jacobian

commit d21fb16b00ec4b51acc2cffc58828521d43695f3
parent 16b64229ee6e1bf7e0edfe779f6df94b39f7dd41
Author: David Freifeld <freifeld.david@gmail.com>
Date:   Fri, 19 Jun 2020 17:43:24 -0700

More stats outputs, determined rough source of a bug

Diffstat:
M
bpnn.cpp
 | 
14
++++++++++----
M
mr_bpnn_2.cpp
 | 
12
++++++++----

2 files changed, 18 insertions(+), 8 deletions(-)
diff --git a/bpnn.cpp b/bpnn.cpp
@@ -120,12 +120,15 @@ float Network::cost()
 float Network::accuracy()
 {
   float correct = 0;
+  int total = 0;
   for (int i = 0; i < layers[length-1].contents->rows(); i++) {
-    // printf("%lf vs %lf\n", (*labels)(i, 0), (*layers[length-1].contents)(i, 0));
     if ((*labels)(i, 0) == round((*layers[length-1].contents)(i, 0))) {
+      // printf("Correct!\n");
       correct += 1;
     }
+    total = i;
   }
+  // printf("CORRECT: %f/%i\n", correct, batch_size);
   // std::cout << (1.0/batch_size) * correct << "\n";
   return (1.0/batch_size) * correct;
 }
@@ -300,12 +303,15 @@ void demo(int total_epochs)
         break;
       }
     }
-    printf("Avg time spent across %i batches: %lf on feedforward, %lf on backprop, %lf on cost, %lf on acc, %lf on next batch\n", net.batches, times[0]/net.batches, times[1]/net.batches, times[2]/net.batches, times[3]/net.batches, times[4]/net.batches);
-    net.batches=1;
     epoch_accuracy = 1.0/((float) linecount/net.batch_size) * acc_sum;
     epoch_cost = 1.0/((float) linecount/net.batch_size) * cost_sum;
     auto ep_end = std::chrono::high_resolution_clock::now();
-    printf("Epoch %i/%i - time %f - cost %f - acc %f\n", epochs+1, total_epochs, (double) std::chrono::duration_cast<std::chrono::nanoseconds>(ep_end-ep_begin).count() / pow(10,9), epoch_cost, epoch_accuracy);
+    double epochtime = (double) std::chrono::duration_cast<std::chrono::nanoseconds>(ep_end-ep_begin).count() / pow(10,9);
+    printf("───\nEpoch %i/%i - time %f - cost %f - acc %f\n", epochs+1, total_epochs, epochtime, epoch_cost, epoch_accuracy);
+    printf("Avg time spent across %i batches: %lf on feedforward, %lf on backprop, %lf on cost, %lf on acc, %lf on next batch.\n", net.batches, times[0]/net.batches, times[1]/net.batches, times[2]/net.batches, times[3]/net.batches, times[4]/net.batches);
+    printf("Time spent across epoch: %lf on feedforward, %lf on backprop, %lf on cost, %lf on acc, %lf on next batch, %lf other.\n", times[0], times[1], times[2], times[3], times[4], epochtime-times[0]-times[1]-times[2]-times[3]-times[4]);
+
+    net.batches=1;
     epochs++;
   }
   printf("Test accuracy: %f\n", net.test("./test.txt"));
diff --git a/mr_bpnn_2.cpp b/mr_bpnn_2.cpp
@@ -5,7 +5,7 @@ struct pair* map (struct pair input_pair)
   char* path = new char[100];
   path = (char*)input_pair.key;
   int linecount = prep_file(path);
-  Network* net = new Network (path, 4, 2, 1, 5, 1, 1);  
+  Network* net = new Network (path, 4, 2, 1, 5, 10, 1);  
   auto begin = std::chrono::high_resolution_clock::now();
   // std::cout << "\n\n\n";
   float epoch_cost = 1000;
@@ -17,11 +17,11 @@ struct pair* map (struct pair input_pair)
   // std::cout << net.cost() << "\n";
 
   printf("Beginning train on %i instances for %i epochs...\n", linecount, 50);
-  while (epochs < 50) {
+  while (epochs < 1) {
     auto ep_begin = std::chrono::high_resolution_clock::now();
     float cost_sum = 0;
     float acc_sum = 0;
-    // int linecount = prep_file("./data_banknote_authentication.txt");
+    int linecount = prep_file("./data_banknote_authentication.txt");
     double times[5] = {0};
     for (int i = 0; i <= linecount-net->batch_size; i+=net->batch_size) {
       auto feed_begin = std::chrono::high_resolution_clock::now();
@@ -32,6 +32,9 @@ struct pair* map (struct pair input_pair)
       cost_sum += net->cost();
       // std::cout << acc_sum << " "<< net.accuracy() << " " << net.batch_size << "\n";
       auto acc_begin = std::chrono::high_resolution_clock::now();
+      if (i < 1*net->batch_size) {
+        printf("Batch accuracy: %f\n", net->accuracy());
+      }
       acc_sum += net->accuracy();
       // std::cout << net.cost() << " as it is " << net.labels[0] << " vs " << *net.layers[net.length-1].contents << "\n";
       auto batch_begin = std::chrono::high_resolution_clock::now();
@@ -104,5 +107,6 @@ void translate(char* path)
 
 int main(int argc, char** argv)
 {
-  begin(argv[2], map, reduce, translate, strtol(argv[1], NULL, 10), 1, argv[3], strtol(argv[4], NULL, 10));
+  // begin(argv[2], map, reduce, translate, strtol(argv[1], NULL, 10), 1, argv[3], strtol(argv[4], NULL, 10));
+  demo(50);
 }