caffe-yolo 训练
【更新完这个之后，不再更行yolo的东西，应该也不会再使用yolo框架】
一、添加LeakyLayer层
leaky_layer.hpp
template <typename Dtype>
class LeakyLayer : public NeuronLayer{
public:
explicit LeakyLayer(const LayerParameter& param)
: NeuronLayer(param) {}
virtual void LayerSetUp(const vector leaky_layer.cpp
template <typename Dtype>
void LeakyLayer::LayerSetUp(const vector::LayerSetUp(bottom, top);
CHECK_NE(top[0], bottom[0]) << this->type() << " Layer does not "
"allow in-place computation.";
}
template <typename Dtype>
void LeakyLayer::Forward_cpu(
const vector leaky_layer.cu
template <typename Dtype>
__global__ void LeakyForward(const int n, const Dtype* in, Dtype* out){
CUDA_KERNEL_LOOP(index, n){
out[index] = in[index] > 0 ? in[index] : in[index]*0.1;
}
}
template <typename Dtype>
void LeakyLayer::Forward_gpu(
const vector<<>>(
count, bottom_data, top_data);
CUDA_POST_KERNEL_CHECK;
}
template<typename Dtype>
__global__ void LeakyBackward(const int n, const Dtype* bottom_data, Dtype* bottom_diff, const Dtype* top_diff){
CUDA_KERNEL_LOOP(index, n){
bottom_diff[index] = bottom_data[index] > 0 ? top_diff[index] : top_diff[index]*0.1;
}
}
template<typename Dtype>
void LeakyLayer::Backward_gpu(const vector<<>>(
count, bottom_data, bottom_diff, top_diff);
}
INSTANTIATE_LAYER_GPU_FUNCS(LeakyLayer); 二、添加detect层(loss)
detect_layer.hpp
template<typename Dtype>
class DetectLayer : public Layer{
public:
explicit DetectLayer(const LayerParameter& param);
virtual ~DetectLayer(){}
virtual void LayerSetUp(const vector detect_layer.cpp
template<typename Dtype>
Dtype lap(Dtype x1_min,Dtype x1_max,Dtype x2_min,Dtype x2_max){
if(x1_min < x2_min){
if(x1_max < x2_min){
return 0;
}else{
if(x1_max > x2_min){
if(x1_max < x2_max){
return x1_max - x2_min;
}else{
return x2_max - x2_min;
}
}else{
return 0;
}
}
}else{
if(x1_min < x2_max){
if(x1_max < x2_max)
return x1_max-x1_min;
else
return x2_max-x1_min;
}else{
return 0;
}
}
}
template<typename Dtype>
Dtype box_iou(const vector::DetectLayer(const LayerParameter& param) : Layer(param){
this->layer_param_.add_propagate_down(true);
this->layer_param_.add_propagate_down(false);
const DetectParameter& detect_param = this->layer_param_.detect_param();
classes = detect_param.classes();
coords = detect_param.coords();
rescore = detect_param.rescore();
side = detect_param.side();
num = detect_param.num();
softmax = detect_param.softmax();
sqrt = detect_param.sqrt();
jiter = detect_param.jitter();
object_scale = detect_param.object_scale();
noobject_scale = detect_param.noobject_scale();
class_scale = detect_param.class_scale();
coord_scale = detect_param.coord_scale();
}
template <typename Dtype>
void DetectLayer::LayerSetUp(const vector::LayerSetUp(bottom, top);
this->layer_param_.add_loss_weight(Dtype(1));
int inputs = (side*side*(((1+coords)*num)+classes));
CHECK_EQ(inputs, bottom[0]->count(1)) << "input dimensions error";
CHECK_EQ(top.size(), 1) << "top size must be 1";
}
template <typename Dtype>
void DetectLayer::Reshape(const vector::Forward_cpu(const vector::Backward_cpu(const vector 三、train的prototxt
yolo-train.prototxt
name: "yolo"
layer {
name: "data"
type: "Data"
top: "data"
include {
phase: TRAIN
}
data_param {
source: ""
batch_size: 15
backend: LMDB
}
transform_param {
mean_value:127.5
mean_value:127.5
mean_value:127.5
scale: 0.00784
}
}
layer {
name: "data"
type: "Data"
top: "data"
include {
phase: TEST
}
data_param {
source: ""
batch_size: 15
backend: LMDB
}
transform_param {
mean_value:127.5
mean_value:127.5
mean_value:127.5
scale: 0.00784
}
}
layer {
name: "truth"
type: "HDF5Data"
top: "label"
include {
phase: TRAIN
}
hdf5_data_param {
source: ""
batch_size: 15
}
}
layer {
name: "truth"
type: "HDF5Data"
top: "label"
include {
phase: TEST
}
hdf5_data_param {
source: ""
batch_size: 15
}
}
layer{
name: "conv1"
type: "Convolution"
bottom: "data"
top: "conv1"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 64
kernel_size: 7
stride: 2
pad: 3
}
}
layer{
name: "Leaky1"
type: "Leaky"
bottom: "conv1"
top: "Leaky1"
}
layer{
name: "pool1"
type: "Pooling"
bottom: "Leaky1"
top: "pool1"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer{
name: "conv2"
type: "Convolution"
bottom: "pool1"
top: "conv2"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 192
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky2"
type: "Leaky"
bottom: "conv2"
top: "Leaky2"
}
layer{
name: "pool2"
type: "Pooling"
bottom: "Leaky2"
top: "pool2"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer{
name: "conv3"
type: "Convolution"
bottom: "pool2"
top: "conv3"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 128
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky3"
type: "Leaky"
bottom: "conv3"
top: "Leaky3"
}
layer{
name: "conv4"
type: "Convolution"
bottom: "Leaky3"
top: "conv4"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 256
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky4"
type: "Leaky"
bottom: "conv4"
top: "Leaky4"
}
layer{
name: "conv5"
type: "Convolution"
bottom: "Leaky4"
top: "conv5"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 256
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky5"
type: "Leaky"
bottom: "conv5"
top: "Leaky5"
}
layer{
name: "conv6"
type: "Convolution"
bottom: "Leaky5"
