Diff: main.cpp

Revision:

2:995d7426e3ba

Parent:

1:2d0abf41b7a3

--- a/main.cpp	Thu Jan 25 02:37:42 2018 +0000
+++ b/main.cpp	Tue Feb 11 00:55:05 2020 +0000
@@ -1,10 +1,10 @@
 /******************************************************************************
  *  NM500 NeuroShield Board SimpleScript
  *  Simple Test Script to understand how the neurons learn and recognize
- *  revision 1.1.3, 01/03, 2018
+ *  revision 1.1.5, 2020/02/11
  *  Copyright (c) 2017 nepes inc.
  *
- *  Please use the NeuroShield library v1.1.3 or later
+ *  Please use the NeuroShield library v1.1.4 or later
  ******************************************************************************/
 
 #include "mbed.h"
@@ -19,16 +19,42 @@
 DigitalOut sdcard_ss(D6);       // SDCARD_SSn
 DigitalOut arduino_con(D5);     // SPI_SEL
 
+uint8_t vector[NEURON_SIZE];
+uint16_t vector16[NEURON_SIZE];   
+uint16_t dists[READ_COUNT], cats[READ_COUNT], nids[READ_COUNT];
+uint16_t response_nbr, norm_lsup = 0;
+uint16_t fpga_version;
+
+void displayNeurons()
+{
+    uint16_t nm_ncr, nm_aif, nm_cat;
+    uint16_t ncount = hnn.getNcount();
+    printf("Display the neurons, ncount = %d\n", ncount);
+    uint16_t temp_nsr = hnn.getNsr();
+    hnn.setNsr(0x0010);
+    hnn.resetChain();
+    for (int i = 1; i <= ncount; i++) {
+        nm_ncr = hnn.getNcr();
+        hnn.readCompVector(vector16, VECTOR_LENGTH);
+        nm_aif = hnn.getAif();
+        nm_cat = hnn.getCat();
+        
+        printf("neuron#%d \tvector=", i);
+        for (int j = 0; j < VECTOR_LENGTH; j++) {
+            printf("%d, ", vector16[j]);
+        }
+        if (nm_cat & 0x8000) {
+            printf(" \tncr=%d \taif=%d \tcat=%d (degenerated)\n", nm_ncr, nm_aif, (nm_cat & 0x7FFF));
+        }
+        else {
+            printf(" \tncr=%d \taif=%d \tcat=%d\n", nm_ncr, nm_aif, nm_cat);
+        }
+    }
+    hnn.setNsr(temp_nsr);
+}
+
 int main()
 {
-    int i, j;
-    uint8_t value;
-    uint8_t vector[NEURON_SIZE];
-    uint16_t vector16[NEURON_SIZE];
-    uint16_t ncr, cat, aif, ncount, minif, response_nbr, norm_lsup = 0;
-    uint16_t dists[READ_COUNT], cats[READ_COUNT], nids[READ_COUNT];
-    uint16_t fpga_version;
-    
     arduino_con = LOW;
     sdcard_ss = HIGH;
     wait(0.5);
@@ -44,14 +70,14 @@
         else {
             printf("\n\n#### Unknown Board (Board v%d.0 / FPGA v%d.0) ####\n", ((fpga_version >> 4) & 0x000F), (fpga_version & 0x000F));
         }
-        printf("\nNM500 is initialized!\n");
-        printf("There are %d neurons\n", hnn.total_neurons);
+        printf("\nStart NM500 initialization...\n");
+        printf("  NM500 is initialized!\n");
+        printf("  There are %d neurons\n", hnn.total_neurons);
     }
     else {
-        minif = hnn.getMinif();
-        printf("\nread value = %d", minif);
-        printf("\nWarning!!! NM500 Shield board not properly responding!!");
-        printf("\nCheck the connection and Reboot again!");
+        printf("\n\nStart NM500 initialization...\n");
+        printf("  NM500 is not connected properly!!\n");
+        printf("  Please check the connection and reboot!\n");
         while (1);
     }
     
@@ -60,127 +86,92 @@
     hnn.setGcr(1 + norm_lsup);
     
