Replace nats_bench by soft link
This commit is contained in:
parent
9046a4e87c
commit
95e304495f
3
.gitmodules
vendored
3
.gitmodules
vendored
@ -1,3 +1,6 @@
|
||||
[submodule ".latent-data/qlib"]
|
||||
path = .latent-data/qlib
|
||||
url = git@github.com:D-X-Y/qlib.git
|
||||
[submodule ".latent-data/NATS-Bench"]
|
||||
path = .latent-data/NATS-Bench
|
||||
url = git@github.com:D-X-Y/NATS-Bench.git
|
||||
|
1
.latent-data/NATS-Bench
Submodule
1
.latent-data/NATS-Bench
Submodule
@ -0,0 +1 @@
|
||||
Subproject commit 51187c1e9152ff79b02b11c80bca0b03b402a7e5
|
@ -94,6 +94,12 @@ Some visualization codes may require `opencv`.
|
||||
CIFAR and ImageNet should be downloaded and extracted into `$TORCH_HOME`.
|
||||
Some methods use knowledge distillation (KD), which require pre-trained models. Please download these models from [Google Drive](https://drive.google.com/open?id=1ANmiYEGX-IQZTfH8w0aSpj-Wypg-0DR-) (or train by yourself) and save into `.latent-data`.
|
||||
|
||||
Please use
|
||||
```
|
||||
git clone --recurse-submodules git@github.com:D-X-Y/AutoDL-Projects.git
|
||||
```
|
||||
to download this repo with submodules.
|
||||
|
||||
## Citation
|
||||
|
||||
If you find that this project helps your research, please consider citing the related paper:
|
||||
|
@ -8,6 +8,7 @@ We also show the versatility of NATS-Bench by benchmarking 13 recent state-of-th
|
||||
This facilitates a much larger community of researchers to focus on developing better NAS algorithms in a more comparable and computationally effective environment.
|
||||
|
||||
**You can use `pip install nats_bench` to install the library of NATS-Bench.**
|
||||
or install from the [source codes](https://github.com/D-X-Y/NATS-Bench) via `python setup.py install`.
|
||||
|
||||
The structure of this Markdown file:
|
||||
- [How to use NATS-Bench?](#How-to-Use-NATS-Bench)
|
||||
|
@ -9,6 +9,11 @@ The Python files in this folder are used to re-produce the results in ``NATS-Ben
|
||||
- [`regularized_ea.py`](https://github.com/D-X-Y/AutoDL-Projects/blob/main/exps/NATS-algos/regularized_ea.py) contains the REA algorithm for both search spaces.
|
||||
- [`reinforce.py`](https://github.com/D-X-Y/AutoDL-Projects/blob/main/exps/NATS-algos/reinforce.py) contains the REINFORCE algorithm for both search spaces.
|
||||
|
||||
## Requirements
|
||||
|
||||
- `nats_bench`>=v1.1 : you can use `pip install nats_bench` to install or from [sources](https://github.com/D-X-Y/NATS-Bench)
|
||||
- `hpbandster` : if you want to run BOHB
|
||||
|
||||
## Citation
|
||||
|
||||
If you find that this project helps your research, please consider citing the related paper:
|
||||
|
24
lib/layers/super_mlp.py
Normal file
24
lib/layers/super_mlp.py
Normal file
@ -0,0 +1,24 @@
|
||||
import torch.nn as nn
|
||||
from typing import Optional
|
||||
|
||||
class MLP(nn.Module):
|
||||
# MLP: FC -> Activation -> Drop -> FC -> Drop
|
||||
def __init__(self, in_features, hidden_features: Optional[int] = None,
|
||||
out_features: Optional[int] = None,
|
||||
act_layer=nn.GELU,
|
||||
drop: Optional[float] = None):
|
||||
super(MLP, self).__init__()
|
||||
out_features = out_features or in_features
|
||||
hidden_features = hidden_features or in_features
|
||||
self.fc1 = nn.Linear(in_features, hidden_features)
|
||||
self.act = act_layer()
|
||||
self.fc2 = nn.Linear(hidden_features, out_features)
|
||||
self.drop = nn.Dropout(drop or 0)
|
||||
|
||||
def forward(self, x):
|
||||
x = self.fc1(x)
|
||||
x = self.act(x)
|
||||
x = self.drop(x)
|
||||
x = self.fc2(x)
|
||||
x = self.drop(x)
|
||||
return x
|
7
lib/layers/super_module.py
Normal file
7
lib/layers/super_module.py
Normal file
@ -0,0 +1,7 @@
|
||||
import torch.nn as nn
|
||||
|
||||
class SuperModule(nn.Module):
|
||||
def __init__(self):
|
||||
super(SuperModule, self).__init__()
|
||||
|
||||
|
@ -1,70 +0,0 @@
|
||||
##############################################################################
|
||||
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2020.08 ##########################
|
||||
##############################################################################
|
||||
# NATS-Bench: Benchmarking NAS algorithms for Architecture Topology and Size #
|
||||
##############################################################################
|
||||
"""The official Application Programming Interface (API) for NATS-Bench."""
|
||||
from nats_bench.api_size import NATSsize
|
||||
from nats_bench.api_topology import NATStopology
|
||||
from nats_bench.api_utils import ArchResults
|
||||
from nats_bench.api_utils import pickle_load
|
||||
from nats_bench.api_utils import pickle_save
|
||||
from nats_bench.api_utils import ResultsCount
|
||||
|
||||
|
||||
NATS_BENCH_API_VERSIONs = ['v1.0', # [2020.08.31]
|
||||
'v1.1'] # [2020.12.20] adding unit tests
|
||||
NATS_BENCH_SSS_NAMEs = ('sss', 'size')
|
||||
NATS_BENCH_TSS_NAMEs = ('tss', 'topology')
|
||||
|
||||
|
||||
def version():
|
||||
return NATS_BENCH_API_VERSIONs[-1]
|
||||
|
||||
|
||||
def create(file_path_or_dict, search_space, fast_mode=False, verbose=True):
|
||||
"""Create the instead for NATS API.
|
||||
|
||||
Args:
|
||||
file_path_or_dict: None or a file path or a directory path.
|
||||
search_space: This is a string indicates the search space in NATS-Bench.
|
||||
fast_mode: If True, we will not load all the data at initialization,
|
||||
instead, the data for each candidate architecture will be loaded when
|
||||
quering it; If False, we will load all the data during initialization.
|
||||
verbose: This is a flag to indicate whether log additional information.
|
||||
|
||||
Raises:
|
||||
ValueError: If not find the matched serach space description.
|
||||
|
||||
Returns:
|
||||
The created NATS-Bench API.
