diff --git a/cnn.c b/cnn.c
index 4a3f872..94de085 100644
--- a/cnn.c
+++ b/cnn.c
@@ -26,43 +26,37 @@ float* expand(const float* old_matrix, u8 old_matrix_length, u8 layer){
 //返回卷积的结果
 float* convolution(Model model_w, Model model_b, const float* input_matrix, u8 input_matrix_length){
     // 初始化卷积层参数
-    u8 c_rl = input_matrix_length - 2;
+    u8 im_l = input_matrix_length;
+    u8 cr_l = input_matrix_length - 2;
     float conv_temp; // 临时变量，用于存储卷积计算的中间结果
-    float* conv_rlst = (float *) malloc(sizeof (float) * model_w.num_kernels * model_w.layer * (c_rl*c_rl));
-    memset(conv_rlst, 0, sizeof (float) * model_w.num_kernels * model_w.layer * (c_rl*c_rl));
+    float* conv_rlst = (float *) malloc(sizeof (float) * model_w.num_kernels * (cr_l * cr_l));
+    memset(conv_rlst, 0, sizeof (float) * model_w.num_kernels * (cr_l * cr_l));
     // 遍历30个卷积核（假设有30个通道）
+
+    for(u8 l=0;l<model_w.layer;l++){
         for(u8 n=0; n<model_w.num_kernels; n++){
-            for(u8 l=0;l<model_w.layer;l++){
-                // 遍历输出图像的每一行（卷积输出大小为24x24）
-                for(u8 row=0; row<(c_rl); row++) {
-                    // 遍历输出图像的每一列
-                    for (u8 col = 0; col < (input_matrix_length - 2); col++) {
-                        conv_temp = 0; // 每个输出像素初始化为0
-                        // 进行3x3的卷积操作
-                        for (u8 x = 0; x < 3; x++) {
-                            for (u8 y = 0; y < 3; y++) {
-                                // 将输入图像的对应像素与卷积核权重相乘，并累加到conv_temp
-                                conv_temp += input_matrix[model_w.layer*(input_matrix_length*input_matrix_length)+row*28
-                                                          +col+(x*(input_matrix_length)+y)] * model_w.array[n*(model_w.layer*3*3)+l*(3*3)+x*3+y];
-                            }
+            for(u8 row = 0; row < cr_l; row++) {
+                for (u8 col = 0; col < cr_l; col++) {
+                    conv_temp = 0; // 每个输出像素初始化为0
+                    // 进行3x3的卷积操作
+                    for (u8 x = 0; x < 3; x++) {
+                        for (u8 y = 0; y < 3; y++) {
+                            // 将输入图像的对应像素与卷积核权重相乘，并累加到conv_temp
+                            conv_temp += input_matrix[(l*(im_l*im_l)) + (row*im_l) + (col) + (x*im_l) + (y)] *
+                                    model_w.array[(x*3) + y + (n*(3*3))];
                         }
-                        // 加上对应卷积核的偏置
-                        conv_temp += model_b.array[n];
-                        // 激活函数：ReLU（将小于0的值设为0）
-                        if (conv_temp > 0)
-                            conv_rlst[row * (input_matrix_length - 2) + col +
-                                      n * (input_matrix_length - 2) * (input_matrix_length - 2) +
-                                      0
-                            ] = conv_temp; // 如果卷积结果大于0，存入结果数组
-                        else
-                            conv_rlst[row * (input_matrix_length - 2) + col +
-                                      n * (input_matrix_length - 2) * (input_matrix_length - 2) +
-                                      0
-                            ] = 0; // 否则存入0
                     }
+                    // 加上对应卷积核的偏置
+                    conv_temp += model_b.array[n];
+                    // 激活函数：ReLU（将小于0的值设为0）
+                    if (conv_temp > 0)
+                        conv_rlst[(n*(cr_l*cr_l)) + (row*cr_l) + (col)] = conv_temp; // 如果卷积结果大于0，存入结果数组
+                    else
+                        conv_rlst[(n*(cr_l*cr_l)) + (row*cr_l) + (col)] = 0; // 否则存入0
                 }
-            }
+           }
         }
+    }
     return conv_rlst;
 }
 