top: "conv6"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 512
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky6"
type: "Leaky"
bottom: "conv6"
top: "Leaky6"
}
layer{
name: "pool3"
type: "Pooling"
bottom: "Leaky6"
top: "pool3"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer{
name: "conv7"
type: "Convolution"
bottom: "pool3"
top: "conv7"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 256
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky7"
type: "Leaky"
bottom: "conv7"
top: "Leaky7"
}
layer{
name: "conv8"
type: "Convolution"
bottom: "Leaky7"
top: "conv8"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 512
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky8"
type: "Leaky"
bottom: "conv8"
top: "Leaky8"
}
layer{
name: "conv9"
type: "Convolution"
bottom: "Leaky8"
top: "conv9"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 256
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky9"
type: "Leaky"
bottom: "conv9"
top: "Leaky9"
}
layer{
name: "conv10"
type: "Convolution"
bottom: "Leaky9"
top: "conv10"
convolution_param{
num_output: 512
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky10"
type: "Leaky"
bottom: "conv10"
top: "Leaky10"
}
layer{
name: "conv11"
type: "Convolution"
bottom: "Leaky10"
top: "conv11"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 256
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky11"
type: "Leaky"
bottom: "conv11"
top: "Leaky11"
}
layer{
name: "conv12"
type: "Convolution"
bottom: "Leaky11"
top: "conv12"
convolution_param{
num_output:512
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky12"
type: "Leaky"
bottom: "conv12"
top: "Leaky12"
}
layer{
name: "conv13"
type: "Convolution"
bottom: "Leaky12"
top: "conv13"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 256
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky13"
type: "Leaky"
bottom: "conv13"
top: "Leaky13"
}
layer{
name: "conv14"
type: "Convolution"
bottom: "Leaky13"
top: "conv14"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 512
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky14"
type: "Leaky"
bottom: "conv14"
top: "Leaky14"
}
layer{
name: "conv15"
type: "Convolution"
bottom: "Leaky14"
top: "conv15"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 512
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky15"
type: "Leaky"
bottom: "conv15"
top: "Leaky15"
}
layer{
name: "conv16"
type: "Convolution"
bottom: "Leaky15"
top: "conv16"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 1024
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky16"
type: "Leaky"
bottom: "conv16"
top: "Leaky16"
}
layer{
name: "pool4"
type: "Pooling"
bottom: "Leaky16"
top: "pool4"
pooling_param {
pool: MAX
kernel_size: 2
stride: 2
}
}
layer{
name: "conv17"
type: "Convolution"
bottom: "pool4"
top: "conv17"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 512
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky17"
type: "Leaky"
bottom: "conv17"
top: "Leaky17"
}
layer{
name: "conv18"
type: "Convolution"
bottom: "Leaky17"
top: "conv18"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 1024
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky18"
type: "Leaky"
bottom: "conv18"
top: "Leaky18"
}
layer{
name: "conv19"
type: "Convolution"
bottom: "Leaky18"
top: "conv19"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 512
kernel_size: 1
stride: 1
pad: 0
}
}
layer{
name: "Leaky19"
type: "Leaky"
bottom: "conv19"
top: "Leaky19"
}
layer{
name: "conv20"
type: "Convolution"
bottom: "Leaky19"
top: "conv20"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 1024
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky20"
type: "Leaky"
bottom: "conv20"
top: "Leaky20"
}
layer{
name: "conv21"
type: "Convolution"
bottom: "Leaky20"
top: "conv21"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 1024
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky21"
type: "Leaky"
bottom: "conv21"
top: "Leaky21"
}
layer{
name: "conv22"
type: "Convolution"
bottom: "Leaky21"
top: "conv22"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 1024
kernel_size: 3
stride: 2
pad: 1
}
}
layer{
name: "Leaky22"
type: "Leaky"
bottom: "conv22"
top: "Leaky22"
}
layer{
name: "conv23"
type: "Convolution"
bottom: "Leaky22"
top: "conv23"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 1024
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky23"
type: "Leaky"
bottom: "conv23"
top: "Leaky23"
}
layer{
name: "conv24"
type: "Convolution"
bottom: "Leaky23"
top: "conv24"
param {
lr_mult: 1
}
param {
lr_mult: 2
}
convolution_param{
num_output: 1024
kernel_size: 3
stride: 1
pad: 1
}
}
layer{
name: "Leaky24"
type: "Leaky"
bottom: "conv24"
top: "Leaky24"
}
layer {
name: "connect1"
type: "InnerProduct"
bottom: "Leaky24"
top: "connect1"
param {
lr_mult: 10
}
param {
lr_mult: 20
}
inner_product_param {
num_output: 4096
}
}
layer{
name: "Leaky25"
type: "Leaky"
bottom: "connect1"
top: "Leaky25"
}
layer {
name: "connect2_add"
type: "InnerProduct"
bottom: "Leaky25"
top: "connect2_add"
param {
lr_mult: 10
}
param {
lr_mult: 20
}
inner_product_param {
num_output: 637
weight_filler {
type: "uniform"
max: 1
min: -1
}
bias_filler {
type: "constant"
}
}
}
layer {
name: "detect"
type: "Detect"
top: "loss"
bottom: "connect2_add"
bottom: "label"
detect_param {
classes: 3
}
}