|
||||
"""
|
||||
if search_space in NATS_BENCH_TSS_NAMEs:
|
||||
return NATStopology(file_path_or_dict, fast_mode, verbose)
|
||||
elif search_space in NATS_BENCH_SSS_NAMEs:
|
||||
return NATSsize(file_path_or_dict, fast_mode, verbose)
|
||||
else:
|
||||
raise ValueError('invalid search space : {:}'.format(search_space))
|
||||
|
||||
|
||||
def search_space_info(main_tag, aux_tag):
|
||||
"""Obtain the search space information."""
|
||||
nats_sss = dict(candidates=[8, 16, 24, 32, 40, 48, 56, 64],
|
||||
num_layers=5)
|
||||
nats_tss = dict(op_names=['none', 'skip_connect',
|
||||
'nor_conv_1x1', 'nor_conv_3x3',
|
||||
'avg_pool_3x3'],
|
||||
num_nodes=4)
|
||||
if main_tag == 'nats-bench':
|
||||
if aux_tag in NATS_BENCH_SSS_NAMEs:
|
||||
return nats_sss
|
||||
elif aux_tag in NATS_BENCH_TSS_NAMEs:
|
||||
return nats_tss
|
||||
else:
|
||||
raise ValueError('Unknown auxiliary tag: {:}'.format(aux_tag))
|
||||
elif main_tag == 'nas-bench-201':
|
||||
if aux_tag is not None:
|
||||
raise ValueError('For NAS-Bench-201, the auxiliary tag should be None.')
|
||||
return nats_tss
|
||||
else:
|
||||
raise ValueError('Unknown main tag: {:}'.format(main_tag))
|
@ -1,291 +0,0 @@
|
||||
#####################################################
|
||||
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2020.08 #
|
||||
##############################################################################
|
||||
# NATS-Bench: Benchmarking NAS algorithms for Architecture Topology and Size #
|
||||
##############################################################################
|
||||
# The history of benchmark files are as follows, #
|
||||
# where the format is (the name is NATS-sss-[version]-[md5].pickle.pbz2) #
|
||||
# [2020.08.31] NATS-sss-v1_0-50262.pickle.pbz2 #
|
||||
##############################################################################
|
||||
# pylint: disable=line-too-long
|
||||
"""The API for size search space in NATS-Bench."""
|
||||
import collections
|
||||
import copy
|
||||
import os
|
||||
import random
|
||||
from typing import Dict, Optional, Text, Union, Any
|
||||
|
||||
from nats_bench.api_utils import ArchResults
|
||||
from nats_bench.api_utils import NASBenchMetaAPI
|
||||
from nats_bench.api_utils import get_torch_home
|
||||
from nats_bench.api_utils import nats_is_dir
|
||||
from nats_bench.api_utils import nats_is_file
|
||||
from nats_bench.api_utils import PICKLE_EXT
|
||||
from nats_bench.api_utils import pickle_load
|
||||
from nats_bench.api_utils import time_string
|
||||
|
||||
|
||||
ALL_BASE_NAMES = ['NATS-sss-v1_0-50262']
|
||||
|
||||
|
||||
def print_information(information, extra_info=None, show=False):
|
||||
"""print out the information of a given ArchResults."""
|
||||
dataset_names = information.get_dataset_names()
|
||||
strings = [
|
||||
information.arch_str,
|
||||
'datasets : {:}, extra-info : {:}'.format(dataset_names, extra_info)
|
||||
]
|
||||
|
||||
def metric2str(loss, acc):
|
||||
return 'loss = {:.3f} & top1 = {:.2f}%'.format(loss, acc)
|
||||
|
||||
for dataset in dataset_names:
|
||||
metric = information.get_compute_costs(dataset)
|
||||
flop, param, latency = metric['flops'], metric['params'], metric['latency']
|
||||
str1 = '{:14s} FLOP={:6.2f} M, Params={:.3f} MB, latency={:} ms.'.format(
|
||||
dataset, flop, param,
|
||||
'{:.2f}'.format(latency *
|
||||
1000) if latency is not None and latency > 0 else None)
|
||||
train_info = information.get_metrics(dataset, 'train')
|
||||
if dataset == 'cifar10-valid':
|
||||
valid_info = information.get_metrics(dataset, 'x-valid')
|
||||
test__info = information.get_metrics(dataset, 'ori-test')
|
||||
str2 = '{:14s} train : [{:}], valid : [{:}], test : [{:}]'.format(
|
||||
dataset, metric2str(train_info['loss'], train_info['accuracy']),
|
||||
metric2str(valid_info['loss'], valid_info['accuracy']),
|
||||
metric2str(test__info['loss'], test__info['accuracy']))
|
||||
elif dataset == 'cifar10':
|
||||
test__info = information.get_metrics(dataset, 'ori-test')
|
||||
str2 = '{:14s} train : [{:}], test : [{:}]'.format(
|
||||
dataset, metric2str(train_info['loss'], train_info['accuracy']),
|
||||
metric2str(test__info['loss'], test__info['accuracy']))
|
||||
else:
|
||||
valid_info = information.get_metrics(dataset, 'x-valid')
|
||||
test__info = information.get_metrics(dataset, 'x-test')
|
||||
str2 = '{:14s} train : [{:}], valid : [{:}], test : [{:}]'.format(
|
||||
dataset, metric2str(train_info['loss'], train_info['accuracy']),
|
||||
metric2str(valid_info['loss'], valid_info['accuracy']),
|
||||
metric2str(test__info['loss'], test__info['accuracy']))
|
||||
strings += [str1, str2]
|
||||
if show: print('\n'.join(strings))
|
||||
return strings
|
||||
|
||||
|
||||
class NATSsize(NASBenchMetaAPI):
|
||||
"""This is the class for the API of size search space in NATS-Bench."""
|
||||
|
||||
def __init__(self,
|
||||
file_path_or_dict: Optional[Union[Text, Dict[Text, Any]]] = None,
|
||||
fast_mode: bool = False,
|
||||
verbose: bool = True):
|
||||
"""The initialization function that takes the dataset file path (or a dict loaded from that path) as input."""
