X-Git-Url: https://www.fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=conv_chain.py;h=3077874c1ea50310452bf15dd6b2f496a705eef6;hb=c16fa89db08b59e454c6ca4b5c68bf7396e876dc;hp=85ae4fcc5d1040f985538791af35cb8631ad29e4;hpb=77af470cdb98b4a97af6432ca1421c28062b9aae;p=pytorch.git

diff --git a/conv_chain.py b/conv_chain.py
index 85ae4fc..3077874 100755
--- a/conv_chain.py
+++ b/conv_chain.py
@@ -1,12 +1,14 @@
 #!/usr/bin/env python
 
-import torch
-from torch import nn
+# Any copyright is dedicated to the Public Domain.
+# https://creativecommons.org/publicdomain/zero/1.0/
+
+# Written by Francois Fleuret <francois@fleuret.org>
 
 ######################################################################
 
-def conv_chain(input_size, output_size, depth, cond):
-    if depth == 0:
+def conv_chain(input_size, output_size, remain_depth, cond):
+    if remain_depth == 0:
         if input_size == output_size:
             return [ [ ] ]
         else:
@@ -14,11 +16,11 @@ def conv_chain(input_size, output_size, depth, cond):
     else:
         r = [ ]
         for kernel_size in range(1, input_size + 1):
-            for stride in range(1, input_size + 1):
-                if cond(depth, kernel_size, stride):
+            for stride in range(1, input_size):
+                if cond(remain_depth, kernel_size, stride):
                     n = (input_size - kernel_size) // stride + 1
-                    if (n - 1) * stride + kernel_size == input_size:
-                        q = conv_chain(n, output_size, depth - 1, cond)
+                    if n >= output_size and (n - 1) * stride + kernel_size == input_size:
+                        q = conv_chain(n, output_size, remain_depth - 1, cond)
                         r += [ [ (kernel_size, stride) ] + u for u in q ]
         return r
 
@@ -26,12 +28,17 @@ def conv_chain(input_size, output_size, depth, cond):
 
 if __name__ == "__main__":
 
+    import torch
+    from torch import nn
+
     # Example
 
     c = conv_chain(
         input_size = 64, output_size = 8,
-        depth = 5,
-        cond = lambda d, k, s: k <= 4 and s <= k and (s == 1 or d < 3)
+        remain_depth = 5,
+        # We want kernels smaller than 4, strides smaller than the
+        # kernels, and strides of 1 except in the two last layers
+        cond = lambda d, k, s: k <= 4 and s <= k and (s == 1 or d <= 2)
     )
 
     x = torch.rand(1, 1, 64)