caffe-yolo 训练

23 篇文章 0 订阅
15 篇文章 0 订阅

【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<Dtype>{
public:
    explicit LeakyLayer(const LayerParameter& param)
       : NeuronLayer<Dtype>(param) {}
    virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
          const vector<Blob<Dtype>*>& top);
    virtual inline const char* type() const { return "Leaky"; }
    virtual inline int ExactNumBottomBlobs() const { return 1; }
    virtual inline int ExactNumTopBlobs() const { return 1; }
protected:
      virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
          const vector<Blob<Dtype>*>& top);
      virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
          const vector<Blob<Dtype>*>& top);
      virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
          const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom){};//ÔÝʱ»¹Ã»ÊµÏÖ
      virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
          const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
};

leaky_layer.cpp

template <typename Dtype>
void LeakyLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
          const vector<Blob<Dtype>*>& top) {
    NeuronLayer<Dtype>::LayerSetUp(bottom, top);
      CHECK_NE(top[0], bottom[0]) << this->type() << " Layer does not "
        "allow in-place computation.";
}

template <typename Dtype>
void LeakyLayer<Dtype>::Forward_cpu(
        const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
      const int count = top[0]->count();
      Dtype* top_data = top[0]->mutable_cpu_data();
      const Dtype* bottom_data = bottom[0]->cpu_data();
      for(int i = 0; i < count; ++i){
          if(bottom_data[i] > 0)
              top_data[i] = bottom_data[i];
          else
              top_data[i] = 0.1*bottom_data[i];
          //top_data[i] = bottom_data[i] > 0£¿ bottom_data[i]: (Dtype(0.1)*bottom_data[i]);
      }
}
#ifdef CPU_ONLY
STUB_GPU(LeakyLayer);
#endif
INSTANTIATE_CLASS(LeakyLayer);
REGISTER_LAYER_CLASS(Leaky);

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<Dtype>::Forward_gpu(
    const vector<Blob<Dtype>*>& bottom, const vector<Blob<Dtype>*>& top) {
  const int count = bottom[0]->count();
  const Dtype* bottom_data = bottom[0]->gpu_data();
  Dtype* top_data = top[0]->mutable_gpu_data();
  LeakyForward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
          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<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top,
          const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom){
    const int count = bottom[0]->count();
    Dtype* bottom_diff = bottom[0]->mutable_gpu_diff();
    const Dtype* top_diff = top[0]->mutable_gpu_diff();
    const Dtype* bottom_data = bottom[0]->gpu_data();
    LeakyBackward<Dtype><<<CAFFE_GET_BLOCKS(count), CAFFE_CUDA_NUM_THREADS>>>(
          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<Dtype>{
public:
    explicit DetectLayer(const LayerParameter& param);
    virtual ~DetectLayer(){}
    virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
            const vector<Blob<Dtype>*>& top);
    virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
            const vector<Blob<Dtype>*>& top);
    virtual inline const char* type() const { return "Detect";}
    virtual inline int ExactNumBottomBlobs() const {return 2;}
    virtual inline int ExactNumTopBlobs() const { return 1;}
protected:
    virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
            const vector<Blob<Dtype>*>& top);
    virtual void Backward_cpu(const vector<Blob<Dtype>*>& bottom,
            const vector<bool>& propagate_down,const vector<Blob<Dtype>*>& top);
    int classes;
    int coords;
    int rescore;
    int side;
    int num;
    bool softmax;
    bool sqrt;
    float jiter;
    float object_scale;
    float noobject_scale;
    float class_scale;
    float coord_scale;

};

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<Dtype> box1, const vector<Dtype> box2){
    Dtype lap_x = lap(box1[0]-box1[2]/2,box1[0]+box1[2]/2,box2[0]-box2[2]/2,box2[0]+box2[2]/2);
    Dtype lap_y = lap(box1[1]-box1[3]/2,box1[1]+box1[3]/2,box2[1]-box2[3]/2,box2[1]+box2[3]/2);

    Dtype are = box1[2]*box1[3]+box2[2]*box2[3]-lap_x*lap_y;
    if(are < 0.00001)
        return 0.0;
    else
        return (lap_x*lap_y)/are;
}

template <typename Dtype>
DetectLayer<Dtype>::DetectLayer(const LayerParameter& param) : Layer<Dtype>(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<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
        const vector<Blob<Dtype>*>& top){
    Layer<Dtype>::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<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
    const vector<Blob<Dtype>*>& top){
    vector<int> shape(0);
    top[0]->Reshape(shape);
}
template <typename Dtype>
void DetectLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
        const vector<Blob<Dtype>*>& top){
    int input_num_each = side*side*(((1+coords)*num)+classes);
    int batch = bottom[0]->num();
    int locations = side*side;
    const Dtype* truth = bottom[1]->cpu_data();
    const Dtype* input = bottom[0]->cpu_data();

