update codes

lib/models/__init__.py

@@ -13,20 +13,21 @@ from config_utils import dict2config
 from .SharedUtils import change_key
 from .cell_searchs import CellStructure, CellArchitectures
 
+
 # Cell-based NAS Models
 def get_cell_based_tiny_net(config):
   super_type = getattr(config, 'super_type', 'basic')
   group_names = ['DARTS-V1', 'DARTS-V2', 'GDAS', 'SETN', 'ENAS', 'RANDOM']
   if super_type == 'basic' and config.name in group_names:
-    from .cell_searchs import nas_super_nets
+    from .cell_searchs import nas102_super_nets as nas_super_nets
     try:
       return nas_super_nets[config.name](config.C, config.N, config.max_nodes, config.num_classes, config.space, config.affine, config.track_running_stats)
     except:
       return nas_super_nets[config.name](config.C, config.N, config.max_nodes, config.num_classes, config.space)
-  elif super_type == 'l2s-base' and config.name in group_names:
-    from .l2s_cell_searchs import nas_super_nets
-    return nas_super_nets[config.name](config.C, config.N, config.max_nodes, config.num_classes, config.space \
-                                      ,config.n_piece)
+  elif super_type == 'nasnet-super':
+    from .cell_searchs import nasnet_super_nets as nas_super_nets
+    return nas_super_nets[config.name](config.C, config.N, config.steps, config.multiplier, \
+                    config.stem_multiplier, config.num_classes, config.space, config.affine, config.track_running_stats)
   elif config.name == 'infer.tiny':
     from .cell_infers import TinyNetwork
     return TinyNetwork(config.C, config.N, config.genotype, config.num_classes)

lib/models/cell_operations.py

@@ -28,7 +28,6 @@ SearchSpaceNames = {'connect-nas'  : CONNECT_NAS_BENCHMARK,
                     'aa-nas'       : NAS_BENCH_102,
                     'nas-bench-102': NAS_BENCH_102,
                     'darts'        : DARTS_SPACE}
-                    #'full'         : sorted(list(OPS.keys()))}
 
 
 class ReLUConvBN(nn.Module):

lib/models/cell_searchs/__init__.py

@@ -1,16 +1,22 @@
 ##################################################
 # Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
 ##################################################
+# The macro structure is defined in NAS-Bench-102
 from .search_model_darts    import TinyNetworkDarts
 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
+# NASNet-based macro structure
+from .search_model_gdas_nasnet import NASNetworkGDAS
 
-nas_super_nets = {'DARTS-V1': TinyNetworkDarts,
+
+nas102_super_nets = {'DARTS-V1': TinyNetworkDarts,
                   'DARTS-V2': TinyNetworkDarts,
                   'GDAS'    : TinyNetworkGDAS,
                   'SETN'    : TinyNetworkSETN,
                   'ENAS'    : TinyNetworkENAS,
                   'RANDOM'  : TinyNetworkRANDOM}
+
+nasnet_super_nets = {'GDAS' : NASNetworkGDAS}

lib/models/cell_searchs/search_cells.py

@@ -9,10 +9,11 @@ from copy import deepcopy
 from ..cell_operations import OPS
 
 
-class SearchCell(nn.Module):
+# This module is used for NAS-Bench-102, represents a small search space with a complete DAG
+class NAS102SearchCell(nn.Module):
 
   def __init__(self, C_in, C_out, stride, max_nodes, op_names, affine=False, track_running_stats=True):
-    super(SearchCell, self).__init__()
+    super(NAS102SearchCell, self).__init__()
 
     self.op_names  = deepcopy(op_names)
     self.edges     = nn.ModuleDict()
@@ -74,7 +75,7 @@ class SearchCell(nn.Module):
       nodes.append( sum(inter_nodes) )
     return nodes[-1]
 
