Generic conv & maxpool

README.md

@@ -33,11 +33,9 @@ Read the paper [here](https://arxiv.org/abs/1902.06714).
 | Embedding | `embedding` | n/a | 2 | ✅ | ✅ |
 | Dense (fully-connected) | `dense` | `input1d`, `dense`, `dropout`, `flatten` | 1 | ✅ | ✅ |
 | Dropout | `dropout` | `dense`, `flatten`, `input1d` | 1 | ✅ | ✅ |
-| Locally connected (1-d) | `locally_connected1d` | `input2d`, `locally_connected1d`, `conv1d`, `maxpool1d`, `reshape2d` | 2 | ✅ | ✅ |
-| Convolutional (1-d) | `conv1d` | `input2d`, `conv1d`, `maxpool1d`, `reshape2d` | 2 | ✅ | ✅ |
-| Convolutional (2-d) | `conv2d` | `input3d`, `conv2d`, `maxpool2d`, `reshape` | 3 | ✅ | ✅ |
-| Max-pooling (1-d) | `maxpool1d` | `input2d`, `conv1d`, `maxpool1d`, `reshape2d` | 2 | ✅ | ✅ |
-| Max-pooling (2-d) | `maxpool2d` | `input3d`, `conv2d`, `maxpool2d`, `reshape` | 3 | ✅ | ✅ |
+| Locally connected (1-d) | `locally_connected` | `input`, `locally_connected`, `conv`, `maxpool`, `reshape` | 2 | ✅ | ✅ |
+| Convolutional (1-d and 2-d) | `conv` | `input`, `conv`, `maxpool`, `reshape` | 2, 3 | ✅ | ✅ |
+| Max-pooling (1-d and 2-d) | `maxpool` | `input`, `conv`, `maxpool`, `reshape` | 2, 3 | ✅ | ✅ |
 | Linear (2-d) | `linear2d` | `input2d`, `layernorm`, `linear2d`, `self_attention` | 2 | ✅ | ✅ |
 | Self-attention | `self_attention` | `input2d`, `layernorm`, `linear2d`, `self_attention` | 2 | ✅ | ✅ |
 | Layer Normalization | `layernorm` | `linear2d`, `self_attention` | 2 | ✅ | ✅ |

example/cnn_mnist.f90

@@ -1,7 +1,7 @@
 program cnn_mnist
 
   use nf, only: network, sgd, &
-    input, conv2d, maxpool2d, flatten, dense, reshape, &
+    input, conv, maxpool, flatten, dense, reshape, &
     load_mnist, label_digits, softmax, relu
 
   implicit none
@@ -21,10 +21,10 @@ program cnn_mnist
   net = network([ &
     input(784), &
     reshape(1, 28, 28), &
-    conv2d(filters=8, kernel_size=3, activation=relu()), &
-    maxpool2d(pool_size=2), &
-    conv2d(filters=16, kernel_size=3, activation=relu()), &
-    maxpool2d(pool_size=2), &
+    conv(filters=8, kernel_width=3, kernel_height=3, activation=relu()), &
+    maxpool(pool_width=2, pool_height=2, stride=2), &
+    conv(filters=16, kernel_width=3, kernel_height=3, activation=relu()), &
+    maxpool(pool_width=2, pool_height=2, stride=2), &
     dense(10, activation=softmax()) &
   ])
 

example/cnn_mnist_1d.f90

@@ -1,7 +1,7 @@
 program cnn_mnist_1d
 
     use nf, only: network, sgd, &
-      input, conv1d, maxpool1d, flatten, dense, reshape, locally_connected1d, &
+      input, maxpool, flatten, dense, reshape, locally_connected, &
       load_mnist, label_digits, softmax, relu
 
     implicit none
@@ -21,10 +21,10 @@ program cnn_mnist_1d
     net = network([ &
       input(784), &
       reshape(28, 28), &
-      locally_connected1d(filters=8, kernel_size=3, activation=relu()), &
-      maxpool1d(pool_size=2), &
-      locally_connected1d(filters=16, kernel_size=3, activation=relu()), &
-      maxpool1d(pool_size=2), &
+      locally_connected(filters=8, kernel_size=3, activation=relu()), &
+      maxpool(pool_width=2, stride=2), &
+      locally_connected(filters=16, kernel_size=3, activation=relu()), &
+      maxpool(pool_width=2, stride=2), &
       dense(10, activation=softmax()) &
     ])
 

fpm.toml

@@ -1,5 +1,5 @@
 name = "neural-fortran"
-version = "0.21.0"
+version = "0.22.0"
 license = "MIT"
 author = "Milan Curcic"
 maintainer = "[email protected]"

src/nf.f90

@@ -3,18 +3,16 @@ module nf
   use nf_datasets_mnist, only: label_digits, load_mnist
   use nf_layer, only: layer
   use nf_layer_constructors, only: &
-    conv1d, &
-    conv2d, &
+    conv, &
     dense, &
     dropout, &
     embedding, &
     flatten, &
     input, &
     layernorm, &
     linear2d, &
-    locally_connected1d, &
-    maxpool1d, &
-    maxpool2d, &
+    locally_connected, &
+    maxpool, &
     reshape, &
     self_attention
   use nf_loss, only: mse, quadratic