Add example about loading a Keras model from file

Author: milancurcic

CMakeLists.txt

@@ -106,13 +106,13 @@ string(REGEX REPLACE "^ | $" "" LIBS "${LIBS}")
 
 # tests
 enable_testing()
-foreach(execid input1d_layer input3d_layer dense_layer conv2d_layer maxpool2d_layer flatten_layer dense_network conv2d_network io_hdf5 keras_read_model)
+foreach(execid input1d_layer input3d_layer dense_layer conv2d_layer maxpool2d_layer flatten_layer dense_network dense_network_from_keras conv2d_network io_hdf5 keras_read_model)
   add_executable(test_${execid} test/test_${execid}.f90)
   target_link_libraries(test_${execid} neural ${LIBS})
   add_test(test_${execid} bin/test_${execid})
 endforeach()
 
-foreach(execid cnn mnist simple sine)
+foreach(execid cnn mnist mnist_from_keras simple sine)
   add_executable(${execid} example/${execid}.f90)
   target_link_libraries(${execid} neural ${LIBS})
 endforeach()

README.md

@@ -180,6 +180,8 @@ examples, in increasing level of complexity:
   dataset
 4. [cnn](example/cnn.f90): Creating and running forward a simple CNN using
   `input`, `conv2d`, `maxpool2d`, `flatten`, and `dense` layers.
+5. [mnist_from_keras](example/mnist_from_keras.f90): Creating a pre-trained
+  model from a Keras HDF5 file.
 
 The examples also show you the extent of the public API that's meant to be
 used in applications, i.e. anything from the `nf` module.

example/mnist_from_keras.f90

@@ -0,0 +1,51 @@
+program mnist_from_keras
+
+  ! This example demonstrates loading a pre-trained MNIST model from Keras
+  ! from an HDF5 file and running an inferrence on the testing dataset.
+
+  use nf, only: network, label_digits, load_mnist
+  use nf_datasets, only: download_and_unpack, keras_model_dense_mnist_url
+
+  implicit none
+
+  type(network) :: net
+  real, allocatable :: training_images(:,:), training_labels(:)
+  real, allocatable :: validation_images(:,:), validation_labels(:)
+  real, allocatable :: testing_images(:,:), testing_labels(:)
+  character(*), parameter :: test_data_path = 'keras_dense_mnist.h5'
+  logical :: file_exists
+
+  inquire(file=test_data_path, exist=file_exists)
+  if (.not. file_exists) call download_and_unpack(keras_model_dense_mnist_url)
+
+  call load_mnist(training_images, training_labels, &
+                  validation_images, validation_labels, &
+                  testing_images, testing_labels)
+
+  print '("Loading a pre-trained MNIST model from Keras")'
+  print '(60("="))'
+
+  net = network(test_data_path)
+
+  call net % print_info()
+
+  if (this_image() == 1) &
+    print '(a,f5.2,a)', '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 % output(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 mnist_from_keras