Integer division trunc mode

sparseconvnet/averagePooling.py

@@ -29,7 +29,7 @@ class AveragePooling(Module):
         output = SparseConvNetTensor()
         output.metadata = input.metadata
         output.spatial_size = (
-            input.spatial_size - self.pool_size) // self.pool_stride + 1
+            input.spatial_size - self.pool_size).div(self.pool_stride, rounding_mode='trunc') + 1
         assert ((output.spatial_size - 1) * self.pool_stride +
                 self.pool_size == input.spatial_size).all()
         output.features = AveragePoolingFunction.apply(

sparseconvnet/convolution.py

@@ -32,8 +32,8 @@ class Convolution(Module):
         assert input.features.nelement() == 0 or input.features.size(1) == self.nIn
         output = SparseConvNetTensor()
         output.metadata = input.metadata
-        output.spatial_size =\
-            (input.spatial_size - self.filter_size) // self.filter_stride + 1
+        output.spatial_size = (input.spatial_size - self.filter_size).div(
+            self.filter_stride, rounding_mode='trunc') + 1
         assert ((output.spatial_size - 1) * self.filter_stride +
                 self.filter_size == input.spatial_size).all(), (input.spatial_size,output.spatial_size,self.filter_size,self.filter_stride)
         output.features = ConvolutionFunction.apply(

sparseconvnet/maxPooling.py

@@ -80,7 +80,7 @@ class MaxPooling(Module):
         output = SparseConvNetTensor()
         output.metadata = input.metadata
         output.spatial_size = (
-            input.spatial_size - self.pool_size) // self.pool_stride + 1
+            input.spatial_size - self.pool_size).div(self.pool_stride, rounding_mode='trunc') + 1
         assert ((output.spatial_size - 1) * self.pool_stride +
                 self.pool_size == input.spatial_size).all()
         output.features = MaxPoolingFunction.apply(

sparseconvnet/randomizedStrideConvolution.py

@@ -44,7 +44,7 @@ class RandomizedStrideConvolution(Module):
         output = SparseConvNetTensor()
         output.metadata = input.metadata
         output.spatial_size =\
-            (input.spatial_size - self.filter_size) // self.filter_stride + 1
+            (input.spatial_size - self.filter_size).div(self.filter_stride, rounding_mode='trunc') + 1
         assert ((output.spatial_size - 1) * self.filter_stride +
                 self.filter_size == input.spatial_size).all()
         output.features = (RandomizedStrideConvolutionFunction if self.training else ConvolutionFunction).apply(

sparseconvnet/randomizedStrideMaxPooling.py

@@ -80,7 +80,7 @@ class RandomizedStrideMaxPooling(Module):
         output = SparseConvNetTensor()
         output.metadata = input.metadata
         output.spatial_size = (
-            input.spatial_size - self.pool_size) // self.pool_stride + 1
+            input.spatial_size - self.pool_size).div(self.pool_stride, rounding_mode='trunc') + 1
         assert ((output.spatial_size - 1) * self.pool_stride +
                 self.pool_size == input.spatial_size).all()
         output.features = (RandomizedStrideMaxPoolingFunction if self.training else MaxPoolingFunction).apply(