     // build knowledge by learning 3 patterns with each constant values (respectively 11, 15 and 20)
-    printf("\nLearning three patterns...");
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    printf("\nLearning three patterns...\n");
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         vector[i] = 11;
     hnn.learn(vector, VECTOR_LENGTH, 55);
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         vector[i] = 15;
     hnn.learn(vector, VECTOR_LENGTH, 33);
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         vector[i] = 20;
-    ncount = hnn.learn(vector, VECTOR_LENGTH, 100);
-    // display the content of the committed neurons
-    printf("\nDisplay the neurons, count = %d", ncount);
-    for (i = 1; i <= ncount; i++) {
-        hnn.readNeuron(i, vector16, &ncr, &aif, &cat);
-        printf("\nneuron#%d \tmodel=", i);
-        for (j = 0; j < VECTOR_LENGTH; j++)
-            printf("%d, ", vector16[j]);
-        if (cat & 0x8000)
-            printf("\tncr=%d \taif=%d \tcat=%d (degenerated)", ncr, aif, (cat & 0x7FFF));
-        else
-            printf("\tncr=%d \taif=%d \tcat=%d", ncr, aif, (cat & 0x7FFF));
-    }
+    hnn.learn(vector, VECTOR_LENGTH, 100);
+    displayNeurons();
     
-    for (value = 12; value < 16; value++) {
-        for (i = 0; i < VECTOR_LENGTH; i++)
+    for (uint8_t value = 12; value < 16; value++) {
+        for (int i = 0; i < VECTOR_LENGTH; i++)
             vector[i] = value;
-        printf("\n\nRecognizing a new pattern: ");
-        for (i = 0; i < VECTOR_LENGTH; i++)
+        printf("\nRecognizing a new pattern: ");
+        for (int i = 0; i < VECTOR_LENGTH; i++)
             printf("%d, ", vector[i]);
+        printf("\n");
         response_nbr = hnn.classify(vector, VECTOR_LENGTH, READ_COUNT, dists, cats, nids);
-        for (i = 0; i < response_nbr; i++) {
-            if (cats[i] & 0x8000)
-                printf("\nFiring neuron#%d, category=%d (degenerated), distance=%d", nids[i], (cats[i] & 0x7FFF), dists[i]);
-            else
-                printf("\nFiring neuron#%d, category=%d, distance=%d", nids[i], (cats[i] & 0x7FFF), dists[i]);
+        for (int i = 0; i < response_nbr; i++) {
+            if (cats[i] & 0x8000) {
+                printf("Firing neuron#%d, category=%d (degenerated), distance=%d\n", nids[i], (cats[i] & 0x7FFF), dists[i]);
+            }
+            else {
+                printf("Firing neuron#%d, category=%d, distance=%d\n", nids[i], (cats[i] & 0x7FFF), dists[i]);
+            }
         }
     }
     
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         vector[i] = 20;
-    printf("\n\nRecognizing a new pattern using KNN classifier: ");
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    printf("\nRecognizing a new pattern using KNN classifier: ");
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         printf("%d, ", vector[i]);
+    printf("\n");
     hnn.setKnnClassifier();
     response_nbr = hnn.classify(vector, VECTOR_LENGTH, READ_COUNT, dists, cats, nids);
     hnn.setRbfClassifier();
-    for (i = 0; i < READ_COUNT; i++) {
-        if (cats[i] & 0x8000)
-            printf("\nFiring neuron#%d, category=%d (degenerated), distance=%d", nids[i], (cats[i] & 0x7FFF), dists[i]);
-        else
-            printf("\nFiring neuron#%d, category=%d, distance=%d", nids[i], (cats[i] & 0x7FFF), dists[i]);
+    for (int i = 0; i < READ_COUNT; i++) {
+        if (cats[i] & 0x8000) {
+            printf("Firing neuron#%d, category=%d (degenerated), distance=%d\n", nids[i], (cats[i] & 0x7FFF), dists[i]);
+        }
+        else {
+            printf("Firing neuron#%d, category=%d, distance=%d\n", nids[i], (cats[i] & 0x7FFF), dists[i]);
+        }
     }
     
-    printf("\n\nLearning a new example (13) falling between neuron1 and neuron2");
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    printf("\nLearning a new example (13) falling between neuron1 and neuron2\n");
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         vector[i] = 13;
-    ncount = hnn.learn(vector, VECTOR_LENGTH, 100);
-    // display the content of the committed neurons
-    printf("\nDisplay the neurons, count = %d", ncount);
-    for (i = 1; i <= ncount; i++) {
-        hnn.readNeuron(i, vector16, &ncr, &aif, &cat);
-        printf("\nneuron#%d \tmodel=", i);
-        for (j = 0; j < VECTOR_LENGTH; j++)
-            printf("%d, ", vector16[j]);
-        if (cat & 0x8000)
-            printf("\tncr=%d \taif=%d \tcat=%d (degenerated)", ncr, aif, (cat & 0x7FFF));
-        else
-            printf("\tncr=%d \taif=%d \tcat=%d", ncr, aif, (cat & 0x7FFF));
-    }
-    printf("\n=> Notice the addition of neuron 4 and the shrinking of the influence fields of neuron1 and 2");
+    hnn.learn(vector, VECTOR_LENGTH, 100);
+    displayNeurons();
+    printf("=> Notice the addition of neuron 4 and the shrinking of the influence fields of neuron1 and 2\n");
     
