116 lines
4.1 KiB
Python
116 lines
4.1 KiB
Python
import math, torch
|
|
import torch.nn as nn
|
|
import torch.nn.functional as F
|
|
from copy import deepcopy
|
|
from ..cell_operations import OPS
|
|
|
|
|
|
class SearchCell(nn.Module):
|
|
|
|
def __init__(self, C_in, C_out, stride, max_nodes, op_names):
|
|
super(SearchCell, self).__init__()
|
|
|
|
self.op_names = deepcopy(op_names)
|
|
self.edges = nn.ModuleDict()
|
|
self.max_nodes = max_nodes
|
|
self.in_dim = C_in
|
|
self.out_dim = C_out
|
|
for i in range(1, max_nodes):
|
|
for j in range(i):
|
|
node_str = '{:}<-{:}'.format(i, j)
|
|
if j == 0:
|
|
xlists = [OPS[op_name](C_in , C_out, stride) for op_name in op_names]
|
|
else:
|
|
xlists = [OPS[op_name](C_in , C_out, 1) for op_name in op_names]
|
|
self.edges[ node_str ] = nn.ModuleList( xlists )
|
|
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 extra_repr(self):
|
|
string = 'info :: {max_nodes} nodes, inC={in_dim}, outC={out_dim}'.format(**self.__dict__)
|
|
return string
|
|
|
|
def forward(self, inputs, weightss):
|
|
nodes = [inputs]
|
|
for i in range(1, self.max_nodes):
|
|
inter_nodes = []
|
|
for j in range(i):
|
|
node_str = '{:}<-{:}'.format(i, j)
|
|
weights = weightss[ self.edge2index[node_str] ]
|
|
inter_nodes.append( sum( layer(nodes[j]) * w for layer, w in zip(self.edges[node_str], weights) ) )
|
|
nodes.append( sum(inter_nodes) )
|
|
return nodes[-1]
|
|
|
|
# GDAS
|
|
def forward_acc(self, inputs, weightss, indexess):
|
|
nodes = [inputs]
|
|
for i in range(1, self.max_nodes):
|
|
inter_nodes = []
|
|
for j in range(i):
|
|
node_str = '{:}<-{:}'.format(i, j)
|
|
weights = weightss[ self.edge2index[node_str] ]
|
|
indexes = indexess[ self.edge2index[node_str] ].item()
|
|
import pdb; pdb.set_trace() # to-do
|
|
#inter_nodes.append( self.edges[node_str][indexes](nodes[j]) * weights[indexes] )
|
|
nodes.append( sum(inter_nodes) )
|
|
return nodes[-1]
|
|
|
|
# joint
|
|
def forward_joint(self, inputs, weightss):
|
|
nodes = [inputs]
|
|
for i in range(1, self.max_nodes):
|
|
inter_nodes = []
|
|
for j in range(i):
|
|
node_str = '{:}<-{:}'.format(i, j)
|
|
weights = weightss[ self.edge2index[node_str] ]
|
|
aggregation = sum( layer(nodes[j]) * w for layer, w in zip(self.edges[node_str], weights) ) / weights.numel()
|
|
inter_nodes.append( aggregation )
|
|
nodes.append( sum(inter_nodes) )
|
|
return nodes[-1]
|
|
|
|
# uniform random sampling per iteration
|
|
def forward_urs(self, inputs):
|
|
nodes = [inputs]
|
|
for i in range(1, self.max_nodes):
|
|
while True: # to avoid select zero for all ops
|
|
sops, has_non_zero = [], False
|
|
for j in range(i):
|
|
node_str = '{:}<-{:}'.format(i, j)
|
|
candidates = self.edges[node_str]
|
|
select_op = random.choice(candidates)
|
|
sops.append( select_op )
|
|
if not hasattr(select_op, 'is_zero') or select_op.is_zero == False: has_non_zero=True
|
|
if has_non_zero: break
|
|
inter_nodes = []
|
|
for j, select_op in enumerate(sops):
|
|
inter_nodes.append( select_op(nodes[j]) )
|
|
nodes.append( sum(inter_nodes) )
|
|
return nodes[-1]
|
|
|
|
# select the argmax
|
|
def forward_select(self, inputs, weightss):
|
|
nodes = [inputs]
|
|
for i in range(1, self.max_nodes):
|
|
inter_nodes = []
|
|
for j in range(i):
|
|
node_str = '{:}<-{:}'.format(i, j)
|
|
weights = weightss[ self.edge2index[node_str] ]
|
|
inter_nodes.append( self.edges[node_str][ weights.argmax().item() ]( nodes[j] ) )
|
|
#inter_nodes.append( sum( layer(nodes[j]) * w for layer, w in zip(self.edges[node_str], weights) ) )
|
|
nodes.append( sum(inter_nodes) )
|
|
return nodes[-1]
|
|
|
|
# select the argmax
|
|
def forward_dynamic(self, inputs, structure):
|
|
nodes = [inputs]
|
|
for i in range(1, self.max_nodes):
|
|
cur_op_node = structure.nodes[i-1]
|
|
inter_nodes = []
|
|
for op_name, j in cur_op_node:
|
|
node_str = '{:}<-{:}'.format(i, j)
|
|
op_index = self.op_names.index( op_name )
|
|
inter_nodes.append( self.edges[node_str][op_index]( nodes[j] ) )
|
|
nodes.append( sum(inter_nodes) )
|
|
return nodes[-1]
|