/layer4-2-conv1.bin";
const char *layer4_2_conv2_bin = "../tests/resnet101/layers/layer4-2-conv2.bin";
const char *layer4_2_conv3_bin = "../tests/resnet101/layers/layer4-2-conv3.bin";
"../tests/resnet101/layers/layer4-2-conv1.bin",
"../tests/resnet101/layers/layer4-2-conv2.bin",
"../tests/resnet101/layers/layer4-2-conv3.bin"};
//final
const char *fc_bin = "../tests/resnet101/layers/fc.bin";
const char *output_bin = "../tests/resnet101/debug/layer1-0-relu.bin";
const char *output_bin = "../tests/resnet101/debug/fc.bin";
int main()
{
@@ -162,204 +167,132 @@ int main()
tk::dnn::Pooling maxpool4(&net, 3, 3, 2, 2, 1, 1, tk::dnn::POOLING_MAX);
//layer 1
tk::dnn::Conv2d layer1_0_conv1(&net, 64, 1, 1, 1, 1, 0, 0, layer1_0_conv1_bin, true);
tk::dnn::Activation relu1_0_1(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer1_0_conv2(&net, 64, 3, 3, 1, 1, 1, 1, layer1_0_conv2_bin, true);
tk::dnn::Activation relu1_0_2(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer1_0_conv3(&net, 256, 1, 1, 1, 1, 0, 0, layer1_0_conv3_bin, true);
int id_layer1_bin = 0;
tk::dnn::Layer *last = &maxpool4;
for(int i=0; i<3;i++)
{
tk::dnn::Conv2d *layer1_0_conv1 = new tk::dnn::Conv2d(&net, 64, 1, 1, 1, 1, 0, 0, layer1_bin[id_layer1_bin++], true);
tk::dnn::Activation *relu1_0_1 = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d *layer1_0_conv2 = new tk::dnn::Conv2d(&net, 64, 3, 3, 1, 1, 1, 1, layer1_bin[id_layer1_bin++], true);
tk::dnn::Activation *relu1_0_2 = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d *layer1_0_conv3 = new tk::dnn::Conv2d(&net, 256, 1, 1, 1, 1, 0, 0, layer1_bin[id_layer1_bin++], true);
if(i==0) {
tk::dnn::Layer *route_1_0_layers[1] = { last };
tk::dnn::Route *route_1_0 = new tk::dnn::Route(&net, route_1_0_layers, 1);
tk::dnn::Conv2d *layer1_0_downsample_0 = new tk::dnn::Conv2d(&net, 256, 1, 1, 1, 1, 0, 0, layer1_bin[id_layer1_bin++], true);
tk::dnn::Shortcut *s1_0 = new tk::dnn::Shortcut(&net, layer1_0_conv3);
} else {
tk::dnn::Shortcut *s1_0 = new tk::dnn::Shortcut(&net, last);
}
tk::dnn::Activation *layer1_0_relu = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
last = layer1_0_relu;
}
// tk::dnn::Activation *last_activation = (tk::dnn::Activation *) net.layers[net.num_layers-1];
// layer 2
int id_layer2_bin = 0;
for(int i=0; i<4;i++)
{
tk::dnn::Conv2d *layer1_0_conv1 = new tk::dnn::Conv2d(&net, 128, 1, 1, 1, 1, 0, 0, layer2_bin[id_layer2_bin++], true);
tk::dnn::Activation *relu1_0_1 = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d *layer1_0_conv2;
if(i==0)
layer1_0_conv2 = new tk::dnn::Conv2d(&net, 128, 3, 3, 2, 2, 1, 1, layer2_bin[id_layer2_bin++], true);
else
layer1_0_conv2 = new tk::dnn::Conv2d(&net, 128, 3, 3, 1, 1, 1, 1, layer2_bin[id_layer2_bin++], true);
tk::dnn::Activation *relu1_0_2 = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d *layer1_0_conv3 = new tk::dnn::Conv2d(&net, 512, 1, 1, 1, 1, 0, 0, layer2_bin[id_layer2_bin++], true);
if(i==0)
{
tk::dnn::Layer *route_1_0_layers[1] = { last };
tk::dnn::Route *route_1_0 = new tk::dnn::Route(&net, route_1_0_layers, 1);
tk::dnn::Conv2d *layer1_0_downsample_0 = new tk::dnn::Conv2d(&net, 512, 1, 1, 2, 2, 0, 0, layer2_bin[id_layer2_bin++], true);
tk::dnn::Shortcut *s1_0 = new tk::dnn::Shortcut(&net, layer1_0_conv3);
}
else
{
tk::dnn::Shortcut *s1_0 = new tk::dnn::Shortcut(&net, last);
}
tk::dnn::Activation *layer1_0_relu = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
last = layer1_0_relu;
}
tk::dnn::Layer *m83_layers[1] = { &maxpool4 };
tk::dnn::Route m83 (&net, m83_layers, 1);
tk::dnn::Conv2d layer1_0_downsample_0(&net, 256, 1, 1, 1, 1, 0, 0, layer1_0_downsample_0_bin, true);
tk::dnn::Shortcut s1_0 (&net, &layer1_0_conv3);
tk::dnn::Activation layer1_0_relu(&net, CUDNN_ACTIVATION_RELU);
/*
tk::dnn::Conv2d layer1_1_conv1(&net, 64, 1, 1, 1, 1, 1, 1, layer1_1_conv1_bin, true);