|
||||
self._all_base_names = ALL_BASE_NAMES
|
||||
self.filename = None
|
||||
self._search_space_name = 'size'
|
||||
self._fast_mode = fast_mode
|
||||
self._archive_dir = None
|
||||
self._full_train_epochs = 90
|
||||
self.reset_time()
|
||||
if file_path_or_dict is None:
|
||||
if self._fast_mode:
|
||||
self._archive_dir = os.path.join(
|
||||
get_torch_home(), '{:}-simple'.format(ALL_BASE_NAMES[-1]))
|
||||
else:
|
||||
file_path_or_dict = os.path.join(
|
||||
get_torch_home(), '{:}.{:}'.format(
|
||||
ALL_BASE_NAMES[-1], PICKLE_EXT))
|
||||
print('{:} Try to use the default NATS-Bench (size) path from '
|
||||
'fast_mode={:} and path={:}.'.format(time_string(), self._fast_mode,
|
||||
file_path_or_dict))
|
||||
if isinstance(file_path_or_dict, str):
|
||||
file_path_or_dict = str(file_path_or_dict)
|
||||
if verbose:
|
||||
print('{:} Try to create the NATS-Bench (size) api '
|
||||
'from {:} with fast_mode={:}'.format(
|
||||
time_string(), file_path_or_dict, fast_mode))
|
||||
if not nats_is_file(file_path_or_dict) and not nats_is_dir(
|
||||
file_path_or_dict):
|
||||
raise ValueError('{:} is neither a file or a dir.'.format(
|
||||
file_path_or_dict))
|
||||
self.filename = os.path.basename(file_path_or_dict)
|
||||
if fast_mode:
|
||||
if nats_is_file(file_path_or_dict):
|
||||
raise ValueError('fast_mode={:} must feed the path for directory '
|
||||
': {:}'.format(fast_mode, file_path_or_dict))
|
||||
else:
|
||||
self._archive_dir = file_path_or_dict
|
||||
else:
|
||||
if nats_is_dir(file_path_or_dict):
|
||||
raise ValueError('fast_mode={:} must feed the path for file '
|
||||
': {:}'.format(fast_mode, file_path_or_dict))
|
||||
else:
|
||||
file_path_or_dict = pickle_load(file_path_or_dict)
|
||||
elif isinstance(file_path_or_dict, dict):
|
||||
file_path_or_dict = copy.deepcopy(file_path_or_dict)
|
||||
self.verbose = verbose
|
||||
if isinstance(file_path_or_dict, dict):
|
||||
keys = ('meta_archs', 'arch2infos', 'evaluated_indexes')
|
||||
for key in keys:
|
||||
if key not in file_path_or_dict:
|
||||
raise ValueError('Can not find key[{:}] in the dict'.format(key))
|
||||
self.meta_archs = copy.deepcopy(file_path_or_dict['meta_archs'])
|
||||
# NOTE(xuanyidong): This is a dict mapping each architecture to a dict,
|
||||
# where the key is #epochs and the value is ArchResults
|
||||
self.arch2infos_dict = collections.OrderedDict()
|
||||
self._avaliable_hps = set()
|
||||
for xkey in sorted(list(file_path_or_dict['arch2infos'].keys())):
|
||||
all_infos = file_path_or_dict['arch2infos'][xkey]
|
||||
hp2archres = collections.OrderedDict()
|
||||
for hp_key, results in all_infos.items():
|
||||
hp2archres[hp_key] = ArchResults.create_from_state_dict(results)
|
||||
self._avaliable_hps.add(hp_key) # save the avaliable hyper-parameter
|
||||
self.arch2infos_dict[xkey] = hp2archres
|
||||
self.evaluated_indexes = set(file_path_or_dict['evaluated_indexes'])
|
||||
elif self.archive_dir is not None:
|
||||
benchmark_meta = pickle_load('{:}/meta.{:}'.format(
|
||||
self.archive_dir, PICKLE_EXT))
|
||||
self.meta_archs = copy.deepcopy(benchmark_meta['meta_archs'])
|
||||
self.arch2infos_dict = collections.OrderedDict()
|
||||
self._avaliable_hps = set()
|
||||
self.evaluated_indexes = set()
|
||||
else:
|
||||
raise ValueError('file_path_or_dict [{:}] must be a dict or archive_dir '
|
||||
'must be set'.format(type(file_path_or_dict)))
|
||||
self.archstr2index = {}
|
||||
for idx, arch in enumerate(self.meta_archs):
|
||||
if arch in self.archstr2index:
|
||||
raise ValueError('This [{:}]-th arch {:} already in the '
|
||||
'dict ({:}).'.format(
|
||||
idx, arch, self.archstr2index[arch]))
|
||||
self.archstr2index[arch] = idx
|
||||
if self.verbose:
|
||||
print('{:} Create NATS-Bench (size) done with {:}/{:} architectures '
|
||||
'avaliable.'.format(time_string(),
|
||||
len(self.evaluated_indexes),
|
||||
len(self.meta_archs)))
|
||||
|
||||
def query_info_str_by_arch(self, arch, hp: Text = '12'):
|
||||
"""Query the information of a specific architecture.
|
||||
|
||||
Args:
|
||||
arch: it can be an architecture index or an architecture string.
|
||||
|
||||
hp: the hyperparamete indicator, could be 01, 12, or 90. The difference
|
||||
between these three configurations are the number of training epochs.
|
||||
|
||||
Returns:
|
||||
ArchResults instance
|
||||
"""
|
||||
if self.verbose:
|
||||
print('{:} Call query_info_str_by_arch with arch={:}'
|
||||
'and hp={:}'.format(time_string(), arch, hp))
|
||||
return self._query_info_str_by_arch(arch, hp, print_information)
|
||||
|
||||
def get_more_info(self,
|
||||
index,
|
||||
dataset,
|
||||
iepoch=None,
|
||||
hp: Text = '12',
|
||||
is_random: bool = True):
|
||||
"""Return the metric for the `index`-th architecture.
|
||||
|
||||
Args:
|
||||
index: the architecture index.
|
||||
dataset:
|
||||
'cifar10-valid' : using the proposed train set of CIFAR-10 as the training set
|
||||
'cifar10' : using the proposed train+valid set of CIFAR-10 as the training set
|
||||
'cifar100' : using the proposed train set of CIFAR-100 as the training set
|
||||
'ImageNet16-120' : using the proposed train set of ImageNet-16-120 as the training set
|
||||
iepoch: the index of training epochs from 0 to 11/199.
|
||||
When iepoch=None, it will return the metric for the last training epoch
|
||||
When iepoch=11, it will return the metric for the 11-th training epoch (starting from 0)
|
||||
hp: indicates different hyper-parameters for training
|
||||
When hp=01, it trains the network with 01 epochs and the LR decayed from 0.1 to 0 within 01 epochs
|
||||
When hp=12, it trains the network with 01 epochs and the LR decayed from 0.1 to 0 within 12 epochs
|
||||
When hp=90, it trains the network with 01 epochs and the LR decayed from 0.1 to 0 within 90 epochs
|
||||
is_random:
|
||||
When is_random=True, the performance of a random architecture will be returned
|
||||
When is_random=False, the performanceo of all trials will be averaged.
