iicd/autodl-projects
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

update 10 NAS algs

Browse Source
This commit is contained in:
D-X-Y
2019-11-15 17:15:07 +11:00
parent 672a9ef0db
commit c72e66b66c
139 changed files with 5863 additions and 368 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
lib/models/cell_searchs/__init__.py
View File

@@ -1,3 +1,6 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
##################################################
from .search_model_darts_v1 import TinyNetworkDartsV1
from .search_model_darts_v2 import TinyNetworkDartsV2
from .search_model_gdas import TinyNetworkGDAS

3
lib/models/cell_searchs/_test_module.py
View File

@@ -1,3 +1,6 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
##################################################
import torch
from search_model_enas_utils import Controller

115
lib/models/cell_searchs/cells.py
View File

@@ -1,115 +0,0 @@
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]

3
lib/models/cell_searchs/genotypes.py
View File

@@ -1,3 +1,6 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
##################################################
from copy import deepcopy

3
lib/models/cell_searchs/search_cells.py
View File

@@ -1,3 +1,6 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
##################################################
import math, random, torch
import warnings
import torch.nn as nn

2
lib/models/cell_searchs/search_model_darts_v1.py
View File

@@ -1,3 +1,5 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
########################################################
# DARTS: Differentiable Architecture Search, ICLR 2019 #
########################################################

2
lib/models/cell_searchs/search_model_darts_v2.py
View File

@@ -1,3 +1,5 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
########################################################
# DARTS: Differentiable Architecture Search, ICLR 2019 #
########################################################

2
lib/models/cell_searchs/search_model_enas.py
View File

@@ -1,3 +1,5 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
##########################################################################
# Efficient Neural Architecture Search via Parameters Sharing, ICML 2018 #
##########################################################################

2
lib/models/cell_searchs/search_model_enas_utils.py
View File

@@ -1,3 +1,5 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
##########################################################################
# Efficient Neural Architecture Search via Parameters Sharing, ICML 2018 #
##########################################################################

2
lib/models/cell_searchs/search_model_random.py
View File

@@ -1,3 +1,5 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
##############################################################################
# Random Search and Reproducibility for Neural Architecture Search, UAI 2019 #
##############################################################################

2
lib/models/cell_searchs/search_model_setn.py
View File

@@ -1,3 +1,5 @@
##################################################
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019 #
######################################################################################
# One-Shot Neural Architecture Search via Self-Evaluated Template Network, ICCV 2019 #
######################################################################################