Merge branch 'master' into test1

iariav · Aug 28, 2019 · afb07fe · afb07fe
2 parents b94dfa2 + aca71fa
commit afb07fe
Show file tree

Hide file tree

Showing 3 changed files with 17 additions and 12 deletions.
diff --git a/auto_deeplab.py b/auto_deeplab.py
@@ -19,7 +19,8 @@ def __init__(self, num_classes, num_layers, criterion = None, filter_multiplier
         self._filter_multiplier = filter_multiplier
         self._criterion = criterion
         self._initialize_alphas_betas ()
-        C_initial = self._filter_multiplier *  self._block_multiplier
+#         C_initial = self._filter_multiplier *  self._block_multiplier
+        C_initial = 128
         half_C_initial = int(C_initial / 2)
 
         self.stem0 = nn.Sequential(
@@ -142,16 +143,16 @@ def __init__(self, num_classes, num_layers, criterion = None, filter_multiplier
                 self.cells += [cell4]
 
         self.aspp_4 = nn.Sequential (
-            ASPP (self._block_multiplier * self._filter_multiplier, self._num_classes, 24, 24) #96 / 4 as in the paper
+            ASPP (self._filter_multiplier, self._num_classes, 24, 24) #96 / 4 as in the paper
         )
         self.aspp_8 = nn.Sequential (
-            ASPP (self._block_multiplier * self._filter_multiplier * 2, self._num_classes, 12, 12) #96 / 8
+            ASPP (self._filter_multiplier * 2, self._num_classes, 12, 12) #96 / 8
         )
         self.aspp_16 = nn.Sequential (
-            ASPP (self._block_multiplier * self._filter_multiplier * 4, self._num_classes, 6, 6) #96 / 16
+            ASPP (self._filter_multiplier * 4, self._num_classes, 6, 6) #96 / 16
         )
         self.aspp_32 = nn.Sequential (
-            ASPP (self._block_multiplier * self._filter_multiplier * 8, self._num_classes, 3, 3) #96 / 32
+            ASPP (self._filter_multiplier * 8, self._num_classes, 3, 3) #96 / 32
         )
 
 

diff --git a/cell_level_search.py b/cell_level_search.py
@@ -29,16 +29,15 @@ def __init__(self, steps, block_multiplier, prev_prev_fmultiplier,
                  filter_multiplier):
 
         super(Cell, self).__init__()
-        # self.C_in = block_multiplier * filter_multiplier * block_multiplier
-        # self.C_out = filter_multiplier * block_multiplier
+
         self.C_in = block_multiplier * filter_multiplier
         self.C_out = filter_multiplier
+
         self.C_prev_prev = int(prev_prev_fmultiplier * block_multiplier)
         self._prev_fmultiplier_same = prev_fmultiplier_same
-        # self.C_prev_prev = int(prev_prev_fmultiplier)
+
         if prev_fmultiplier_down is not None:
             self.C_prev_down = int(prev_fmultiplier_down * block_multiplier)
-            # self.C_prev_down = prev_fmultiplier_down
             self.preprocess_down = FactorizedReduce(
                 self.C_prev_down, self.C_out, affine=False)
         if prev_fmultiplier_same is not None:
@@ -66,7 +65,7 @@ def __init__(self, steps, block_multiplier, prev_prev_fmultiplier,
                     op = MixedOp(self.C_out, stride)
                 self._ops.append(op)
 
-        self.ReLUConvBN = ReLUConvBN(self.C_in, self.C_out, 1, 1, 0)
+        #self.ReLUConvBN = ReLUConvBN(self.C_in, self.C_out, 1, 1, 0)
 
     def forward(self, s0, s1_down, s1_same, s1_up, n_alphas):
 
@@ -116,6 +115,5 @@ def forward(self, s0, s1_down, s1_same, s1_up, n_alphas):
                 states.append(s)
 
             concat_feature = torch.cat(states[-self.block_multiplier:], dim=1)
-            # final_concates.append(self.ReLUConvBN(concat_feature))
             final_concates.append(concat_feature)
         return final_concates
diff --git a/operations.py b/operations.py
@@ -31,7 +31,8 @@ def __init__(self, C_in, C_out, kernel_size, stride, padding, dilation, affine=T
     super(DilConv, self).__init__()
     self.op = nn.Sequential(
       nn.ReLU(inplace=False),
-      nn.Conv2d(C_in, C_out, kernel_size=kernel_size, stride=stride, padding=padding, dilation=dilation, bias=False),
+      nn.Conv2d(C_in, C_in, kernel_size=kernel_size, stride=stride, padding=padding, groups=C_in, dilation=dilation, bias=False),
+      nn.Conv2d(C_in, C_out, kernel_size=1, padding=0, bias=False),
       nn.BatchNorm2d(C_out, affine=affine),
       )
 
@@ -46,10 +47,15 @@ def __init__(self, C_in, C_out, kernel_size, stride, padding, affine=True):
     self.op = nn.Sequential(
       nn.ReLU(inplace=False),
       nn.Conv2d(C_in, C_in, kernel_size=kernel_size, stride=stride, padding=padding, groups=C_in, bias=False),
+      nn.Conv2d(C_in, C_in, kernel_size=1, padding=0, bias=False),
+      nn.BatchNorm2d(C_in, affine=affine),
+      nn.ReLU(inplace=False),
+      nn.Conv2d(C_in, C_in, kernel_size=kernel_size, stride=1, padding=padding, groups=C_in, bias=False),
       nn.Conv2d(C_in, C_out, kernel_size=1, padding=0, bias=False),
       nn.BatchNorm2d(C_out, affine=affine),
       )
 
+
   def forward(self, x):
     return self.op(x)