|
||||
|
||||
Returns:
|
||||
a dict, where key is the metric name and value is its value.
|
||||
"""
|
||||
if self.verbose:
|
||||
print('{:} Call the get_more_info function with index={:}, dataset={:}, '
|
||||
'iepoch={:}, hp={:}, and is_random={:}.'.format(
|
||||
time_string(), index, dataset, iepoch, hp, is_random))
|
||||
index = self.query_index_by_arch(index) # To avoid the input is a string or an instance of a arch object
|
||||
self._prepare_info(index)
|
||||
if index not in self.arch2infos_dict:
|
||||
raise ValueError('Did not find {:} from arch2infos_dict.'.format(index))
|
||||
archresult = self.arch2infos_dict[index][str(hp)]
|
||||
# if randomly select one trial, select the seed at first
|
||||
if isinstance(is_random, bool) and is_random:
|
||||
seeds = archresult.get_dataset_seeds(dataset)
|
||||
is_random = random.choice(seeds)
|
||||
# collect the training information
|
||||
train_info = archresult.get_metrics(
|
||||
dataset, 'train', iepoch=iepoch, is_random=is_random)
|
||||
total = train_info['iepoch'] + 1
|
||||
xinfo = {
|
||||
'train-loss': train_info['loss'],
|
||||
'train-accuracy': train_info['accuracy'],
|
||||
'train-per-time': train_info['all_time'] / total,
|
||||
'train-all-time': train_info['all_time']
|
||||
}
|
||||
# collect the evaluation information
|
||||
if dataset == 'cifar10-valid':
|
||||
valid_info = archresult.get_metrics(
|
||||
dataset, 'x-valid', iepoch=iepoch, is_random=is_random)
|
||||
try:
|
||||
test_info = archresult.get_metrics(
|
||||
dataset, 'ori-test', iepoch=iepoch, is_random=is_random)
|
||||
except Exception as unused_e: # pylint: disable=broad-except
|
||||
test_info = None
|
||||
valtest_info = None
|
||||
xinfo['comment'] = 'In this dict, train-loss/accuracy/time is the metric on the train set of CIFAR-10. The test-loss/accuracy/time is the performance of the CIFAR-10 test set after training on the train set by {:} epochs. The per-time and total-time indicate the per epoch and total time costs, respectively.'.format(hp)
|
||||
else:
|
||||
if dataset == 'cifar10':
|
||||
xinfo['comment'] = 'In this dict, train-loss/accuracy/time is the metric on the train+valid sets of CIFAR-10. The test-loss/accuracy/time is the performance of the CIFAR-10 test set after training on the train+valid sets by {:} epochs. The per-time and total-time indicate the per epoch and total time costs, respectively.'.format(hp)
|
||||
try: # collect results on the proposed test set
|
||||
if dataset == 'cifar10':
|
||||
test_info = archresult.get_metrics(
|
||||
dataset, 'ori-test', iepoch=iepoch, is_random=is_random)
|
||||
else:
|
||||
test_info = archresult.get_metrics(
|
||||
dataset, 'x-test', iepoch=iepoch, is_random=is_random)
|
||||
except Exception as unused_e: # pylint: disable=broad-except
|
||||
test_info = None
|
||||
try: # collect results on the proposed validation set
|
||||
valid_info = archresult.get_metrics(
|
||||
dataset, 'x-valid', iepoch=iepoch, is_random=is_random)
|
||||
except Exception as unused_e: # pylint: disable=broad-except
|
||||
valid_info = None
|
||||
try:
|
||||
if dataset != 'cifar10':
|
||||
valtest_info = archresult.get_metrics(
|
||||
dataset, 'ori-test', iepoch=iepoch, is_random=is_random)
|
||||
else:
|
||||
valtest_info = None
|
||||
except Exception as unused_e: # pylint: disable=broad-except
|
||||
valtest_info = None
|
||||
if valid_info is not None:
|
||||
xinfo['valid-loss'] = valid_info['loss']
|
||||
xinfo['valid-accuracy'] = valid_info['accuracy']
|
||||
xinfo['valid-per-time'] = valid_info['all_time'] / total
|
||||
xinfo['valid-all-time'] = valid_info['all_time']
|
||||
if test_info is not None:
|
||||
xinfo['test-loss'] = test_info['loss']
|
||||
xinfo['test-accuracy'] = test_info['accuracy']
|
||||
xinfo['test-per-time'] = test_info['all_time'] / total
|
||||
xinfo['test-all-time'] = test_info['all_time']
|
||||
if valtest_info is not None:
|
||||
xinfo['valtest-loss'] = valtest_info['loss']
|
||||
xinfo['valtest-accuracy'] = valtest_info['accuracy']
|
||||
xinfo['valtest-per-time'] = valtest_info['all_time'] / total
|
||||
xinfo['valtest-all-time'] = valtest_info['all_time']
|
||||
return xinfo
|
||||
|
||||
def show(self, index: int = -1) -> None:
|
||||
"""Print the information of a specific (or all) architecture(s)."""
|
||||
self._show(index, print_information)
|
@ -1,131 +0,0 @@
|
||||
##############################################################################
|
||||
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2020.08 ##########################
|
||||
##############################################################################
|
||||
# NATS-Bench: Benchmarking NAS algorithms for Architecture Topology and Size #
|
||||
##############################################################################
|
||||
# pytest --capture=tee-sys #
|
||||
##############################################################################
|
||||
"""This file is used to quickly test the API."""
