diff --git a/cnn.c b/cnn.c
index 3300878..318fb5c 100644
--- a/cnn.c
+++ b/cnn.c
@@ -43,8 +43,8 @@ float* convolution(Model model_w, Model model_b, const float* input_matrix, int
     float conv_temp; // 临时变量，用于存储卷积计算的中间结果
 
     //用于合并前的数组，具有32*64*50*50(第二层)的大小
-    float* _conv_rlst = (float *) malloc(sizeof (float) * model_w.channel * model_w.num_kernels * (cr_l * cr_l));
-    memset(_conv_rlst, 0, sizeof (float) * model_w.channel * model_w.num_kernels * (cr_l * cr_l));
+    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));
     //子图合并后的数组
     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));
@@ -63,32 +63,35 @@ float* convolution(Model model_w, Model model_b, const float* input_matrix, int
                                     * model_w.array[((c+k*model_w.channel)*3*3) + (x*3+y)];
                         }
                     }
-                    _conv_rlst[(c*model_w.num_kernels*cr_l*cr_l) + (k*cr_l*cr_l) + (row*cr_l+col)] = conv_temp;
+                    _conv_rlst[(k*cr_l*cr_l) + (row*cr_l+col)] = conv_temp;
                 }
            }
         }
-    }
-    //合并子图
-    {
+        //合并子图
         for(int k=0; k < model_w.num_kernels; k++) {
             for (int row = 0; row < cr_l; row++) {
                 for (int col = 0; col < cr_l; col++) {
-                    conv_temp = 0; // 每个输出像素初始化为0
-                    for (int c = 0; c < model_w.channel; c++) {
-                        conv_temp += _conv_rlst[(c * model_w.num_kernels * cr_l * cr_l) + (k * cr_l * cr_l) + (row * cr_l + col)];
-                    }
-                    // 加上对应卷积核的偏置
-                    conv_temp += model_b.array[k];
-                    // 激活函数：ReLU（将小于0的值设为0）
-                    if (conv_temp > 0)
-                        conv_rlst[(k * (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[(k * (cr_l * cr_l)) + (row * cr_l) + (col)] = 0; // 否则存入0
+                    conv_rlst[(k*cr_l*cr_l) + (row*cr_l+col)] += _conv_rlst[(k*cr_l*cr_l) + (row*cr_l+col)];
                 }
             }
         }
     }
+    for(int k=0; k < model_w.num_kernels; k++) {
+        for (int row = 0; row < cr_l; row++) {
+            for (int col = 0; col < cr_l; col++) {
+                conv_temp = conv_rlst[(k * cr_l * cr_l) + (row * cr_l + col)];
+                // 加上对应卷积核的偏置
+                conv_temp += model_b.array[k];
+                // 激活函数：ReLU（将小于0的值设为0）
+                if (conv_temp > 0)
+                    conv_rlst[(k * (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[(k * (cr_l * cr_l)) + (row * cr_l) + (col)] = 0; // 否则存入0
+            }
+        }
+    }
     free(_conv_rlst);
+    _conv_rlst = NULL;
     return conv_rlst;
 }