l = parse_convolutional(options, params);

l = parse_convolutional(options, params);函数主体如下所示

//进行卷积层操作，最后返回layer类型的结构体
convolutional_layer parse_convolutional(list *options, size_params params)
{
    int n = option_find_int(options, "filters",1);//设置卷积核个数，同时也是输出特征图个数
    int size = option_find_int(options, "size",1);//设置卷积核尺寸
    int stride = option_find_int(options, "stride",1);//设置卷积步长
    int pad = option_find_int_quiet(options, "pad",0);//设置卷积方式，=1,即是same填充
    int padding = option_find_int_quiet(options, "padding",0);//填充
    int groups = option_find_int_quiet(options, "groups", 1);//分组数
    if(pad) padding = size/2;//如果pad设置了，那么padding将边缘填充卷积核尺寸的一半，这里向下取整

    char *activation_s = option_find_str(options, "activation", "logistic");//选择激活函数，yolo使用的一般是leaky激活
    ACTIVATION activation = get_activation(activation_s);//设置选择的激活函数

    int batch,h,w,c;//设置高宽通道并进行赋值初始化
    h = params.h;
    w = params.w;
    c = params.c;
    batch=params.batch;//一次的图像数量
    if(!(h && w && c)) error("Layer before convolutional layer must output image.");//若有一个为0则报错
    int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);//是否进行批标准化处理
    int binary = option_find_int_quiet(options, "binary", 0);//是否对权重进行二值化，默认为0
    int xnor = option_find_int_quiet(options, "xnor", 0);//是否对权重以及输入进行二值化，默认为0
	//创建网络架构，具体参考[博客](https://blog.csdn.net/m0_37799466/article/details/106051226)
    convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,groups,size,stride,padding,activation, batch_normalize, binary, xnor, params.net->adam);
    layer.flipped = option_find_int_quiet(options, "flipped", 0);//图像翻转
    layer.dot = option_find_float_quiet(options, "dot", 0);//点乘

    return layer;
}

convolutional_layer结构体，即layer

struct layer{
    LAYER_TYPE type;
    ACTIVATION activation;
    COST_TYPE cost_type;
    void (*forward)   (struct layer, struct network);//声明了函数指针，指针forward等都是指向函数的指针
    void (*backward)  (struct layer, struct network);
    void (*update)    (struct layer, update_args);
    void (*forward_gpu)   (struct layer, struct network);
    void (*backward_gpu)  (struct layer, struct network);
    void (*update_gpu)    (struct layer, update_args);
    int batch_normalize;
    int shortcut;
    int batch;
    int forced;
    int flipped;
    int inputs;
    int outputs;
    int nweights;
    int nbiases;
    int extra;
    int truths;
    int h,w,c;
    int out_h, out_w, out_c;
    int n;
    int max_boxes;
    int groups;
    int size;
    int side;
    int stride;
    int reverse;
    int flatten;
    int spatial;
    int pad;
    int sqrt;
    int flip;
    int index;
    int binary;
    int xnor;
    int steps;
    int hidden;
    int truth;
    float smooth;
    float dot;
    float angle;
    float jitter;
    float saturation;
    float exposure;
    float shift;
    float ratio;
    float learning_rate_scale;
    float clip;
    int noloss;
    int softmax;
    int classes;
    int coords;
    int background;
    int rescore;
    int objectness;
    int joint;
    int noadjust;
    int reorg;
    int log;
    int tanh;
    int *mask;
    int total;

    float alpha;
    float beta;
    float kappa;

    float coord_scale;
    float object_scale;
    float noobject_scale;
    float mask_scale;
    float class_scale;
    int bias_match;
    int random;
    float ignore_thresh;
    float truth_thresh;
    float thresh;
    float focus;
    int classfix;
    int absolute;

    int onlyforward;
    int stopbackward;
    int dontload;
    int dontsave;
    int dontloadscales;
    int numload;

    float temperature;
    float probability;
    float scale;

    char  * cweights;
    int   * indexes;
    int   * input_layers;
    int   * input_sizes;
    int   * map;
    int   * counts;
    float ** sums;
    float * rand;
    float * cost;
    float * state;
    float * prev_state;
    float * forgot_state;
    float * forgot_delta;
    float * state_delta;
    float * combine_cpu;
    float * combine_delta_cpu;

    float * concat;
    float * concat_delta;

    float * binary_weights;

    float * biases;
    float * bias_updates;

    float * scales;
    float * scale_updates;

    float * weights;
    float * weight_updates;

    float * delta;
    float * output;
    float * loss;
    float * squared;
    float * norms;

    float * spatial_mean;
    float * mean;
    float * variance;

    float * mean_delta;
    float * variance_delta;

    float * rolling_mean;
    float * rolling_variance;

    float * x;
    float * x_norm;

    float * m;
    float * v;
    
    float * bias_m;
    float * bias_v;
    float * scale_m;
    float * scale_v;


    float *z_cpu;
    float *r_cpu;
    float *h_cpu;
    float * prev_state_cpu;

    float *temp_cpu;
    float *temp2_cpu;
    float *temp3_cpu;

