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

yolo3 debug start

Browse Source
This commit is contained in:
Francesco Gatti
2018-12-19 19:39:31 +01:00
parent dc55874f14
commit bc0ea65766
4 changed files with 841 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/yolo3_berkeley/yolo3_berkeley.cfg
+785
View File
@@ -0,0 +1,785 @@
[net]
# Testing
batch=1
subdivisions=1
# Training
#batch=32
#subdivisions=8
width=544
height=320
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 = 50200
policy=steps
steps=40000,45000
scales=.1,.1
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
# Downsample
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=128
size=3
stride=2
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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=256
size=3
stride=2
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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=512
size=3
stride=2
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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=2
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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
[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
[shortcut]
from=-3
activation=linear
######################
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=45
activation=linear
[yolo]
mask = 6,7,8
anchors = 8.2087,8.5515, 18.4134,20.3391, 40.2194,29.2990, 31.6137,69.2240, 69.8497,48.3838, 108.8817,76.6316, 96.5753,145.5743, 165.9182,117.4493, 215.7497,198.4648
classes=10
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 61
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=45
activation=linear
[yolo]
mask = 3,4,5
anchors = 8.2087,8.5515, 18.4134,20.3391, 40.2194,29.2990, 31.6137,69.2240, 69.8497,48.3838, 108.8817,76.6316, 96.5753,145.5743, 165.9182,117.4493, 215.7497,198.4648
classes=10
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 36
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=45
activation=linear
[yolo]
mask = 0,1,2
anchors = 8.2087,8.5515, 18.4134,20.3391, 40.2194,29.2990, 31.6137,69.2240, 69.8497,48.3838, 108.8817,76.6316, 96.5753,145.5743, 165.9182,117.4493, 215.7497,198.4648
classes=10
num=9
jitter=.3
ignore_thresh = .5
truth_thresh = 1
random=0
tests/yolo3_berkeley/yolo3_berkeley.cpp
+52
View File
@@ -0,0 +1,52 @@
#include<iostream>
#include "tkdnn.h"
const char *input_bin = "../tests/yolo3_berkeley/layers/input.bin";
const char *c0_bin = "../tests/yolo3_berkeley/layers/c0.bin";
const char *c1_bin = "../tests/yolo3_berkeley/layers/c1.bin";
const char *c2_bin = "../tests/yolo3_berkeley/layers/c2.bin";
const char *c3_bin = "../tests/yolo3_berkeley/layers/c3.bin";
const char *output_bin = "../tests/yolo3_berkeley/debug/layer3_out.bin";
int main() {
// Network layout
tk::dnn::dataDim_t dim(1, 3, 320, 544, 1);
tk::dnn::Network net(dim);
tk::dnn::Conv2d c0 (&net, 32, 3, 3, 1, 1, 1, 1, c0_bin, true);
tk::dnn::Activation a0 (&net, tk::dnn::ACTIVATION_LEAKY);
tk::dnn::Conv2d c1 (&net, 64, 3, 3, 2, 2, 1, 1, c1_bin, true);
tk::dnn::Activation a1 (&net, tk::dnn::ACTIVATION_LEAKY);
tk::dnn::Conv2d c2 (&net, 32, 1, 1, 1, 1, 0, 0, c2_bin, true);
tk::dnn::Activation a2 (&net, tk::dnn::ACTIVATION_LEAKY);
tk::dnn::Conv2d c3 (&net, 64, 3, 3, 1, 1, 1, 1, c3_bin, true);
tk::dnn::Activation a3 (&net, tk::dnn::ACTIVATION_LEAKY);
// Load input
dnnType *data;
dnnType *input_h;
readBinaryFile(input_bin, dim.tot(), &input_h, &data);
//print network model
net.print();
dnnType *out_data; // cudnn output
tk::dnn::dataDim_t dim1 = dim; //input dim
printCenteredTitle(" CUDNN inference ", '=', 30); {
dim1.print();
TIMER_START
out_data = net.infer(dim1, data);
TIMER_STOP
dim1.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);
return 0;
}