voc
This commit is contained in:
Alessio
@@ -0,0 +1,258 @@
|
||||
[net]
|
||||
# Testing
|
||||
batch=1
|
||||
subdivisions=1
|
||||
# Training
|
||||
# batch=64
|
||||
# subdivisions=8
|
||||
height=416
|
||||
width=416
|
||||
channels=3
|
||||
momentum=0.9
|
||||
decay=0.0005
|
||||
angle=0
|
||||
saturation = 1.5
|
||||
exposure = 1.5
|
||||
hue=.1
|
||||
|
||||
learning_rate=0.001
|
||||
burn_in=1000
|
||||
max_batches = 80200
|
||||
policy=steps
|
||||
steps=40000,60000
|
||||
scales=.1,.1
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=32
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[maxpool]
|
||||
size=2
|
||||
stride=2
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=64
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[maxpool]
|
||||
size=2
|
||||
stride=2
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=64
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[maxpool]
|
||||
size=2
|
||||
stride=2
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=128
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[maxpool]
|
||||
size=2
|
||||
stride=2
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=256
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[maxpool]
|
||||
size=2
|
||||
stride=2
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=1024
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=1024
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=512
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
filters=1024
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
activation=leaky
|
||||
|
||||
|
||||
#######
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=1024
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=1024
|
||||
activation=leaky
|
||||
|
||||
[route]
|
||||
layers=-9
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
filters=64
|
||||
activation=leaky
|
||||
|
||||
[reorg]
|
||||
stride=2
|
||||
|
||||
[route]
|
||||
layers=-1,-4
|
||||
|
||||
[convolutional]
|
||||
batch_normalize=1
|
||||
size=3
|
||||
stride=1
|
||||
pad=1
|
||||
filters=1024
|
||||
activation=leaky
|
||||
|
||||
[convolutional]
|
||||
size=1
|
||||
stride=1
|
||||
pad=1
|
||||
filters=125
|
||||
activation=linear
|
||||
|
||||
|
||||
[region]
|
||||
anchors = 1.3221, 1.73145, 3.19275, 4.00944, 5.05587, 8.09892, 9.47112, 4.84053, 11.2364, 10.0071
|
||||
bias_match=1
|
||||
classes=20
|
||||
coords=4
|
||||
num=5
|
||||
softmax=1
|
||||
jitter=.3
|
||||
rescore=1
|
||||
|
||||
object_scale=5
|
||||
noobject_scale=1
|
||||
class_scale=1
|
||||
coord_scale=1
|
||||
|
||||
absolute=1
|
||||
thresh = .6
|
||||
random=1
|
||||
@@ -0,0 +1,150 @@
|
||||
#include<iostream>
|
||||
#include "tkdnn.h"
|
||||
|
||||
const char *input_bin = "../tests/yolo_voc/layers/input.bin";
|
||||
const char *c0_bin = "../tests/yolo_voc/layers/c0.bin";
|
||||
const char *c2_bin = "../tests/yolo_voc/layers/c2.bin";
|
||||
const char *c4_bin = "../tests/yolo_voc/layers/c4.bin";
|
||||
const char *c5_bin = "../tests/yolo_voc/layers/c5.bin";
|
||||
const char *c6_bin = "../tests/yolo_voc/layers/c6.bin";
|
||||
const char *c8_bin = "../tests/yolo_voc/layers/c8.bin";
|
||||
const char *c9_bin = "../tests/yolo_voc/layers/c9.bin";
|
||||
const char *c10_bin = "../tests/yolo_voc/layers/c10.bin";
|
||||