    Dtype* delta = bottom[0]->mutable_cpu_diff();
    Dtype& cost = top[0]->mutable_cpu_data()[0];
    cost = Dtype(0.0);

    for(int i = 0; i < bottom[0]->count(); ++i){
        delta[i] = Dtype(0.0);
    }
    float avg_iou = 0;
    float avg_cat = 0;
    float avg_allcat = 0;
    float avg_obj = 0;
    float avg_anyobj = 0;
    int count = 0;
    for(int b = 0; b < batch; ++b){
        int input_index = b*input_num_each;
        for(int l = 0; l < locations; ++l){
            int truth_index = (b*locations+l)*(1+coords+classes);
            Dtype is_obj = truth[truth_index];
            for(int n = 0; n < num;++n){
                int delta_index = input_index + locations*classes + l*num + n;
                delta[delta_index] = noobject_scale*(0 - input[delta_index]);
                cost += noobject_scale*pow(input[delta_index],2);
                avg_anyobj += input[delta_index];
            }

            int best_index = 0;
            float best_iou = 0;
            float best_rmse = 400;

            if(is_obj < 0.0001) continue;

            int class_index = input_index + l*classes;
            for(int j = 0; j < classes; ++j){
                delta[class_index+j]= class_scale * (truth[truth_index+1+j] - input[class_index+j]);
                if(truth[truth_index+1+j]) avg_cat += input[class_index+j];
                avg_allcat += input[class_index+j];
            }//classes

            vector<float> truth_box;
            truth_box.push_back(float(truth[truth_index+1+classes]/side));
            truth_box.push_back(float(truth[truth_index+1+classes+1]/side));
            truth_box.push_back(float(truth[truth_index+1+classes+2]));
            truth_box.push_back(float(truth[truth_index+1+classes+3]));
            for(int n = 0; n < num; ++n){
                int box_index = input_index + locations*(classes+num)+(l*num+n)*coords;
                vector<float> out_box;
                out_box.push_back(float(input[box_index]/side));
                out_box.push_back(float(input[box_index+1]/side));
                if(sqrt){
                    out_box.push_back(float(input[box_index+2]*input[box_index+2]));
                    out_box.push_back(float(input[box_index+3]*input[box_index+3]));
                }else{
                    out_box.push_back(float(input[box_index+2]));
                    out_box.push_back(float(input[box_index+3]));
                }
                float iou = box_iou(truth_box, out_box);
                float rmse = (pow(truth_box[0]-out_box[0],2)+pow(truth_box[1]-out_box[1],2)+pow(truth_box[2]-out_box[2],2)+pow(truth_box[3]-out_box[3],2));
                if(best_iou > 0 || iou > 0){
                    if(iou > best_iou){
                        best_iou = iou;
                        best_index = n;
                    }
                }else{
                    if(rmse < best_rmse){
                        best_rmse = rmse;
                        best_index = n;
                    }
                }       
            }//for num
            int box_index = input_index + locations*(classes+num)+(l*num+best_index)*coords;
            int tbox_index = truth_index+1+classes;

            vector<float> best_box;
            best_box.push_back(float(input[box_index]/side));
            best_box.push_back(float(input[box_index+1]/side));
            if(sqrt){
                best_box.push_back(float(input[box_index+2]*input[box_index+2]));
                best_box.push_back(float(input[box_index+3]*input[box_index+3]));
            }else{
                best_box.push_back(float(input[box_index+2]));
                best_box.push_back(float(input[box_index+3]));
            }
            int p_index = input_index + locations*classes + l*num + best_index;
            cost -= noobject_scale*pow(input[p_index],2);
            cost += object_scale*pow(1-input[p_index],2);
            avg_obj += input[p_index];
            delta[p_index] = object_scale*(1. - input[p_index]);
            if(rescore){
                //delta[p_index] = object_scale*(best_iou - input[p_index]);
            }

            delta[box_index] = coord_scale*(truth[tbox_index]-input[box_index]);
            delta[box_index+1] = coord_scale*(truth[tbox_index+1]-input[box_index+1]);
            delta[box_index+2] = coord_scale*(truth[tbox_index+2]-input[box_index+2]);
            delta[box_index+3] = coord_scale*(truth[tbox_index+3]-input[box_index+3]);
            if(sqrt) {
                delta[box_index+2] = coord_scale*(std::sqrt(truth[tbox_index+2])-input[box_index+2]);
                delta[box_index+3] = coord_scale*(std::sqrt(truth[tbox_index+3])-input[box_index+3]);
            }
            cost += pow(1-best_iou, 2);
            avg_iou += best_iou;
            ++count;
        }//locations
    }//batch
    for(int i = 0; i < bottom[0]->count(); ++i){
        delta[i] = -delta[i];
    }
    //printf("Detection Avg IOU: %f, Pos Cat: %f, All Cat: %f, Pos Obj: %f, Any Obj: %f, count: %d\n", avg_iou, avg_cat, avg_allcat, avg_obj, avg_anyobj, count);
}
template <typename Dtype>
void DetectLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& bottom,
        const vector<bool>& propagate_down,const vector<Blob<Dtype>*>& top){
}

template float lap(float x1_min,float x1_max,float x2_min,float x2_max);
template double lap(double x1_min,double x1_max,double x2_min,double x2_max);
template float box_iou(const vector<float> box1, const vector<float> box2);
template double box_iou(const vector<double> box1, const vector<double> box2);

#ifdef CPU_ONLY
STUB_GPU(DetectLayer);
#endif
INSTANTIATE_CLASS(DetectLayer);
REGISTER_LAYER_CLASS(Detect);

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
  }
}
  • 4
    点赞
  • 12
    收藏
    觉得还不错? 一键收藏
  • 29
    评论
评论 29
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值