@@ -73,33 +67,33 @@ float* convolution(Model model_w, Model model_b, const float* input_matrix, u8 i
 //input_matrix_length 输入图像的边长：100
 //输出图像的边长：50
 //返回池化的结果
-float* pooling(u8 num_kernels, u8 area, const float* input_matrix, u8 input_matrix_length){
-
+float* pooling(Model model_w, const float* input_matrix, u8 input_matrix_length){
+    u8 im_l = input_matrix_length;
     float pool_temp = 0; // 临时变量，用于存储池化操作的最大值
-    float* pool_rslt = (float *) malloc(sizeof (float)*num_kernels*input_matrix_length*input_matrix_length);
-    memset(pool_rslt, 0, sizeof (float)*num_kernels*input_matrix_length*input_matrix_length);
+    float* pool_rslt = (float *) malloc(sizeof (float)*model_w.num_kernels*im_l*im_l);
+    memset(pool_rslt, 0, sizeof (float)*model_w.num_kernels*im_l*im_l);
     // 遍历30个通道（与卷积核数量相同）
-    for(u8 n=0; n<num_kernels; n++)
+    for(u8 n=0; n<model_w.num_kernels; n++)
     {
         // 遍历输入图像的每一行，步长为2（2x2的池化窗口）
-        for(u8 row=0; row<input_matrix_length; row=row+2)
+        for(u8 row=0; row<im_l; row=row+2)
         {
             // 遍历输入图像的每一列，步长为2
-            for(u8 col=0; col<input_matrix_length; col=col+2)
+            for(u8 col=0; col<im_l; col=col+2)
             {
                 pool_temp = 0; // 每个池化区域的最大值初始化为0
                 // 进行2x2的最大池化操作
-                for(u8 x=0; x<area; x++)
+                for(u8 x=0; x<2; x++)
                 {
-                    for(u8 y=0; y<area; y++)
+                    for(u8 y=0; y<2; y++)
                     {
                         // 更新当前池化区域的最大值
-                        if(pool_temp <= input_matrix[row*input_matrix_length+col+x*input_matrix_length+y+n*(input_matrix_length*input_matrix_length)])
-                            pool_temp = input_matrix[row*input_matrix_length+col+x*input_matrix_length+y+n*(input_matrix_length*input_matrix_length)];
+                        if(pool_temp <= input_matrix[row*im_l+col+x*im_l+y+n*(im_l*im_l)])
+                            pool_temp = input_matrix[row*im_l+col+x*im_l+y+n*(im_l*im_l)];
                     }
                 }
                 // 将最大值存入池化结果数组
-                pool_rslt[(row/2)*(input_matrix_length/2)+col/2+n*((input_matrix_length/2)*(input_matrix_length/2))] = pool_temp;
+                pool_rslt[(row/2)*(im_l/2)+col/2+n*((im_l/2)*(im_l/2))] = pool_temp;
             }
         }
     }
@@ -131,20 +125,27 @@ int main(){
 
 //第一层：填充102 * 102
     float* expand_matrix_1 = expand(data.array, 100, 1);
-        print_rslt(expand_matrix_1, 102, (0*102*102));
+//        print_rslt(expand_matrix_1, 102, (1*102*102));
     float* conv_rlst_1 = convolution(conv1_weight,conv1_bias,expand_matrix_1, 102);
-        print_rslt(conv_rlst_1, 32, (1*100));
-//    float* pool_rslt_1 = pooling(32, 2, conv_rlst_1, 100);
-//
-////第二层：填充102 * 102
-//    float* expand_matrix_2 = expand(pool_rslt_1, 50, 32);
-//        print_rslt(expand_matrix_2, 52, (0*52*52));
-//    float* conv_rlst_2 = convolution(conv2_weight,conv2_bias,expand_matrix_2, 102);
-//        print_rslt(conv_rlst_2, 64, (1*50*50));
-//    float* pool_rslt_2 = pooling(64, 2, conv_rlst_2, 50);
-//
+//        print_rslt(conv_rlst_1, 100, (32*100*100));
+    float* pool_rslt_1 = pooling(conv1_weight, conv_rlst_1, 100);
+//        print_rslt(pool_rslt_1, 50, (32*50*50));
 
+//第二层：填充32 * 52 * 52
+    float* expand_matrix_2 = expand(pool_rslt_1, 50, 32);
+//        print_rslt(expand_matrix_2, 52, (1*52*52));
+    float* conv_rlst_2 = convolution(conv2_weight,conv2_bias,expand_matrix_2, 52);
+//        print_rslt(conv_rlst_2, 50, (1*50*50));
+    float* pool_rslt_2 = pooling(conv2_weight, conv_rlst_2, 50);
+//        print_rslt(pool_rslt_2, 25, (1*25*25));
 
+//第三层：填充 64 * 27 * 27
+    float* expand_matrix_3 = expand(pool_rslt_2, 25, 64);
+//        print_rslt(expand_matrix_2, 52, (1*52*52));
+    float* conv_rlst_3 = convolution(conv3_weight,conv3_bias,expand_matrix_3, 27);
+            print_rslt(conv_rlst_3, 25, (1*25*25));
+    float* pool_rslt_3 = pooling(conv3_weight, conv_rlst_3, 25);
+            print_rslt(pool_rslt_3, 25, (1*12*12));
 
 
 
diff --git a/cnn_model.c b/cnn_model.c
index 4a81e9d..cb87d66 100644
--- a/cnn_model.c
+++ b/cnn_model.c
@@ -361,8 +361,8 @@ void model_init(){
 	conv3_weight.name = "conv3_weight";
 	conv3_weight.array = modelmym_init(conv3_weight.name);
 	conv3_weight.maxlength = CONV3_WEIGHT_ARRSIZE;
-    conv2_weight.layer = 64;
-    conv2_weight.num_kernels = 128;
+    conv3_weight.layer = 64;
+    conv3_weight.num_kernels = 128;
 
 	fc1_bias.name = "fc1_bias";
 	fc1_bias.array = modelmym_init(fc1_bias.name);