darknet源码学习：结构体network定义

最新推荐文章于 2022-07-29 16:41:01 发布

haimianjie2012

最新推荐文章于 2022-07-29 16:41:01 发布

阅读量532

点赞数

分类专栏： # darknet 文章标签： darknet

本文链接：https://blog.youkuaiyun.com/haimianjie2012/article/details/103312344

版权

darknet 专栏收录该内容

68 篇文章

订阅专栏

本文详细解析了深度学习网络的结构定义，包括网络参数、学习策略、输入输出配置及优化算法等关键信息，为理解复杂神经网络提供基础。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

network结构定义：

// network.h
typedef struct network {
    int n;
    int batch;
    uint64_t *seen;
    int *t;
    float epoch;
    int subdivisions;
    layer *layers;
    float *output;
    learning_rate_policy policy;

    float learning_rate;
    float learning_rate_min;
    float learning_rate_max;
    int batches_per_cycle;
    int batches_cycle_mult;
    float momentum;
    float decay;
    float gamma;
    float scale;
    float power;
    int time_steps;
    int step;
    int max_batches;
    int num_boxes;
    int train_images_num;
    float *seq_scales;
    float *scales;
    int   *steps;
    int num_steps;
    int burn_in;
    int cudnn_half;

    int adam;
    float B1;
    float B2;
    float eps;

    int inputs;
    int outputs;
    int truths;
    int notruth;
    int h, w, c;
    int max_crop;
    int min_crop;
    float max_ratio;
    float min_ratio;
    int center;
    int flip; // horizontal flip 50% probability augmentaiont for classifier training (default = 1)
    int blur;
    int mixup;
    int letter_box;
    float angle;
    float aspect;
    float exposure;
    float saturation;
    float hue;
    int random;
    int track;
    int augment_speed;
    int sequential_subdivisions;
    int init_sequential_subdivisions;
    int current_subdivision;
    int try_fix_nan;

    int gpu_index;
    tree *hierarchy;

    float *input;
    float *truth;
    float *delta;
    float *workspace;
    int train;
    int index;
    float *cost;
    float clip;

#ifdef GPU
    //float *input_gpu;
    //float *truth_gpu;
    float *delta_gpu;
    float *output_gpu;

    float *input_state_gpu;
    float *input_pinned_cpu;
    int input_pinned_cpu_flag;

    float **input_gpu;
    float **truth_gpu;
    float **input16_gpu;
    float **output16_gpu;
    size_t *max_input16_size;
    size_t *max_output16_size;
    int wait_stream;
#endif
} network;