tk::dnn::Conv2d layer1_1_conv2(&net, 64, 3, 3, 1, 1, 1, 1, layer1_1_conv2_bin, true);
tk::dnn::Conv2d layer1_1_conv3(&net, 256, 1, 1, 1, 1, 1, 1, layer1_1_conv3_bin, true);
tk::dnn::Activation layer1_1_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer1_2_conv1(&net, 64, 1, 1, 1, 1, 1, 1, layer1_2_conv1_bin, true);
tk::dnn::Conv2d layer1_2_conv2(&net, 64, 3, 3, 1, 1, 1, 1, layer1_2_conv2_bin, true);
tk::dnn::Conv2d layer1_2_conv3(&net, 256, 1, 1, 1, 1, 1, 1, layer1_2_conv3_bin, true);
tk::dnn::Activation layer1_2_relu(&net, CUDNN_ACTIVATION_RELU);
//layer 2
tk::dnn::Conv2d layer2_0_conv1(&net, 128, 1, 1, 1, 1, 1, 1, layer2_0_conv1_bin, true);
tk::dnn::Conv2d layer2_0_conv2(&net, 128, 3, 3, 2, 2, 1, 1, layer2_0_conv2_bin, true);
tk::dnn::Conv2d layer2_0_conv3(&net, 512, 1, 1, 1, 1, 1, 1, layer2_0_conv3_bin, true);
tk::dnn::Activation layer2_0_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer2_0_downsample_0(&net, 512, 1, 1, 2, 2, 1, 1, layer2_0_downsample_0, true);
tk::dnn::Conv2d layer2_1_conv1(&net, 128, 1, 1, 1, 1, 1, 1, layer2_1_conv1_bin, true);
tk::dnn::Conv2d layer2_1_conv2(&net, 128, 3, 3, 1, 1, 1, 1, layer2_1_conv2_bin, true);
tk::dnn::Conv2d layer2_1_conv3(&net, 512, 1, 1, 1, 1, 1, 1, layer2_1_conv3_bin, true);
tk::dnn::Activation layer2_1_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer2_2_conv1(&net, 128, 1, 1, 1, 1, 1, 1, layer2_2_conv1_bin, true);
tk::dnn::Conv2d layer2_2_conv2(&net, 128, 3, 3, 1, 1, 1, 1, layer2_2_conv2_bin, true);
tk::dnn::Conv2d layer2_2_conv3(&net, 512, 1, 1, 1, 1, 1, 1, layer2_2_conv3_bin, true);
tk::dnn::Activation layer2_2_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer2_3_conv1(&net, 128, 1, 1, 1, 1, 1, 1, layer2_3_conv1_bin, true);
tk::dnn::Conv2d layer2_3_conv2(&net, 128, 3, 3, 1, 1, 1, 1, layer2_3_conv2_bin, true);
tk::dnn::Conv2d layer2_3_conv3(&net, 512, 1, 1, 1, 1, 1, 1, layer2_3_conv3_bin, true);
tk::dnn::Activation layer2_3_relu(&net, CUDNN_ACTIVATION_RELU);
//layer 3
tk::dnn::Conv2d layer3_0_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_0_conv1_bin, true);
tk::dnn::Conv2d layer3_0_conv2(&net, 256, 3, 3, 2, 2, 1, 1, layer3_0_conv2_bin, true);
tk::dnn::Conv2d layer3_0_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_0_conv3_bin, true);
tk::dnn::Activation layer3_0_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_0_downsample_0(&net, 1024, 1, 1, 2, 2, 1, 1, layer3_0_downsample_0, true);
tk::dnn::Conv2d layer3_1_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_1_conv1_bin, true);
tk::dnn::Conv2d layer3_1_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_1_conv2_bin, true);
tk::dnn::Conv2d layer3_1_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_1_conv3_bin, true);
tk::dnn::Activation layer3_1_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_2_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_2_conv1_bin, true);
tk::dnn::Conv2d layer3_2_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_2_conv2_bin, true);
tk::dnn::Conv2d layer3_2_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_2_conv3_bin, true);
tk::dnn::Activation layer3_2_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_3_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_3_conv1_bin, true);
tk::dnn::Conv2d layer3_3_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_3_conv2_bin, true);
tk::dnn::Conv2d layer3_3_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_3_conv3_bin, true);
tk::dnn::Activation layer3_3_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_4_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_4_conv1_bin, true);
tk::dnn::Conv2d layer3_4_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_4_conv2_bin, true);
tk::dnn::Conv2d layer3_4_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_4_conv3_bin, true);