|
||||
import os
|
||||
import pytest
|
||||
import random
|
||||
|
||||
from nats_bench.api_size import NATSsize
|
||||
from nats_bench.api_size import ALL_BASE_NAMES as sss_base_names
|
||||
from nats_bench.api_topology import NATStopology
|
||||
from nats_bench.api_topology import ALL_BASE_NAMES as tss_base_names
|
||||
|
||||
|
||||
def get_fake_torch_home_dir():
|
||||
print('This file is {:}'.format(os.path.abspath(__file__)))
|
||||
print('The current directory is {:}'.format(os.path.abspath(os.getcwd())))
|
||||
xname = 'FAKE_TORCH_HOME'
|
||||
if xname in os.environ:
|
||||
return os.environ['FAKE_TORCH_HOME']
|
||||
else:
|
||||
return os.path.join(os.path.dirname(os.path.abspath(__file__)), '..', 'fake_torch_dir')
|
||||
|
||||
|
||||
class TestNATSBench(object):
|
||||
|
||||
def test_nats_bench_tss(self, benchmark_dir=None, fake_random=True):
|
||||
if benchmark_dir is None:
|
||||
benchmark_dir = os.path.join(get_fake_torch_home_dir(), sss_base_names[-1] + '-simple')
|
||||
return _test_nats_bench(benchmark_dir, True, fake_random)
|
||||
|
||||
def test_nats_bench_sss(self, benchmark_dir=None, fake_random=True):
|
||||
if benchmark_dir is None:
|
||||
benchmark_dir = os.path.join(get_fake_torch_home_dir(), tss_base_names[-1] + '-simple')
|
||||
return _test_nats_bench(benchmark_dir, False, fake_random)
|
||||
|
||||
def prepare_fake_tss(self):
|
||||
print('')
|
||||
tss_benchmark_dir = os.path.join(get_fake_torch_home_dir(), tss_base_names[-1] + '-simple')
|
||||
api = NATStopology(tss_benchmark_dir, True, False)
|
||||
return api
|
||||
|
||||
def test_01_th_issue(self):
|
||||
# Link: https://github.com/D-X-Y/NATS-Bench/issues/1
|
||||
api = self.prepare_fake_tss()
|
||||
# The performance of 0-th architecture on CIFAR-10 (trained by 12 epochs)
|
||||
info = api.get_more_info(0, 'cifar10', hp=12)
|
||||
# First of all, the data split in NATS-Bench is different from that in the official CIFAR paper.
|
||||
# In NATS-Bench, we split the original CIFAR-10 training set into two parts, i.e., a training set and a validation set.
|
||||
# In the following, we will use the splits of NATS-Bench to explain.
|
||||
print(info['comment'])
|
||||
print('The loss on the training + validation sets of CIFAR-10: {:}'.format(info['train-loss']))
|
||||
print('The total training time for 12 epochs on the training + validation sets of CIFAR-10: {:}'.format(info['train-all-time']))
|
||||
print('The per-epoch training time on CIFAR-10: {:}'.format(info['train-per-time']))
|
||||
print('The total evaluation time on the test set of CIFAR-10 for 12 times: {:}'.format(info['test-all-time']))
|
||||
print('The evaluation time on the test set of CIFAR-10: {:}'.format(info['test-per-time']))
|
||||
cost_info = api.get_cost_info(0, 'cifar10')
|
||||
xkeys = ['T-train@epoch', # The per epoch training time on the training + validation sets of CIFAR-10.
|
||||
'T-train@total',
|
||||
'T-ori-test@epoch', # The time cost for the evaluation on CIFAR-10 test set.
|
||||
'T-ori-test@total'] # T-ori-test@epoch * 12 times.
|
||||
for xkey in xkeys:
|
||||
print('The cost info [{:}] for 0-th architecture on CIFAR-10 is {:}'.format(xkey, cost_info[xkey]))
|
||||
|
||||
def test_02_th_issue(self):
|
||||
# https://github.com/D-X-Y/NATS-Bench/issues/2
|
||||
api = self.prepare_fake_tss()
|
||||
data = api.query_by_index(284, dataname='cifar10', hp=200)
|
||||
for xkey, xvalue in data.items():
|
||||
print('{:} : {:}'.format(xkey, xvalue))
|
||||
xinfo = data[777].get_train()
|
||||
print(xinfo)
|
||||
print(data[777].train_acc1es)
|
||||
|
||||
info_012_epochs = api.get_more_info(284, 'cifar10', hp= 12)
|
||||
print('Train accuracy for 12 epochs is {:}'.format(info_012_epochs['train-accuracy']))
|
||||
info_200_epochs = api.get_more_info(284, 'cifar10', hp=200)
|
||||
print('Train accuracy for 200 epochs is {:}'.format(info_200_epochs['train-accuracy']))
|
||||
|
||||
|
||||
def _test_nats_bench(benchmark_dir, is_tss, fake_random, verbose=False):
|
||||
"""The main test entry for NATS-Bench."""
|
||||
if is_tss:
|
||||
api = NATStopology(benchmark_dir, True, verbose)
|
||||
else:
|
||||
api = NATSsize(benchmark_dir, True, verbose)
|
||||
|
||||
if fake_random:
|
||||
test_indexes = [0, 11, 284]
|
||||
else:
|
||||
test_indexes = [random.randint(0, len(api) - 1) for _ in range(10)]
|
||||
|
||||
key2dataset = {'cifar10': 'CIFAR-10',
|
||||
'cifar100': 'CIFAR-100',
|
||||
'ImageNet16-120': 'ImageNet16-120'}
|
||||
|
||||
for index in test_indexes:
|
||||
print('\n\nEvaluate the {:5d}-th architecture.'.format(index))
|
||||
|
||||
for key, dataset in key2dataset.items():
|
||||
# Query the loss / accuracy / time for the `index`-th candidate
|
||||
# architecture on CIFAR-10
|
||||
# info is a dict, where you can easily figure out the meaning by key
|
||||
info = api.get_more_info(index, key)
|
||||
print(' -->> The performance on {:}: {:}'.format(dataset, info))
|
||||
|
||||
# Query the flops, params, latency. info is a dict.
|
||||
info = api.get_cost_info(index, key)
|
||||
print(' -->> The cost info on {:}: {:}'.format(dataset, info))
|
||||
|
||||
# Simulate the training of the `index`-th candidate:
|
||||
validation_accuracy, latency, time_cost, current_total_time_cost = api.simulate_train_eval(
|
||||
index, dataset=key, hp='12')
|
||||
print(' -->> The validation accuracy={:}, latency={:}, '
|
||||
'the current time cost={:} s, accumulated time cost={:} s'
|
||||
.format(validation_accuracy, latency, time_cost,
|
||||
current_total_time_cost))
|
||||
|
||||
# Print the configuration of the `index`-th architecture on CIFAR-10
|
||||
config = api.get_net_config(index, key)
|
||||
print(' -->> The configuration on {:} is {:}'.format(dataset, config))
|
||||
|
||||
# Show the information of the `index`-th architecture
|
||||
api.show(index)
|
||||
|
||||
with pytest.raises(ValueError):
|
||||
api.get_more_info(100000, 'cifar10')
|
@ -1,338 +0,0 @@
|
||||
#####################################################
|
||||
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2020.08 #
|
||||
##############################################################################
|
||||
# NATS-Bench: Benchmarking NAS algorithms for Architecture Topology and Size #
|
||||
##############################################################################
|
||||
# The history of benchmark files are as follows, #
|
||||
# where the format is (the name is NATS-tss-[version]-[md5].pickle.pbz2) #
|
||||
# [2020.08.31] NATS-tss-v1_0-3ffb9.pickle.pbz2 #
|
||||
##############################################################################
|
||||
# pylint: disable=line-too-long
|
||||
"""The API for topology search space in NATS-Bench."""