-  # uniform random sampling per iteration
+  # uniform random sampling per iteration, SETN
   def forward_urs(self, inputs):
     nodes = [inputs]
     for i in range(1, self.max_nodes):
@@ -118,3 +119,61 @@ class SearchCell(nn.Module):
         inter_nodes.append( self.edges[node_str][op_index]( nodes[j] ) )
       nodes.append( sum(inter_nodes) )
     return nodes[-1]
+
+
+
+class MixedOp(nn.Module):
+
+  def __init__(self, space, C, stride, affine, track_running_stats):
+    super(MixedOp, self).__init__()
+    self._ops = nn.ModuleList()
+    for primitive in space:
+      op = OPS[primitive](C, C, stride, affine, track_running_stats)
+      self._ops.append(op)
+
+  def forward(self, x, weights, index):
+    #return sum(w * op(x) for w, op in zip(weights, self._ops))
+    return self._ops[index](x) * weights[index]
+
+
+# Learning Transferable Architectures for Scalable Image Recognition, CVPR 2018
+class NASNetSearchCell(nn.Module):
+
+  def __init__(self, space, steps, multiplier, C_prev_prev, C_prev, C, reduction, reduction_prev, affine, track_running_stats):
+    super(NASNetSearchCell, self).__init__()
+    self.reduction = reduction
+    self.op_names  = deepcopy(space)
+    if reduction_prev: self.preprocess0 = OPS['skip_connect'](C_prev_prev, C, 2, affine, track_running_stats)
+    else             : self.preprocess0 = OPS['nor_conv_1x1'](C_prev_prev, C, 1, affine, track_running_stats)
+    self.preprocess1 = OPS['nor_conv_1x1'](C_prev, C, 1, affine, track_running_stats)
+    self._steps = steps
+    self._multiplier = multiplier
+
+    self._ops = nn.ModuleList()
+    self.edges     = nn.ModuleDict()
+    for i in range(self._steps):
+      for j in range(2+i):
+        node_str = '{:}<-{:}'.format(i, j)
+        stride = 2 if reduction and j < 2 else 1
+        op = MixedOp(space, C, stride, affine, track_running_stats)
+        self.edges[ node_str ] = op
+    self.edge_keys  = sorted(list(self.edges.keys()))
+    self.edge2index = {key:i for i, key in enumerate(self.edge_keys)}
+    self.num_edges  = len(self.edges)
+
+  def forward_gdas(self, s0, s1, weightss, indexs):
+    s0 = self.preprocess0(s0)
+    s1 = self.preprocess1(s1)
+
+    states = [s0, s1]
+    for i in range(self._steps):
+      clist = []
+      for j, h in enumerate(states):
+        node_str = '{:}<-{:}'.format(i, j)
+        op = self.edges[ node_str ]
+        weights = weightss[ self.edge2index[node_str] ]
+        index   = indexs[ self.edge2index[node_str] ].item()
+        clist.append( op(h, weights, index) )
+      states.append( sum(clist) )
+
+    return torch.cat(states[-self._multiplier:], dim=1)

lib/models/cell_searchs/search_model_darts.py

@@ -7,7 +7,7 @@ import torch
 import torch.nn as nn
 from copy import deepcopy
 from ..cell_operations import ResNetBasicblock
-from .search_cells     import SearchCell
+from .search_cells     import NAS102SearchCell as SearchCell
 from .genotypes        import Structure
 
 

lib/models/cell_searchs/search_model_enas.py

@@ -7,7 +7,7 @@ import torch
 import torch.nn as nn
 from copy import deepcopy
 from ..cell_operations import ResNetBasicblock
-from .search_cells     import SearchCell
+from .search_cells     import NAS102SearchCell as SearchCell
 from .genotypes        import Structure
 from .search_model_enas_utils import Controller
 

lib/models/cell_searchs/search_model_gdas.py

@@ -5,7 +5,7 @@ import torch
 import torch.nn as nn
 from copy import deepcopy
 from ..cell_operations import ResNetBasicblock
-from .search_cells     import SearchCell
+from .search_cells     import NAS102SearchCell as SearchCell
 from .genotypes        import Structure
 
 
@@ -59,6 +59,10 @@ class TinyNetworkGDAS(nn.Module):
   def get_alphas(self):
     return [self.arch_parameters]
 
+  def show_alphas(self):
+    with torch.no_grad():
+      return 'arch-parameters :\n{:}'.format( nn.functional.softmax(self.arch_parameters, dim=-1).cpu() )
+
   def get_message(self):
     string = self.extra_repr()
     for i, cell in enumerate(self.cells):