tk::dnn::Activation layer3_4_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_5_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_5_conv1_bin, true);
tk::dnn::Conv2d layer3_5_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_5_conv2_bin, true);
tk::dnn::Conv2d layer3_5_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_5_conv3_bin, true);
tk::dnn::Activation layer3_5_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_6_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_6_conv1_bin, true);
tk::dnn::Conv2d layer3_6_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_6_conv2_bin, true);
tk::dnn::Conv2d layer3_6_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_6_conv3_bin, true);
tk::dnn::Activation layer3_6_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_7_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_7_conv1_bin, true);
tk::dnn::Conv2d layer3_7_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_7_conv2_bin, true);
tk::dnn::Conv2d layer3_7_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_7_conv3_bin, true);
tk::dnn::Activation layer3_7_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_8_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_8_conv1_bin, true);
tk::dnn::Conv2d layer3_8_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_8_conv2_bin, true);
tk::dnn::Conv2d layer3_8_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_8_conv3_bin, true);
tk::dnn::Activation layer3_8_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_9_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_9_conv1_bin, true);
tk::dnn::Conv2d layer3_9_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_9_conv2_bin, true);
tk::dnn::Conv2d layer3_9_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_9_conv3_bin, true);
tk::dnn::Activation layer3_9_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_10_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_10_conv1_bin, true);
tk::dnn::Conv2d layer3_10_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_10_conv2_bin, true);
tk::dnn::Conv2d layer3_10_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_10_conv3_bin, true);
tk::dnn::Activation layer3_10_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_11_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_11_conv1_bin, true);
tk::dnn::Conv2d layer3_11_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_11_conv2_bin, true);
tk::dnn::Conv2d layer3_11_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_11_conv3_bin, true);
tk::dnn::Activation layer3_11_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_12_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_12_conv1_bin, true);
tk::dnn::Conv2d layer3_12_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_12_conv2_bin, true);
tk::dnn::Conv2d layer3_12_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_12_conv3_bin, true);
tk::dnn::Activation layer3_12_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_13_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_13_conv1_bin, true);
tk::dnn::Conv2d layer3_13_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_13_conv2_bin, true);
tk::dnn::Conv2d layer3_13_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_13_conv3_bin, true);
tk::dnn::Activation layer3_13_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_14_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_14_conv1_bin, true);
tk::dnn::Conv2d layer3_14_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_14_conv2_bin, true);
tk::dnn::Conv2d layer3_14_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_14_conv3_bin, true);
tk::dnn::Activation layer3_14_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_15_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_15_conv1_bin, true);
