Merge branch 'main' into hdf5-reader

Author: milancurcic

CMakeLists.txt

@@ -64,51 +64,53 @@ endif()
 
 # library to archive (libneural.a)
 add_library(neural
-  src/nf_activation.f90
-  src/nf_base_layer.f90
-  src/nf_base_layer_submodule.f90
-  src/nf_conv2d_layer.f90
-  src/nf_conv2d_layer_submodule.f90
-  src/nf_datasets_mnist.f90
-  src/nf_datasets_mnist_submodule.f90
-  src/nf_dense_layer.f90
-  src/nf_dense_layer_submodule.f90
   src/nf.f90
-  src/nf_input1d_layer.f90
-  src/nf_input1d_layer_submodule.f90
-  src/nf_input3d_layer.f90
-  src/nf_input3d_layer_submodule.f90
-  src/nf_io.f90
-  src/nf_io_submodule.f90
-  src/nf_layer_constructors.f90
-  src/nf_layer_constructors_submodule.f90
-  src/nf_layer.f90
-  src/nf_layer_submodule.f90
-  src/nf_loss.f90
-  src/nf_loss_submodule.f90
-  src/nf_maxpool2d_layer.f90
-  src/nf_maxpool2d_layer_submodule.f90
-  src/nf_network.f90
-  src/nf_network_submodule.f90
-  src/nf_optimizers.f90
-  src/nf_parallel.f90
-  src/nf_parallel_submodule.f90
-  src/nf_random.f90
-  src/nf_random_submodule.f90
+  src/nf/nf_activation.f90
+  src/nf/nf_base_layer.f90
+  src/nf/nf_base_layer_submodule.f90
+  src/nf/nf_conv2d_layer.f90
+  src/nf/nf_conv2d_layer_submodule.f90
+  src/nf/nf_datasets_mnist.f90
+  src/nf/nf_datasets_mnist_submodule.f90
+  src/nf/nf_dense_layer.f90
+  src/nf/nf_dense_layer_submodule.f90
+  src/nf/nf_flatten_layer.f90
+  src/nf/nf_flatten_layer_submodule.f90
+  src/nf/nf_input1d_layer.f90
+  src/nf/nf_input1d_layer_submodule.f90
+  src/nf/nf_input3d_layer.f90
+  src/nf/nf_input3d_layer_submodule.f90
+  src/nf/nf_io.f90
+  src/nf/nf_io_submodule.f90
+  src/nf/nf_layer_constructors.f90
+  src/nf/nf_layer_constructors_submodule.f90
+  src/nf/nf_layer.f90
+  src/nf/nf_layer_submodule.f90
+  src/nf/nf_loss.f90
+  src/nf/nf_loss_submodule.f90
+  src/nf/nf_maxpool2d_layer.f90
+  src/nf/nf_maxpool2d_layer_submodule.f90
+  src/nf/nf_network.f90
+  src/nf/nf_network_submodule.f90
+  src/nf/nf_optimizers.f90
+  src/nf/nf_parallel.f90
+  src/nf/nf_parallel_submodule.f90
+  src/nf/nf_random.f90
+  src/nf/nf_random_submodule.f90
 )
 
 # Remove leading or trailing whitespace
 string(REGEX REPLACE "^ | $" "" LIBS "${LIBS}")
 
 # tests
 enable_testing()
-foreach(execid input1d_layer input3d_layer dense_layer conv2d_layer maxpool2d_layer dense_network conv2d_network)
+foreach(execid input1d_layer input3d_layer dense_layer conv2d_layer maxpool2d_layer flatten_layer dense_network conv2d_network)
   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 mnist simple sine)
+foreach(execid cnn mnist simple sine)
   add_executable(${execid} example/${execid}.f90)
   target_link_libraries(${execid} neural ${LIBS})
 endforeach()

README.md

@@ -30,6 +30,7 @@ Read the paper [here](https://arxiv.org/abs/1902.06714).
 | Dense (fully-connected) | `dense` | `input` (1-d) | 1 | ✅ | ✅ |
 | Convolutional (2-d) | `conv2d` | `input` (3-d), `conv2d`, `maxpool2d` | 3 | ✅ | ❌ |
 | Max-pooling (2-d) | `maxpool2d` | `input` (3-d), `conv2d`, `maxpool2d` | 3 | ✅ | ❌ |
+| Flatten | `flatten` | `input` (3-d), `conv2d`, `maxpool2d` | 1 | ✅ | ✅ |
 
 ## Getting started
 
@@ -172,9 +173,16 @@ to run the tests.
 The easiest way to get a sense of how to use neural-fortran is to look at
 examples, in increasing level of complexity:
 
-1. [simple](example/simple.f90): Approximating a simple, constant data relationship
+1. [simple](example/simple.f90): Approximating a simple, constant data
+  relationship
 2. [sine](example/sine.f90): Approximating a sine function
-3. [mnist](example/mnist.f90): Hand-written digit recognition using the MNIST dataset
+3. [mnist](example/mnist.f90): Hand-written digit recognition using the MNIST
+  dataset
+4. [cnn](example/cnn.f90): Creating and running forward a simple CNN using
+  `input`, `conv2d`, `maxpool2d`, `flatten`, and `dense` layers.
+
+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.
 
 The MNIST example uses [curl](https://curl.se/) to download the dataset,
 so make sure you have it installed on your system.

example/cnn.f90

@@ -0,0 +1,32 @@
+program cnn
+
+  use nf, only: conv2d, dense, flatten, input, maxpool2d, network
+
+  implicit none
+  type(network) :: net
+  real, allocatable :: x(:,:,:)
+  integer :: n
+
+  print '("Creating a CNN and doing a forward pass")'
+  print '("(backward pass not implemented yet)")'
+  print '(60("="))'
+
+  net = network([ &
+    input([3, 32, 32]), &
+    conv2d(filters=16, kernel_size=3, activation='relu'), & ! (16, 30, 30)
+    maxpool2d(pool_size=2), & ! (16, 15, 15)
+    conv2d(filters=32, kernel_size=3, activation='relu'), & ! (32, 13, 13)
+    maxpool2d(pool_size=2), & ! (32, 6, 6)
+    flatten(), &
+    dense(10) &
+  ])
+
+  ! Print a network summary to the screen
+  call net % print_info()
+
+  allocate(x(3,32,32))
+  call random_number(x)
+
+  print *, 'Output:', net % output(x)
+
+end program cnn

example/mnist.f90

@@ -1,7 +1,6 @@
 program mnist
-  use nf, only: dense, input, network
-  use nf_datasets_mnist, only: label_digits, load_mnist
-  use nf_optimizers, only: sgd
+
+  use nf, only: dense, input, network, sgd, label_digits, load_mnist
 
   implicit none
 

src/nf.f90

@@ -1,6 +1,8 @@
 module nf
+  !! User API: everything an application needs to reference directly
   use nf_datasets_mnist, only: label_digits, load_mnist
   use nf_layer, only: layer
-  use nf_layer_constructors, only: conv2d, dense, input, maxpool2d
+  use nf_layer_constructors, only: conv2d, dense, flatten, input, maxpool2d
   use nf_network, only: network
+  use nf_optimizers, only: sgd
 end module nf