|
||||
import collections
|
||||
import copy
|
||||
import os
|
||||
import random
|
||||
from typing import Any, Dict, List, Optional, Text, Union
|
||||
|
||||
from nats_bench.api_utils import ArchResults
|
||||
from nats_bench.api_utils import NASBenchMetaAPI
|
||||
from nats_bench.api_utils import get_torch_home
|
||||
from nats_bench.api_utils import nats_is_dir
|
||||
from nats_bench.api_utils import nats_is_file
|
||||
from nats_bench.api_utils import PICKLE_EXT
|
||||
from nats_bench.api_utils import pickle_load
|
||||
from nats_bench.api_utils import time_string
|
||||
|
||||
import numpy as np
|
||||
|
||||
|
||||
ALL_BASE_NAMES = ['NATS-tss-v1_0-3ffb9']
|
||||
|
||||
|
||||
def print_information(information, extra_info=None, show=False):
|
||||
"""print out the information of a given ArchResults."""
|
||||
dataset_names = information.get_dataset_names()
|
||||
strings = [
|
||||
information.arch_str,
|
||||
'datasets : {:}, extra-info : {:}'.format(dataset_names, extra_info)
|
||||
]
|
||||
|
||||
def metric2str(loss, acc):
|
||||
return 'loss = {:.3f} & top1 = {:.2f}%'.format(loss, acc)
|
||||
|
||||
for dataset in dataset_names:
|
||||
metric = information.get_compute_costs(dataset)
|
||||
flop, param, latency = metric['flops'], metric['params'], metric['latency']
|
||||
str1 = '{:14s} FLOP={:6.2f} M, Params={:.3f} MB, latency={:} ms.'.format(
|
||||
dataset, flop, param,
|
||||
'{:.2f}'.format(latency *
|
||||
1000) if latency is not None and latency > 0 else None)
|
||||
train_info = information.get_metrics(dataset, 'train')
|
||||
if dataset == 'cifar10-valid':
|
||||
valid_info = information.get_metrics(dataset, 'x-valid')
|
||||
str2 = '{:14s} train : [{:}], valid : [{:}]'.format(
|
||||
dataset, metric2str(train_info['loss'], train_info['accuracy']),
|
||||
metric2str(valid_info['loss'], valid_info['accuracy']))
|
||||
elif dataset == 'cifar10':
|
||||
test__info = information.get_metrics(dataset, 'ori-test')
|
||||
str2 = '{:14s} train : [{:}], test : [{:}]'.format(
|
||||
dataset, metric2str(train_info['loss'], train_info['accuracy']),
|
||||
metric2str(test__info['loss'], test__info['accuracy']))
|
||||
else:
|
||||
valid_info = information.get_metrics(dataset, 'x-valid')
|
||||
test__info = information.get_metrics(dataset, 'x-test')
|
||||
str2 = '{:14s} train : [{:}], valid : [{:}], test : [{:}]'.format(
|
||||
dataset, metric2str(train_info['loss'], train_info['accuracy']),
|
||||
metric2str(valid_info['loss'], valid_info['accuracy']),
|
||||
metric2str(test__info['loss'], test__info['accuracy']))
|
||||
strings += [str1, str2]
|
||||
if show: print('\n'.join(strings))
|
||||
return strings
|
||||
|
||||
|
||||
class NATStopology(NASBenchMetaAPI):
|
||||
"""This is the class for the API of topology search space in NATS-Bench."""
|
||||
|
||||
def __init__(self,
|
||||
file_path_or_dict: Optional[Union[Text, Dict[Text, Any]]] = None,
|
||||
fast_mode: bool = False,
|
||||
verbose: bool = True):
|
||||
"""The initialization function that takes the dataset file path (or a dict loaded from that path) as input."""
|
||||
self._all_base_names = ALL_BASE_NAMES
|
||||
self.filename = None
|
||||
self._search_space_name = 'topology'
|
||||
self._fast_mode = fast_mode
|
||||
self._archive_dir = None
|
||||
self._full_train_epochs = 200
|
||||
self.reset_time()
|
||||
if file_path_or_dict is None:
|
||||
if self._fast_mode:
|
||||
self._archive_dir = os.path.join(
|
||||
get_torch_home(), '{:}-simple'.format(ALL_BASE_NAMES[-1]))
|
||||
else:
|
||||
file_path_or_dict = os.path.join(
|
||||
get_torch_home(), '{:}.{:}'.format(
|
||||
ALL_BASE_NAMES[-1], PICKLE_EXT))
|
||||
print('{:} Try to use the default NATS-Bench (topology) path from '
|
||||
'fast_mode={:} and path={:}.'.format(time_string(), self._fast_mode, file_path_or_dict))
|
||||
if isinstance(file_path_or_dict, str):
|
||||
file_path_or_dict = str(file_path_or_dict)
|
||||
if verbose:
|
||||
print('{:} Try to create the NATS-Bench (topology) api '
|
||||
'from {:} with fast_mode={:}'.format(
|
||||
time_string(), file_path_or_dict, fast_mode))
|
||||
if not nats_is_file(file_path_or_dict) and not nats_is_dir(
|
||||
file_path_or_dict):
|
||||
raise ValueError('{:} is neither a file or a dir.'.format(
|
||||
file_path_or_dict))
|
||||
self.filename = os.path.basename(file_path_or_dict)
|
||||
if fast_mode:
|
||||
if nats_is_file(file_path_or_dict):
|
||||
raise ValueError('fast_mode={:} must feed the path for directory '
|
||||
': {:}'.format(fast_mode, file_path_or_dict))
|
||||
else:
|
||||
self._archive_dir = file_path_or_dict
|
||||
else:
|
||||
if nats_is_dir(file_path_or_dict):
|
||||
raise ValueError('fast_mode={:} must feed the path for file '
|
||||
': {:}'.format(fast_mode, file_path_or_dict))
|
||||
else:
|
||||
file_path_or_dict = pickle_load(file_path_or_dict)
|
||||
elif isinstance(file_path_or_dict, dict):
|
||||
file_path_or_dict = copy.deepcopy(file_path_or_dict)
|
||||
self.verbose = verbose
|
||||
if isinstance(file_path_or_dict, dict):
|
||||
keys = ('meta_archs', 'arch2infos', 'evaluated_indexes')
|
||||
for key in keys:
|
||||
if key not in file_path_or_dict:
|
||||
raise ValueError('Can not find key[{:}] in the dict'.format(key))
|
||||
self.meta_archs = copy.deepcopy(file_path_or_dict['meta_archs'])
|
||||
# NOTE(xuanyidong): This is a dict mapping each architecture to a dict,
|
||||
# where the key is #epochs and the value is ArchResults
|
||||
self.arch2infos_dict = collections.OrderedDict()
|
||||
self._avaliable_hps = set()
|
||||
for xkey in sorted(list(file_path_or_dict['arch2infos'].keys())):
|
||||
all_infos = file_path_or_dict['arch2infos'][xkey]
|
||||
hp2archres = collections.OrderedDict()
|
||||
for hp_key, results in all_infos.items():
|
||||
hp2archres[hp_key] = ArchResults.create_from_state_dict(results)
|
||||
self._avaliable_hps.add(hp_key) # save the avaliable hyper-parameter
|
||||
self.arch2infos_dict[xkey] = hp2archres
|
||||
self.evaluated_indexes = set(file_path_or_dict['evaluated_indexes'])
|
||||
elif self.archive_dir is not None:
|
||||
benchmark_meta = pickle_load('{:}/meta.{:}'.format(
|
||||
