changing reshape layer

Author: ricor07

CMakeLists.txt

@@ -38,8 +38,12 @@ add_library(neural-fortran
   src/nf/nf_layer_constructors_submodule.f90
   src/nf/nf_layer.f90
   src/nf/nf_layer_submodule.f90
+  src/nf/nf_locally_connected_1d_submodule.f90
+  src/nf/nf_locally_connected_1d.f90
   src/nf/nf_loss.f90
   src/nf/nf_loss_submodule.f90
+  src/nf/nf_maxpool1d_layer.f90
+  src/nf/nf_maxpool1d_layer_submodule.f90
   src/nf/nf_maxpool2d_layer.f90
   src/nf/nf_maxpool2d_layer_submodule.f90
   src/nf/nf_metrics.f90
@@ -51,6 +55,8 @@ add_library(neural-fortran
   src/nf/nf_random.f90
   src/nf/nf_reshape_layer.f90
   src/nf/nf_reshape_layer_submodule.f90
+  src/nf/nf_reshape2d_layer.f90
+  src/nf/nf_reshape2d_layer_submodule.f90
   src/nf/io/nf_io_binary.f90
   src/nf/io/nf_io_binary_submodule.f90
 )

example/CMakeLists.txt

@@ -1,5 +1,6 @@
 foreach(execid
   cnn_mnist
+  cnn_mnist_1d
   dense_mnist
   get_set_network_params
   network_parameters

example/cnn_mnist_1d.f90

@@ -0,0 +1,67 @@
+program cnn_mnist
+
+    use nf, only: network, sgd, &
+      input, conv2d, maxpool1d, maxpool2d, flatten, dense, reshape, reshape2d, locally_connected_1d, &
+      load_mnist, label_digits, softmax, relu
+  
+    implicit none
+  
+    type(network) :: net
+  
+    real, allocatable :: training_images(:,:), training_labels(:)
+    real, allocatable :: validation_images(:,:), validation_labels(:)
+    real, allocatable :: testing_images(:,:), testing_labels(:)
+    integer :: n
+    integer, parameter :: num_epochs = 10
+  
+    call load_mnist(training_images, training_labels, &
+                    validation_images, validation_labels, &
+                    testing_images, testing_labels)
+  
+    net = network([ &
+      input(784), &
+      reshape2d([28,28]), &
+      locally_connected_1d(filters=8, kernel_size=3, activation=relu()), &
+      maxpool1d(pool_size=2), &
+      locally_connected_1d(filters=16, kernel_size=3, activation=relu()), &
+      maxpool1d(pool_size=2), &
+      dense(10, activation=softmax()) &
+    ])
+  
+    call net % print_info()
+  
+    epochs: do n = 1, num_epochs
+  
+      call net % train( &
+        training_images, &
+        label_digits(training_labels), &
+        batch_size=16, &
+        epochs=1, &
+        optimizer=sgd(learning_rate=0.003) &
+      )
+  
+      print '(a,i2,a,f5.2,a)', 'Epoch ', n, ' done, Accuracy: ', accuracy( &
+        net, validation_images, label_digits(validation_labels)) * 100, ' %'
+  
+    end do epochs
+  
+    print '(a,f5.2,a)', 'Testing accuracy: ', &
+      accuracy(net, testing_images, label_digits(testing_labels)) * 100, '%'
+  
+  contains
+  
+    real function accuracy(net, x, y)
+      type(network), intent(in out) :: net
+      real, intent(in) :: x(:,:), y(:,:)
+      integer :: i, good
+      good = 0
+      do i = 1, size(x, dim=2)
+        if (all(maxloc(net % predict(x(:,i))) == maxloc(y(:,i)))) then
+          good = good + 1
+        end if
+      end do
+      accuracy = real(good) / size(x, dim=2)
+    end function accuracy
+  
+  end program cnn_mnist
+  

src/nf.f90

@@ -3,7 +3,7 @@ module nf
   use nf_datasets_mnist, only: label_digits, load_mnist
   use nf_layer, only: layer
   use nf_layer_constructors, only: &
-    conv2d, dense, flatten, input, maxpool2d, reshape
+    conv2d, dense, flatten, input, maxpool1d, maxpool2d, reshape, reshape2d, locally_connected_1d
   use nf_loss, only: mse, quadratic
   use nf_metrics, only: corr, maxabs
   use nf_network, only: network