-    printf("\n\nLearning a same example (13) using a different category 77");
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    printf("\nLearning a same example (13) using a different category 77\n");
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         vector[i] = 13;
-    ncount = hnn.learn(vector, VECTOR_LENGTH, 77);
-    // display the content of the committed neurons
-    printf("\nDisplay the neurons, count = %d", ncount);
-    for (i = 1; i <= ncount; i++) {
-        hnn.readNeuron(i, vector16, &ncr, &aif, &cat);
-        printf("\nneuron#%d \tmodel=", i);
-        for (j = 0; j < VECTOR_LENGTH; j++)
-            printf("%d, ", vector16[j]);
-        if (cat & 0x8000)
-            printf("\tncr=%d \taif=%d \tcat=%d (degenerated)", ncr, aif, (cat & 0x7FFF));
-        else
-            printf("\tncr=%d \taif=%d \tcat=%d", ncr, aif, (cat & 0x7FFF));
-    }
-    printf("\n=> Notice if the AIF of a neuron reaches the MINIF, the neuron will be degenerated");
+    hnn.learn(vector, VECTOR_LENGTH, 77);
+    displayNeurons();
+    printf("=> Notice if the AIF of a neuron reaches the MINIF, the neuron will be degenerated\n");
     
-    printf("\n\nLearning a new example (12) using context 5, category 200");
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    printf("\nLearning a new example (12) using context 5, category 200\n");
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         vector[i] = 12;
     hnn.setContext(5);
-    ncount = hnn.learn(vector, VECTOR_LENGTH, 200);
+    hnn.learn(vector, VECTOR_LENGTH, 200);
     hnn.setContext(1);
-    // display the content of the committed neurons
-    printf("\nDisplay the neurons, count = %d", ncount);
-    for (i = 1; i <= ncount; i++) {
-        hnn.readNeuron(i, vector16, &ncr, &aif, &cat);
-        printf("\nneuron#%d \tmodel=", i);
-        for (j = 0; j < VECTOR_LENGTH; j++)
-            printf("%d, ", vector16[j]);
-        if (cat & 0x8000)
-            printf("\tncr=%d \taif=%d \tcat=%d (degenerated)", ncr, aif, (cat & 0x7FFF));
-        else
-            printf("\tncr=%d \taif=%d \tcat=%d", ncr, aif, (cat & 0x7FFF));
-    }
+    displayNeurons();
     
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         vector[i] = 20;
-    printf("\n\nRecognizing a new pattern using context 5: ");
-    for (i = 0; i < VECTOR_LENGTH; i++)
+    printf("\nRecognizing a new pattern using context 5: ");
+    for (int i = 0; i < VECTOR_LENGTH; i++)
         printf("%d, ", vector[i]);
+    printf("\n");
     hnn.setContext(5);
     response_nbr = hnn.classify(vector, VECTOR_LENGTH, READ_COUNT, dists, cats, nids);
     hnn.setContext(1);
-    for (i = 0; i < response_nbr; i++) {
-        if (cats[i] & 0x8000)
-            printf("\nFiring neuron#%d, category=%d (degenerated), distance=%d", nids[i], (cats[i] & 0x7FFF), dists[i]);
-        else
-            printf("\nFiring neuron#%d, category=%d, distance=%d", nids[i], (cats[i] & 0x7FFF), dists[i]);
+    for (int i = 0; i < response_nbr; i++) {
+        if (cats[i] & 0x8000) {
+            printf("Firing neuron#%d, category=%d (degenerated), distance=%d\n", nids[i], (cats[i] & 0x7FFF), dists[i]);
+        }
+        else {
+            printf("Firing neuron#%d, category=%d, distance=%d\n", nids[i], (cats[i] & 0x7FFF), dists[i]);
+        }
     }
-    printf("\n=> Notice the neurons will not be recognize and shrink if the value of context is not equal");
+    printf("=> Notice the neurons will not be recognize and shrink if the value of context is not equal\n");
 }
\ No newline at end of file