updates

lib/models/__init__.py

@@ -13,7 +13,7 @@ from .cell_searchs import CellStructure, CellArchitectures
 
 # Cell-based NAS Models
 def get_cell_based_tiny_net(config):
-  group_names = ['DARTS-V1', 'DARTS-V2', 'GDAS', 'SETN', 'ENAS']
+  group_names = ['DARTS-V1', 'DARTS-V2', 'GDAS', 'SETN', 'ENAS', 'RANDOM']
   from .cell_searchs import nas_super_nets
   if config.name in group_names:
     return nas_super_nets[config.name](config.C, config.N, config.max_nodes, config.num_classes, config.space)

lib/models/cell_searchs/__init__.py

@@ -3,10 +3,12 @@ from .search_model_darts_v2 import TinyNetworkDartsV2
 from .search_model_gdas     import TinyNetworkGDAS
 from .search_model_setn     import TinyNetworkSETN
 from .search_model_enas     import TinyNetworkENAS
+from .search_model_random   import TinyNetworkRANDOM
 from .genotypes             import Structure as CellStructure, architectures as CellArchitectures
 
 nas_super_nets = {'DARTS-V1': TinyNetworkDartsV1,
                   'DARTS-V2': TinyNetworkDartsV2,
                   'GDAS'    : TinyNetworkGDAS,
                   'SETN'    : TinyNetworkSETN,
-                  'ENAS'    : TinyNetworkENAS}
+                  'ENAS'    : TinyNetworkENAS,
+                  'RANDOM'  : TinyNetworkRANDOM}

lib/models/cell_searchs/genotypes.py

@@ -60,6 +60,17 @@ class Structure:
       strings.append( string )
     return '+'.join(strings)
 
+  def check_valid(self):
+    nodes = {0: True}
+    for i, node_info in enumerate(self.nodes):
+      sums = []
+      for op, xin in node_info:
+        if op == 'none' or nodes[xin] == False: x = False
+        else: x = True
+        sums.append( x )
+      nodes[i+1] = sum(sums) > 0
+    return nodes[len(self.nodes)]
+
   def to_unique_str(self, consider_zero=False):
     # this is used to identify the isomorphic cell, which rerquires the prior knowledge of operation
     # two operations are special, i.e., none and skip_connect

lib/models/cell_searchs/search_model_random.py

@@ -0,0 +1,79 @@
+##############################################################################
+# Random Search and Reproducibility for Neural Architecture Search, UAI 2019 # 
+##############################################################################
+import torch, random
+import torch.nn as nn
+from copy import deepcopy
+from ..cell_operations import ResNetBasicblock
+from .search_cells     import SearchCell
+from .genotypes        import Structure
+
+
+class TinyNetworkRANDOM(nn.Module):
+
+  def __init__(self, C, N, max_nodes, num_classes, search_space):
+    super(TinyNetworkRANDOM, self).__init__()
+    self._C        = C
+    self._layerN   = N
+    self.max_nodes = max_nodes
+    self.stem = nn.Sequential(
+                    nn.Conv2d(3, C, kernel_size=3, padding=1, bias=False),
+                    nn.BatchNorm2d(C))
+  
+    layer_channels   = [C    ] * N + [C*2 ] + [C*2  ] * N + [C*4 ] + [C*4  ] * N    
+    layer_reductions = [False] * N + [True] + [False] * N + [True] + [False] * N
+
+    C_prev, num_edge, edge2index = C, None, None
+    self.cells = nn.ModuleList()
+    for index, (C_curr, reduction) in enumerate(zip(layer_channels, layer_reductions)):
+      if reduction:
+        cell = ResNetBasicblock(C_prev, C_curr, 2)
+      else:
+        cell = SearchCell(C_prev, C_curr, 1, max_nodes, search_space)
+        if num_edge is None: num_edge, edge2index = cell.num_edges, cell.edge2index
+        else: assert num_edge == cell.num_edges and edge2index == cell.edge2index, 'invalid {:} vs. {:}.'.format(num_edge, cell.num_edges)
+      self.cells.append( cell )
+      C_prev = cell.out_dim
+    self.op_names   = deepcopy( search_space )
+    self._Layer     = len(self.cells)
+    self.edge2index = edge2index
+    self.lastact    = nn.Sequential(nn.BatchNorm2d(C_prev), nn.ReLU(inplace=True))
+    self.global_pooling = nn.AdaptiveAvgPool2d(1)
+    self.classifier = nn.Linear(C_prev, num_classes)
+    self.arch_cache = None
+    
+  def get_message(self):
+    string = self.extra_repr()
+    for i, cell in enumerate(self.cells):
+      string += '\n {:02d}/{:02d} :: {:}'.format(i, len(self.cells), cell.extra_repr())
+    return string
+
+  def extra_repr(self):
+    return ('{name}(C={_C}, Max-Nodes={max_nodes}, N={_layerN}, L={_Layer})'.format(name=self.__class__.__name__, **self.__dict__))
+
+  def random_genotype(self, set_cache):
+    genotypes = []
+    for i in range(1, self.max_nodes):
+      xlist = []
+      for j in range(i):
+        node_str = '{:}<-{:}'.format(i, j)
+        op_name  = random.choice( self.op_names )
+        xlist.append((op_name, j))
+      genotypes.append( tuple(xlist) )
+    arch = Structure( genotypes )
+    if set_cache: self.arch_cache = arch
+    return arch
+
+  def forward(self, inputs):
+
+    feature = self.stem(inputs)
+    for i, cell in enumerate(self.cells):
+      if isinstance(cell, SearchCell):
+        feature = cell.forward_dynamic(feature, self.arch_cache)
+      else: feature = cell(feature)
+
+    out = self.lastact(feature)
+    out = self.global_pooling( out )
+    out = out.view(out.size(0), -1)
+    logits = self.classifier(out)
+    return out, logits