const char *c12_bin = "../tests/yolo_voc/layers/c12.bin";
|
||||
const char *c13_bin = "../tests/yolo_voc/layers/c13.bin";
|
||||
const char *c14_bin = "../tests/yolo_voc/layers/c14.bin";
|
||||
const char *c15_bin = "../tests/yolo_voc/layers/c15.bin";
|
||||
const char *c16_bin = "../tests/yolo_voc/layers/c16.bin";
|
||||
const char *c18_bin = "../tests/yolo_voc/layers/c18.bin";
|
||||
const char *c19_bin = "../tests/yolo_voc/layers/c19.bin";
|
||||
const char *c20_bin = "../tests/yolo_voc/layers/c20.bin";
|
||||
const char *c21_bin = "../tests/yolo_voc/layers/c21.bin";
|
||||
const char *c22_bin = "../tests/yolo_voc/layers/c22.bin";
|
||||
const char *c23_bin = "../tests/yolo_voc/layers/c23.bin";
|
||||
const char *c24_bin = "../tests/yolo_voc/layers/c24.bin";
|
||||
const char *c26_bin = "../tests/yolo_voc/layers/c26.bin";
|
||||
const char *c29_bin = "../tests/yolo_voc/layers/c29.bin";
|
||||
const char *c30_bin = "../tests/yolo_voc/layers/c30.bin";
|
||||
const char *g31_bin = "../tests/yolo_voc/layers/g31.bin";
|
||||
const char *output_bin = "../tests/yolo_voc/layers/output.bin";
|
||||
|
||||
int main() {
|
||||
|
||||
// Network layout
|
||||
tkDNN::dataDim_t dim(1, 3, 416, 416, 1);
|
||||
tkDNN::Network net(dim);
|
||||
|
||||
tkDNN::Conv2d c0 (&net, 32, 3, 3, 1, 1, 1, 1, c0_bin, true);
|
||||
tkDNN::Activation a0 (&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Pooling p1 (&net, 2, 2, 2, 2, tkDNN::POOLING_MAX);
|
||||
|
||||
tkDNN::Conv2d c2 (&net, 64, 3, 3, 1, 1, 1, 1, c2_bin, true);
|
||||
tkDNN::Activation a2 (&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Pooling p3 (&net, 2, 2, 2, 2, tkDNN::POOLING_MAX);
|
||||
|
||||
tkDNN::Conv2d c4 (&net, 128, 3, 3, 1, 1, 1, 1, c4_bin, true);
|
||||
tkDNN::Activation a4 (&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c5 (&net, 64, 1, 1, 1, 1, 0, 0, c5_bin, true);
|
||||
tkDNN::Activation a5 (&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c6 (&net, 128, 3, 3, 1, 1, 1, 1, c6_bin, true);
|
||||
tkDNN::Activation a6 (&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Pooling p7 (&net, 2, 2, 2, 2, tkDNN::POOLING_MAX);
|
||||
|
||||
tkDNN::Conv2d c8 (&net, 256, 3, 3, 1, 1, 1, 1, c8_bin, true);
|
||||
tkDNN::Activation a8 (&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c9 (&net, 128, 1, 1, 1, 1, 0, 0, c9_bin, true);
|
||||
tkDNN::Activation a9 (&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c10(&net, 256, 3, 3, 1, 1, 1, 1, c10_bin, true);
|
||||
tkDNN::Activation a10(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Pooling p11(&net, 2, 2, 2, 2, tkDNN::POOLING_MAX);
|
||||
|
||||
tkDNN::Conv2d c12(&net, 512, 3, 3, 1, 1, 1, 1, c12_bin, true);
|
||||
tkDNN::Activation a12(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c13(&net, 256, 1, 1, 1, 1, 0, 0, c13_bin, true);
|
||||
tkDNN::Activation a13(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c14(&net, 512, 3, 3, 1, 1, 1, 1, c14_bin, true);
|
||||
tkDNN::Activation a14(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c15(&net, 256, 1, 1, 1, 1, 0, 0, c15_bin, true);
|
||||
tkDNN::Activation a15(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c16(&net, 512, 3, 3, 1, 1, 1, 1, c16_bin, true);
|
||||
tkDNN::Activation a16(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Pooling p17(&net, 2, 2, 2, 2, tkDNN::POOLING_MAX);