tk::dnn::Conv2d layer3_15_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_15_conv2_bin, true);
tk::dnn::Conv2d layer3_15_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_15_conv3_bin, true);
tk::dnn::Activation layer3_15_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_16_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_16_conv1_bin, true);
tk::dnn::Conv2d layer3_16_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_16_conv2_bin, true);
tk::dnn::Conv2d layer3_16_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_16_conv3_bin, true);
tk::dnn::Activation layer3_16_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_17_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_17_conv1_bin, true);
tk::dnn::Conv2d layer3_17_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_17_conv2_bin, true);
tk::dnn::Conv2d layer3_17_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_17_conv3_bin, true);
tk::dnn::Activation layer3_17_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_18_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_18_conv1_bin, true);
tk::dnn::Conv2d layer3_18_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_18_conv2_bin, true);
tk::dnn::Conv2d layer3_18_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_18_conv3_bin, true);
tk::dnn::Activation layer3_18_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_19_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_19_conv1_bin, true);
tk::dnn::Conv2d layer3_19_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_19_conv2_bin, true);
tk::dnn::Conv2d layer3_19_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_19_conv3_bin, true);
tk::dnn::Activation layer3_19_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_20_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_20_conv1_bin, true);
tk::dnn::Conv2d layer3_20_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_20_conv2_bin, true);
tk::dnn::Conv2d layer3_20_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_20_conv3_bin, true);
tk::dnn::Activation layer3_20_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_21_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_21_conv1_bin, true);
tk::dnn::Conv2d layer3_21_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_21_conv2_bin, true);
tk::dnn::Conv2d layer3_21_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_21_conv3_bin, true);
tk::dnn::Activation layer3_21_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer3_22_conv1(&net, 256, 1, 1, 1, 1, 1, 1, layer3_22_conv1_bin, true);
tk::dnn::Conv2d layer3_22_conv2(&net, 256, 3, 3, 1, 1, 1, 1, layer3_22_conv2_bin, true);
tk::dnn::Conv2d layer3_22_conv3(&net, 1024, 1, 1, 1, 1, 1, 1, layer3_22_conv3_bin, true);
tk::dnn::Activation layer3_22_relu(&net, CUDNN_ACTIVATION_RELU);
//layer 4
tk::dnn::Conv2d layer4_0_conv1(&net, 512, 1, 1, 1, 1, 1, 1, layer4_0_conv1_bin, true);
tk::dnn::Conv2d layer4_0_conv2(&net, 512, 3, 3, 2, 2, 1, 1, layer4_0_conv2_bin, true);
tk::dnn::Conv2d layer4_0_conv3(&net, 2048, 1, 1, 1, 1, 1, 1, layer4_0_conv3_bin, true);
tk::dnn::Activation layer4_0_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer4_0_downsample_0(&net, 2048, 1, 1, 2, 2, 1, 1, layer4_0_downsample_0, true);
tk::dnn::Conv2d layer4_1_conv1(&net, 512, 1, 1, 1, 1, 1, 1, layer4_1_conv1_bin, true);
tk::dnn::Conv2d layer4_1_conv2(&net, 512, 3, 3, 1, 1, 1, 1, layer4_1_conv2_bin, true);
tk::dnn::Conv2d layer4_1_conv3(&net, 2048, 1, 1, 1, 1, 1, 1, layer4_1_conv3_bin, true);
tk::dnn::Activation layer4_1_relu(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d layer4_2_conv1(&net, 512, 1, 1, 1, 1, 1, 1, layer4_2_conv1_bin, true);
tk::dnn::Conv2d layer4_2_conv2(&net, 512, 3, 3, 1, 1, 1, 1, layer4_2_conv2_bin, true);
tk::dnn::Conv2d layer4_2_conv3(&net, 2048, 1, 1, 1, 1, 1, 1, layer4_2_conv3_bin, true);