self.archive_dir, PICKLE_EXT))
|
||||
self.meta_archs = copy.deepcopy(benchmark_meta['meta_archs'])
|
||||
self.arch2infos_dict = collections.OrderedDict()
|
||||
self._avaliable_hps = set()
|
||||
self.evaluated_indexes = set()
|
||||
else:
|
||||
raise ValueError('file_path_or_dict [{:}] must be a dict or archive_dir '
|
||||
'must be set'.format(type(file_path_or_dict)))
|
||||
self.archstr2index = {}
|
||||
for idx, arch in enumerate(self.meta_archs):
|
||||
if arch in self.archstr2index:
|
||||
raise ValueError('This [{:}]-th arch {:} already in the '
|
||||
'dict ({:}).'.format(
|
||||
idx, arch, self.archstr2index[arch]))
|
||||
self.archstr2index[arch] = idx
|
||||
if self.verbose:
|
||||
print('{:} Create NATS-Bench (topology) done with {:}/{:} architectures '
|
||||
'avaliable.'.format(time_string(),
|
||||
len(self.evaluated_indexes),
|
||||
len(self.meta_archs)))
|
||||
|
||||
def query_info_str_by_arch(self, arch, hp: Text = '12'):
|
||||
"""Query the information of a specific architecture.
|
||||
|
||||
Args:
|
||||
arch: it can be an architecture index or an architecture string.
|
||||
|
||||
hp: the hyperparamete indicator, could be 12 or 200. The difference
|
||||
between these three configurations are the number of training epochs.
|
||||
|
||||
Returns:
|
||||
ArchResults instance
|
||||
"""
|
||||
if self.verbose:
|
||||
print('{:} Call query_info_str_by_arch with arch={:}'
|
||||
'and hp={:}'.format(time_string(), arch, hp))
|
||||
return self._query_info_str_by_arch(arch, hp, print_information)
|
||||
|
||||
def get_more_info(self,
|
||||
index,
|
||||
dataset,
|
||||
iepoch=None,
|
||||
hp: Text = '12',
|
||||
is_random: bool = True):
|
||||
"""Return the metric for the `index`-th architecture."""
|
||||
if self.verbose:
|
||||
print('{:} Call the get_more_info function with index={:}, dataset={:}, '
|
||||
'iepoch={:}, hp={:}, and is_random={:}.'.format(
|
||||
time_string(), index, dataset, iepoch, hp, is_random))
|
||||
index = self.query_index_by_arch(index) # To avoid the input is a string or an instance of a arch object
|
||||
self._prepare_info(index)
|
||||
if index not in self.arch2infos_dict:
|
||||
raise ValueError('Did not find {:} from arch2infos_dict.'.format(index))
|
||||
archresult = self.arch2infos_dict[index][str(hp)]
|
||||
# if randomly select one trial, select the seed at first
|
||||
if isinstance(is_random, bool) and is_random:
|
||||
seeds = archresult.get_dataset_seeds(dataset)
|
||||
is_random = random.choice(seeds)
|
||||
# collect the training information
|
||||
train_info = archresult.get_metrics(dataset, 'train', iepoch=iepoch, is_random=is_random)
|
||||
total = train_info['iepoch'] + 1
|
||||
xinfo = {
|
||||
'train-loss':
|
||||
train_info['loss'],
|
||||
'train-accuracy':
|
||||
train_info['accuracy'],
|
||||
'train-per-time':
|
||||
train_info['all_time'] /
|
||||
total if train_info['all_time'] is not None else None,
|
||||
'train-all-time':
|
||||
train_info['all_time']
|
||||
}
|
||||
# collect the evaluation information
|
||||
if dataset == 'cifar10-valid':
|
||||
valid_info = archresult.get_metrics(dataset, 'x-valid', iepoch=iepoch, is_random=is_random)
|
||||
try:
|
||||
test_info = archresult.get_metrics(dataset, 'ori-test', iepoch=iepoch, is_random=is_random)
|
||||
except Exception as unused_e: # pylint: disable=broad-except
|
||||
test_info = None
|
||||
valtest_info = None
|
||||
xinfo['comment'] = 'In this dict, train-loss/accuracy/time is the metric on the train set of CIFAR-10. The test-loss/accuracy/time is the performance of the CIFAR-10 test set after training on the train set by {:} epochs. The per-time and total-time indicate the per epoch and total time costs, respectively.'.format(hp)
|
||||
else:
|
||||
if dataset == 'cifar10':
|
||||
xinfo['comment'] = 'In this dict, train-loss/accuracy/time is the metric on the train+valid sets of CIFAR-10. The test-loss/accuracy/time is the performance of the CIFAR-10 test set after training on the train+valid sets by {:} epochs. The per-time and total-time indicate the per epoch and total time costs, respectively.'.format(hp)
|
||||
try: # collect results on the proposed test set
|
||||
if dataset == 'cifar10':
|
||||
test_info = archresult.get_metrics(dataset, 'ori-test', iepoch=iepoch, is_random=is_random)
|
||||
else:
|
||||
test_info = archresult.get_metrics(dataset, 'x-test', iepoch=iepoch, is_random=is_random)
|
||||
except Exception as unused_e: # pylint: disable=broad-except
|
||||
test_info = None
|
||||
try: # collect results on the proposed validation set
|
||||
valid_info = archresult.get_metrics(dataset, 'x-valid', iepoch=iepoch, is_random=is_random)
|
||||
except Exception as unused_e: # pylint: disable=broad-except
|
||||
valid_info = None
|
||||
try:
|
||||
if dataset != 'cifar10':
|
||||
valtest_info = archresult.get_metrics(dataset, 'ori-test', iepoch=iepoch, is_random=is_random)
|
||||
else:
|
||||
valtest_info = None
|
||||
except Exception as unused_e: # pylint: disable=broad-except
|
||||
valtest_info = None
|
||||
if valid_info is not None:
|
||||
xinfo['valid-loss'] = valid_info['loss']
|
||||
xinfo['valid-accuracy'] = valid_info['accuracy']
|
||||
xinfo['valid-per-time'] = valid_info['all_time'] / total if valid_info['all_time'] is not None else None
|
||||
xinfo['valid-all-time'] = valid_info['all_time']
|
||||
if test_info is not None:
|
||||
xinfo['test-loss'] = test_info['loss']
|
||||
xinfo['test-accuracy'] = test_info['accuracy']
|
||||
xinfo['test-per-time'] = test_info['all_time'] / total if test_info['all_time'] is not None else None
|
||||
xinfo['test-all-time'] = test_info['all_time']
|
||||
if valtest_info is not None:
|
||||
xinfo['valtest-loss'] = valtest_info['loss']
|
||||
xinfo['valtest-accuracy'] = valtest_info['accuracy']
|
||||
xinfo['valtest-per-time'] = valtest_info['all_time'] / total if valtest_info['all_time'] is not None else None
|
||||
xinfo['valtest-all-time'] = valtest_info['all_time']
|
||||
return xinfo
|
||||
|
||||
def show(self, index: int = -1) -> None:
|
||||
"""This function will print the information of a specific (or all) architecture(s)."""