|
||||
|
||||
tkDNN::Conv2d c18(&net, 1024, 3, 3, 1, 1, 1, 1, c18_bin, true);
|
||||
tkDNN::Activation a18(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c19(&net, 512, 1, 1, 1, 1, 0, 0, c19_bin, true);
|
||||
tkDNN::Activation a19(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c20(&net, 1024, 3, 3, 1, 1, 1, 1, c20_bin, true);
|
||||
tkDNN::Activation a20(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c21(&net, 512, 1, 1, 1, 1, 0, 0, c21_bin, true);
|
||||
tkDNN::Activation a21(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c22(&net, 1024, 3, 3, 1, 1, 1, 1, c22_bin, true);
|
||||
tkDNN::Activation a22(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c23(&net, 1024, 3, 3, 1, 1, 1, 1, c23_bin, true);
|
||||
tkDNN::Activation a23(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c24(&net, 1024, 3, 3, 1, 1, 1, 1, c24_bin, true);
|
||||
tkDNN::Activation a24(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
|
||||
tkDNN::Layer *m25_layers[1] = { &a16 };
|
||||
tkDNN::Route m25(&net, m25_layers, 1);
|
||||
tkDNN::Conv2d c26(&net, 64, 1, 1, 1, 1, 0, 0, c26_bin, true);
|
||||
tkDNN::Activation a26(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Reorg r27(&net, 2);
|
||||
|
||||
tkDNN::Layer *m28_layers[2] = { &r27, &a24 };
|
||||
tkDNN::Route m28(&net, m28_layers, 2);
|
||||
|
||||
tkDNN::Conv2d c29(&net, 1024, 3, 3, 1, 1, 1, 1, c29_bin, true);
|
||||
tkDNN::Activation a29(&net, tkDNN::ACTIVATION_LEAKY);
|
||||
tkDNN::Conv2d c30(&net, 125, 1, 1, 1, 1, 0, 0, c30_bin, false);
|
||||
tkDNN::Region g31(&net, 20, 4, 5);
|
||||
|
||||
tkDNN::RegionInterpret rI(dim, g31.output_dim, 20, 4, 5, 0.6f, g31_bin);
|
||||
|
||||
// Load input
|
||||
dnnType *data;
|
||||
dnnType *input_h;
|
||||
readBinaryFile(input_bin, dim.tot(), &input_h, &data);
|
||||
|
||||
//print network model
|
||||
net.print();
|
||||
|
||||
//convert network to tensorRT
|
||||
tkDNN::NetworkRT netRT(&net, "yolo_voc.rt");
|
||||
|
||||
dnnType *out_data, *out_data2; // cudnn output, tensorRT output
|
||||
|
||||
tkDNN::dataDim_t dim1 = dim; //input dim
|
||||
printCenteredTitle(" CUDNN inference ", '=', 30); {
|
||||
dim1.print();
|
||||
TIMER_START
|
||||
out_data = net.infer(dim1, data);
|
||||
TIMER_STOP
|
||||
dim1.print();
|
||||
}
|
||||
|
||||
tkDNN::dataDim_t dim2 = dim;
|
||||
printCenteredTitle(" TENSORRT inference ", '=', 30); {
|
||||
dim2.print();
|
||||
TIMER_START
|
||||
out_data2 = netRT.infer(dim2, data);
|
||||
TIMER_STOP
|
||||
dim2.print();
|
||||
}
|
||||
|
||||
printCenteredTitle(" CHECK RESULTS ", '=', 30);
|
||||
dnnType *out, *out_h;
|
||||
int out_dim = net.getOutputDim().tot();
|
||||
readBinaryFile(output_bin, out_dim, &out_h, &out);
|
||||
std::cout<<"CUDNN vs correct"; checkResult(out_dim, out_data, out);
|
||||
std::cout<<"TRT vs correct"; checkResult(out_dim, out_data2, out);
|
||||
std::cout<<"CUDNN vs TRT "; checkResult(out_dim, out_data, out_data2);
|
||||
|
||||
std::cout<<"\n\nDetected objects: \n";
|
||||
dnnType *output_h = new dnnType[rI.output_dim.tot()];
|
||||
checkCuda(cudaMemcpy(output_h, out_data2,
|
||||
rI.output_dim.tot()*sizeof(dnnType), cudaMemcpyDeviceToHost));
|
||||
rI.interpretData(output_h);
|
||||
rI.showImageResult(input_h);
|
||||
return 0;
|
||||
}
|
||||
Reference in New Issue
Block a user