tk::dnn::Activation layer4_2_relu(&net, CUDNN_ACTIVATION_RELU);
// layer 3
int id_layer3_bin = 0;
for(int i=0; i<23;i++)
{
tk::dnn::Conv2d *layer1_0_conv1 = new tk::dnn::Conv2d(&net, 256, 1, 1, 1, 1, 0, 0, layer3_bin[id_layer3_bin++], true);
tk::dnn::Activation *relu1_0_1 = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d *layer1_0_conv2;
if(i==0)
layer1_0_conv2 = new tk::dnn::Conv2d(&net, 256, 3, 3, 2, 2, 1, 1, layer3_bin[id_layer3_bin++], true);
else
layer1_0_conv2 = new tk::dnn::Conv2d(&net, 256, 3, 3, 1, 1, 1, 1, layer3_bin[id_layer3_bin++], true);
tk::dnn::Activation *relu1_0_2 = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d *layer1_0_conv3 = new tk::dnn::Conv2d(&net, 1024, 1, 1, 1, 1, 0, 0, layer3_bin[id_layer3_bin++], true);
if(i==0)
{
tk::dnn::Layer *route_1_0_layers[1] = { last };
tk::dnn::Route *route_1_0 = new tk::dnn::Route(&net, route_1_0_layers, 1);
tk::dnn::Conv2d *layer1_0_downsample_0 = new tk::dnn::Conv2d(&net, 1024, 1, 1, 2, 2, 0, 0, layer3_bin[id_layer3_bin++], true);
tk::dnn::Shortcut *s1_0 = new tk::dnn::Shortcut(&net, layer1_0_conv3);
}
else
{
tk::dnn::Shortcut *s1_0 = new tk::dnn::Shortcut(&net, last);
}
tk::dnn::Activation *layer1_0_relu = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
last = layer1_0_relu;
}
// layer 4
int id_layer4_bin = 0;
for(int i=0; i<3;i++)
{
tk::dnn::Conv2d *layer1_0_conv1 = new tk::dnn::Conv2d(&net, 512, 1, 1, 1, 1, 0, 0, layer4_bin[id_layer4_bin++], true);
tk::dnn::Activation *relu1_0_1 = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d *layer1_0_conv2;
if(i==0)
layer1_0_conv2 = new tk::dnn::Conv2d(&net, 512, 3, 3, 2, 2, 1, 1, layer4_bin[id_layer4_bin++], true);
else
layer1_0_conv2 = new tk::dnn::Conv2d(&net, 512, 3, 3, 1, 1, 1, 1, layer4_bin[id_layer4_bin++], true);
tk::dnn::Activation *relu1_0_2 = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
tk::dnn::Conv2d *layer1_0_conv3 = new tk::dnn::Conv2d(&net, 2048, 1, 1, 1, 1, 0, 0, layer4_bin[id_layer4_bin++], true);
if(i==0)
{
tk::dnn::Layer *route_1_0_layers[1] = { last };
tk::dnn::Route *route_1_0 = new tk::dnn::Route(&net, route_1_0_layers, 1);
tk::dnn::Conv2d *layer1_0_downsample_0 = new tk::dnn::Conv2d(&net, 2048, 1, 1, 2, 2, 0, 0, layer4_bin[id_layer4_bin++], true);
tk::dnn::Shortcut *s1_0 = new tk::dnn::Shortcut(&net, layer1_0_conv3);
}
else
{
tk::dnn::Shortcut *s1_0 = new tk::dnn::Shortcut(&net, last);
}
tk::dnn::Activation *layer1_0_relu = new tk::dnn::Activation(&net, CUDNN_ACTIVATION_RELU);
last = layer1_0_relu;
}
//final
tk::dnn::Pooling avgpool(&net, 3, 3, 2, 2, tk::dnn::POOLING_AVERAGE);
tk::dnn::Pooling avgpool(&net, 7, 7, 7, 7, 0, 0, tk::dnn::POOLING_AVERAGE);
tk::dnn::Dense fc(&net, 1000, fc_bin);
*/
// Load input
dnnType *data;
dnnType *input_h;
readBinaryFile(input_bin, dim.tot(), &input_h, &data);
printDeviceVector(64, data, true);
//printDeviceVector(64, data, true);
//print network model
net.print();
/*
//convert network to tensorRT
tk::dnn::NetworkRT netRT(&net, "resnet101.rt");
*/
tk::dnn::dataDim_t out_dim;
out_dim = net.layers[net.num_layers-1]->output_dim;
@@ -376,8 +309,8 @@ int main()
}
cudnn_out = net.layers[net.num_layers-1]->dstData;
printDeviceVector(64, cudnn_out, true);
/*
//printDeviceVector(64, cudnn_out, true);
tk::dnn::dataDim_t dim2 = dim;
printCenteredTitle(" TENSORRT inference ", '=', 30);
{
@@ -388,7 +321,7 @@ int main()
dim2.print();
}
rt_out = (dnnType *)netRT.buffersRT[1];
*/
printCenteredTitle(std::string(" RESNET CHECK RESULTS ").c_str(), '=', 30);
dnnType *out, *out_h;
@@ -396,11 +329,11 @@ int main()
readBinaryFile(output_bin, odim, &out_h, &out);
std::cout << "CUDNN vs correct";
checkResult(odim, cudnn_out, out);
/*
std::cout << "TRT vs correct";
checkResult(odim, rt_out, out);
std::cout << "CUDNN vs TRT ";
checkResult(odim, cudnn_out, rt_out);
*/
return 0;
}