|
||||
self._show(index, print_information)
|
||||
|
||||
@staticmethod
|
||||
def str2lists(arch_str: Text) -> List[Any]:
|
||||
"""Shows how to read the string-based architecture encoding.
|
||||
|
||||
Args:
|
||||
arch_str: the input is a string indicates the architecture topology, such as
|
||||
|nor_conv_1x1~0|+|none~0|none~1|+|none~0|none~1|skip_connect~2|
|
||||
Returns:
|
||||
a list of tuple, contains multiple (op, input_node_index) pairs.
|
||||
|
||||
[USAGE]
|
||||
It is the same as the `str2structure` func in AutoDL-Projects:
|
||||
`github.com/D-X-Y/AutoDL-Projects/lib/models/cell_searchs/genotypes.py`
|
||||
```
|
||||
arch = api.str2lists( '|nor_conv_1x1~0|+|none~0|none~1|+|none~0|none~1|skip_connect~2|' )
|
||||
print ('there are {:} nodes in this arch'.format(len(arch)+1)) # arch is a list
|
||||
for i, node in enumerate(arch):
|
||||
print('the {:}-th node is the sum of these {:} nodes with op: {:}'.format(i+1, len(node), node))
|
||||
```
|
||||
"""
|
||||
node_strs = arch_str.split('+')
|
||||
genotypes = []
|
||||
for unused_i, node_str in enumerate(node_strs):
|
||||
inputs = list(filter(lambda x: x != '', node_str.split('|'))) # pylint: disable=g-explicit-bool-comparison
|
||||
for xinput in inputs:
|
||||
assert len(
|
||||
xinput.split('~')) == 2, 'invalid input length : {:}'.format(xinput)
|
||||
inputs = (xi.split('~') for xi in inputs)
|
||||
input_infos = tuple((op, int(idx)) for (op, idx) in inputs)
|
||||
genotypes.append(input_infos)
|
||||
return genotypes
|
||||
|
||||
@staticmethod
|
||||
def str2matrix(arch_str: Text,
|
||||
search_space: List[Text] = ('none', 'skip_connect', 'nor_conv_1x1', 'nor_conv_3x3', 'avg_pool_3x3')) -> np.ndarray:
|
||||
"""Convert the string-based architecture encoding to the encoding strategy in NAS-Bench-101.
|
||||
|
||||
Args:
|
||||
arch_str: the input is a string indicates the architecture topology, such as
|
||||
|nor_conv_1x1~0|+|none~0|none~1|+|none~0|none~1|skip_connect~2|
|
||||
search_space: a list of operation string, the default list is the topology search space for NATS-BENCH.
|
||||
the default value should be be consistent with this line https://github.com/D-X-Y/AutoDL-Projects/blob/main/lib/models/cell_operations.py#L24
|
||||
|
||||
Returns:
|
||||
the numpy matrix (2-D np.ndarray) representing the DAG of this architecture topology
|
||||
|
||||
[USAGE]
|
||||
matrix = api.str2matrix( '|nor_conv_1x1~0|+|none~0|none~1|+|none~0|none~1|skip_connect~2|' )
|
||||
This matrix is 4-by-4 matrix representing a cell with 4 nodes (only the lower left triangle is useful).
|
||||
[ [0, 0, 0, 0], # the first line represents the input (0-th) node
|
||||
[2, 0, 0, 0], # the second line represents the 1-st node, is calculated by 2-th-op( 0-th-node )
|
||||
[0, 0, 0, 0], # the third line represents the 2-nd node, is calculated by 0-th-op( 0-th-node ) + 0-th-op( 1-th-node )
|
||||
[0, 0, 1, 0] ] # the fourth line represents the 3-rd node, is calculated by 0-th-op( 0-th-node ) + 0-th-op( 1-th-node ) + 1-th-op( 2-th-node )
|
||||
In the topology search space in NATS-BENCH, 0-th-op is 'none', 1-th-op is 'skip_connect',
|
||||
2-th-op is 'nor_conv_1x1', 3-th-op is 'nor_conv_3x3', 4-th-op is 'avg_pool_3x3'.
|
||||
[NOTE]
|
||||
If a node has two input-edges from the same node, this function does not work. One edge will be overlapped.
|
||||
"""
|
||||
node_strs = arch_str.split('+')
|
||||
num_nodes = len(node_strs) + 1
|
||||
matrix = np.zeros((num_nodes, num_nodes))
|
||||
for i, node_str in enumerate(node_strs):
|
||||
inputs = list(filter(lambda x: x != '', node_str.split('|'))) # pylint: disable=g-explicit-bool-comparison
|
||||
for xinput in inputs:
|
||||
assert len(xinput.split('~')) == 2, 'invalid input length : {:}'.format(xinput)
|
||||
for xi in inputs:
|
||||
op, idx = xi.split('~')
|
||||
if op not in search_space: raise ValueError('this op ({:}) is not in {:}'.format(op, search_space))
|
||||
op_idx, node_idx = search_space.index(op), int(idx)
|
||||
matrix[i+1, node_idx] = op_idx
|
||||
return matrix
|
File diff suppressed because it is too large
Load Diff
1
lib/spaces/__init__.py
Normal file
1
lib/spaces/__init__.py
Normal file
@ -0,0 +1 @@
|
||||
#
|
Loading…
Reference in New Issue
Block a user