lib/models/cell_searchs/search_model_gdas_nasnet.py

@@ -0,0 +1,126 @@
+###########################################################################
+# Searching for A Robust Neural Architecture in Four GPU Hours, CVPR 2019 #
+###########################################################################
+import torch
+import torch.nn as nn
+from copy import deepcopy
+from .search_cells     import NASNetSearchCell as SearchCell
+from .genotypes        import Structure
+
+
+# The macro structure is based on NASNet
+class NASNetworkGDAS(nn.Module):
+
+  def __init__(self, C, N, steps, multiplier, stem_multiplier, num_classes, search_space, affine, track_running_stats):
+    super(NASNetworkGDAS, self).__init__()
+    self._C        = C
+    self._layerN   = N
+    self._steps    = steps
+    self._multiplier = multiplier
+    self.stem = nn.Sequential(
+                    nn.Conv2d(3, C*stem_multiplier, kernel_size=3, padding=1, bias=False),
+                    nn.BatchNorm2d(C*stem_multiplier))
+  
+    # config for each layer
+    layer_channels   = [C    ] * N + [C*2 ] + [C*2  ] * (N-1) + [C*4 ] + [C*4  ] * (N-1)
+    layer_reductions = [False] * N + [True] + [False] * (N-1) + [True] + [False] * (N-1)
+
+    num_edge, edge2index = None, None
+    C_prev_prev, C_prev, C_curr, reduction_prev = C*stem_multiplier, C*stem_multiplier, C, False
+
+    self.cells = nn.ModuleList()
+    for index, (C_curr, reduction) in enumerate(zip(layer_channels, layer_reductions)):
+      cell = SearchCell(search_space, steps, multiplier, C_prev_prev, C_prev, C_curr, reduction, reduction_prev, affine, track_running_stats)
+      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_prev, C_prev, reduction_prev = C_prev, multiplier*C_curr, reduction
+    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_normal_parameters = nn.Parameter( 1e-3*torch.randn(num_edge, len(search_space)) )
+    self.arch_reduce_parameters = nn.Parameter( 1e-3*torch.randn(num_edge, len(search_space)) )
+    self.tau        = 10
+
+  def get_weights(self):
+    xlist = list( self.stem.parameters() ) + list( self.cells.parameters() )
+    xlist+= list( self.lastact.parameters() ) + list( self.global_pooling.parameters() )
+    xlist+= list( self.classifier.parameters() )
+    return xlist
+
+  def set_tau(self, tau):
+    self.tau = tau
+
+  def get_tau(self):
+    return self.tau
+
+  def get_alphas(self):
+    return [self.arch_normal_parameters, self.arch_reduce_parameters]
+
+  def show_alphas(self):
+    with torch.no_grad():
+      A = 'arch-normal-parameters :\n{:}'.format( nn.functional.softmax(self.arch_normal_parameters, dim=-1).cpu() )
+      B = 'arch-reduce-parameters :\n{:}'.format( nn.functional.softmax(self.arch_reduce_parameters, dim=-1).cpu() )
+    return '{:}\n{:}'.format(A, B)
+
+  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}, N={_layerN}, steps={_steps}, multiplier={_multiplier}, L={_Layer})'.format(name=self.__class__.__name__, **self.__dict__))
+
+  def genotype(self):
+    def _parse(weights):
+      gene = []
+      for i in range(self._steps):
+        edges = []
+        for j in range(2+i):
+          node_str = '{:}<-{:}'.format(i, j)
+          ws = weights[ self.edge2index[node_str] ]
+          for k, op_name in enumerate(self.op_names):
+            if op_name == 'none': continue
+            edges.append( (op_name, j, ws[k]) )
+        edges = sorted(edges, key=lambda x: -x[-1])
+        selected_edges = edges[:2]
+        gene.append( tuple(selected_edges) )
+      return gene
+    with torch.no_grad():
+      gene_normal = _parse(torch.softmax(self.arch_normal_parameters, dim=-1).cpu().numpy())
+      gene_reduce = _parse(torch.softmax(self.arch_reduce_parameters, dim=-1).cpu().numpy())
+    return {'normal': gene_normal, 'normal_concat': list(range(2+self._steps-self._multiplier, self._steps+2)),
+            'reduce': gene_reduce, 'reduce_concat': list(range(2+self._steps-self._multiplier, self._steps+2))}
+
+  def forward(self, inputs):
+    def get_gumbel_prob(xins):
+      while True:
+        gumbels = -torch.empty_like(xins).exponential_().log()
+        logits  = (xins.log_softmax(dim=1) + gumbels) / self.tau
+        probs   = nn.functional.softmax(logits, dim=1)
+        index   = probs.max(-1, keepdim=True)[1]
+        one_h   = torch.zeros_like(logits).scatter_(-1, index, 1.0)
+        hardwts = one_h - probs.detach() + probs
+        if (torch.isinf(gumbels).any()) or (torch.isinf(probs).any()) or (torch.isnan(probs).any()):
+          continue
+        else: break
+      return hardwts, index
+
+    normal_hardwts, normal_index = get_gumbel_prob(self.arch_normal_parameters)
+    reduce_hardwts, reduce_index = get_gumbel_prob(self.arch_reduce_parameters)
+
+    s0 = s1 = self.stem(inputs)
+    for i, cell in enumerate(self.cells):
+      if cell.reduction: hardwts, index = reduce_hardwts, reduce_index
+      else             : hardwts, index = normal_hardwts, normal_index
+      s0, s1 = s1, cell.forward_gdas(s0, s1, hardwts, index)
+    out = self.lastact(s1)
+    out = self.global_pooling( out )
+    out = out.view(out.size(0), -1)
+    logits = self.classifier(out)
+
+    return out, logits

lib/models/cell_searchs/search_model_random.py

@@ -7,7 +7,7 @@ import torch, random
 import torch.nn as nn
 from copy import deepcopy
 from ..cell_operations import ResNetBasicblock
-from .search_cells     import SearchCell
+from .search_cells     import NAS102SearchCell as SearchCell
 from .genotypes        import Structure
 
 

lib/models/cell_searchs/search_model_setn.py

@@ -7,7 +7,7 @@ import torch, random
 import torch.nn as nn
 from copy import deepcopy
 from ..cell_operations import ResNetBasicblock
-from .search_cells     import SearchCell
+from .search_cells     import NAS102SearchCell as SearchCell
 from .genotypes        import Structure