    float *dh_cpu;
    float *hh_cpu;
    float *prev_cell_cpu;
    float *cell_cpu;
    float *f_cpu;
    float *i_cpu;
    float *g_cpu;
    float *o_cpu;
    float *c_cpu;
    float *dc_cpu; 

    float * binary_input;

    struct layer *input_layer;
    struct layer *self_layer;
    struct layer *output_layer;

    struct layer *reset_layer;
    struct layer *update_layer;
    struct layer *state_layer;

    struct layer *input_gate_layer;
    struct layer *state_gate_layer;
    struct layer *input_save_layer;
    struct layer *state_save_layer;
    struct layer *input_state_layer;
    struct layer *state_state_layer;

    struct layer *input_z_layer;
    struct layer *state_z_layer;

    struct layer *input_r_layer;
    struct layer *state_r_layer;

    struct layer *input_h_layer;
    struct layer *state_h_layer;
	
    struct layer *wz;
    struct layer *uz;
    struct layer *wr;
    struct layer *ur;
    struct layer *wh;
    struct layer *uh;
    struct layer *uo;
    struct layer *wo;
    struct layer *uf;
    struct layer *wf;
    struct layer *ui;
    struct layer *wi;
    struct layer *ug;
    struct layer *wg;

    tree *softmax_tree;

    size_t workspace_size;

#ifdef GPU
    int *indexes_gpu;

    float *z_gpu;
    float *r_gpu;
    float *h_gpu;

    float *temp_gpu;
    float *temp2_gpu;
    float *temp3_gpu;

    float *dh_gpu;
    float *hh_gpu;
    float *prev_cell_gpu;
    float *cell_gpu;
    float *f_gpu;
    float *i_gpu;
    float *g_gpu;
    float *o_gpu;
    float *c_gpu;
    float *dc_gpu; 

    float *m_gpu;
    float *v_gpu;
    float *bias_m_gpu;
    float *scale_m_gpu;
    float *bias_v_gpu;
    float *scale_v_gpu;

    float * combine_gpu;
    float * combine_delta_gpu;

    float * prev_state_gpu;
    float * forgot_state_gpu;
    float * forgot_delta_gpu;
    float * state_gpu;
    float * state_delta_gpu;
    float * gate_gpu;
    float * gate_delta_gpu;
    float * save_gpu;
    float * save_delta_gpu;
    float * concat_gpu;
    float * concat_delta_gpu;

    float * binary_input_gpu;
    float * binary_weights_gpu;

    float * mean_gpu;
    float * variance_gpu;

    float * rolling_mean_gpu;
    float * rolling_variance_gpu;

    float * variance_delta_gpu;
    float * mean_delta_gpu;

    float * x_gpu;
    float * x_norm_gpu;
    float * weights_gpu;
    float * weight_updates_gpu;
    float * weight_change_gpu;

    float * biases_gpu;
    float * bias_updates_gpu;
    float * bias_change_gpu;

    float * scales_gpu;
    float * scale_updates_gpu;
    float * scale_change_gpu;

    float * output_gpu;
    float * loss_gpu;
    float * delta_gpu;
    float * rand_gpu;
    float * squared_gpu;
    float * norms_gpu;
#ifdef CUDNN
    cudnnTensorDescriptor_t srcTensorDesc, dstTensorDesc;
    cudnnTensorDescriptor_t dsrcTensorDesc, ddstTensorDesc;
    cudnnTensorDescriptor_t normTensorDesc;
    cudnnFilterDescriptor_t weightDesc;
    cudnnFilterDescriptor_t dweightDesc;
    cudnnConvolutionDescriptor_t convDesc;
    cudnnConvolutionFwdAlgo_t fw_algo;
    cudnnConvolutionBwdDataAlgo_t bd_algo;
    cudnnConvolutionBwdFilterAlgo_t bf_algo;
#endif
#endif
};

ACTIVATION;枚举类型

typedef enum{
    LOGISTIC, RELU, RELIE, LINEAR, RAMP, TANH, PLSE, LEAKY, ELU, LOGGY, STAIR, HARDTAN, LHTAN, SELU
} ACTIVATION;

ACTIVATION activation = get_activation(activation_s);函数默认为RELU

ACTIVATION get_activation(char *s)
{
    if (strcmp(s, "logistic")==0) return LOGISTIC;
    if (strcmp(s, "loggy")==0) return LOGGY;
    if (strcmp(s, "relu")==0) return RELU;
    if (strcmp(s, "elu")==0) return ELU;
    if (strcmp(s, "selu")==0) return SELU;
    if (strcmp(s, "relie")==0) return RELIE;
    if (strcmp(s, "plse")==0) return PLSE;
    if (strcmp(s, "hardtan")==0) return HARDTAN;
    if (strcmp(s, "lhtan")==0) return LHTAN;
    if (strcmp(s, "linear")==0) return LINEAR;
    if (strcmp(s, "ramp")==0) return RAMP;
    if (strcmp(s, "leaky")==0) return LEAKY;
    if (strcmp(s, "tanh")==0) return TANH;
    if (strcmp(s, "stair")==0) return STAIR;
    fprintf(stderr, "Couldn't find activation function %s, going with ReLU\n", s);
    return RELU;
}