add nasbench201
This commit is contained in:
parent
c94ce8bee0
commit
192f286cfb
102
NAS-Bench-201/.gitignore
vendored
Executable file
102
NAS-Bench-201/.gitignore
vendored
Executable file
@ -0,0 +1,102 @@
|
||||
# Byte-compiled / optimized / DLL files
|
||||
__pycache__/
|
||||
*.py[cod]
|
||||
*$py.class
|
||||
|
||||
# C extensions
|
||||
*.so
|
||||
|
||||
# Distribution / packaging
|
||||
.Python
|
||||
env/
|
||||
build/
|
||||
develop-eggs/
|
||||
dist/
|
||||
downloads/
|
||||
eggs/
|
||||
.eggs/
|
||||
lib/
|
||||
lib64/
|
||||
parts/
|
||||
sdist/
|
||||
var/
|
||||
*.egg-info/
|
||||
.installed.cfg
|
||||
*.egg
|
||||
|
||||
# PyInstaller
|
||||
# Usually these files are written by a python script from a template
|
||||
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
||||
*.manifest
|
||||
*.spec
|
||||
|
||||
# Installer logs
|
||||
pip-log.txt
|
||||
pip-delete-this-directory.txt
|
||||
|
||||
# Unit test / coverage reports
|
||||
htmlcov/
|
||||
.tox/
|
||||
.coverage
|
||||
.coverage.*
|
||||
.cache
|
||||
nosetests.xml
|
||||
coverage.xml
|
||||
*,cover
|
||||
.hypothesis/
|
||||
|
||||
# Translations
|
||||
*.mo
|
||||
*.pot
|
||||
|
||||
# Django stuff:
|
||||
*.log
|
||||
local_settings.py
|
||||
|
||||
# Flask stuff:
|
||||
instance/
|
||||
.webassets-cache
|
||||
|
||||
# Scrapy stuff:
|
||||
.scrapy
|
||||
|
||||
# Sphinx documentation
|
||||
docs/_build/
|
||||
|
||||
# PyBuilder
|
||||
target/
|
||||
|
||||
# IPython Notebook
|
||||
.ipynb_checkpoints
|
||||
|
||||
# pyenv
|
||||
.python-version
|
||||
|
||||
# celery beat schedule file
|
||||
celerybeat-schedule
|
||||
|
||||
# dotenv
|
||||
.env
|
||||
|
||||
# virtualenv
|
||||
venv/
|
||||
ENV/
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
|
||||
# Rope project settings
|
||||
.ropeproject
|
||||
|
||||
# Pycharm project
|
||||
.idea
|
||||
snapshots
|
||||
*.pytorch
|
||||
*.tar.bz
|
||||
data
|
||||
.*.swp
|
||||
*.sh
|
||||
main_main.py
|
||||
dist
|
||||
build
|
||||
*.egg-info
|
21
NAS-Bench-201/LICENSE.md
Normal file
21
NAS-Bench-201/LICENSE.md
Normal file
@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) since 2019 Xuanyi Dong (GitHub: https://github.com/D-X-Y)
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
185
NAS-Bench-201/README.md
Normal file
185
NAS-Bench-201/README.md
Normal file
@ -0,0 +1,185 @@
|
||||
# NAS-BENCH-201 has been extended to [NATS-Bench](https://xuanyidong.com/assets/projects/NATS-Bench)
|
||||
|
||||
**Since our NAS-BENCH-201 has been extended to NATS-Bench, this repo is deprecated and not maintained. Please use [NATS-Bench](https://github.com/D-X-Y/NATS-Bench), which has 5x more architecture information and faster API than NAS-BENCH-201.**
|
||||
|
||||
# [NAS-BENCH-201: Extending the Scope of Reproducible Neural Architecture Search](https://openreview.net/forum?id=HJxyZkBKDr)
|
||||
|
||||
We propose an algorithm-agnostic NAS benchmark (NAS-Bench-201) with a fixed search space, which provides a unified benchmark for almost any up-to-date NAS algorithms.
|
||||
The design of our search space is inspired by that used in the most popular cell-based searching algorithms, where a cell is represented as a directed acyclic graph.
|
||||
Each edge here is associated with an operation selected from a predefined operation set.
|
||||
For it to be applicable for all NAS algorithms, the search space defined in NAS-Bench-201 includes 4 nodes and 5 associated operation options, which generates 15,625 neural cell candidates in total.
|
||||
|
||||
In this Markdown file, we provide:
|
||||
- [How to Use NAS-Bench-201](#how-to-use-nas-bench-201)
|
||||
|
||||
For the following two things, please use [AutoDL-Projects](https://github.com/D-X-Y/AutoDL-Projects):
|
||||
- [Instruction to re-generate NAS-Bench-201](#instruction-to-re-generate-nas-bench-201)
|
||||
- [10 NAS algorithms evaluated in our paper](#to-reproduce-10-baseline-nas-algorithms-in-nas-bench-201)
|
||||
|
||||
Note: please use `PyTorch >= 1.2.0` and `Python >= 3.6.0`.
|
||||
|
||||
You can simply type `pip install nas-bench-201` to install our api. Please see source codes of `nas-bench-201` module in [this repo](https://github.com/D-X-Y/NAS-Bench-201).
|
||||
|
||||
**If you have any questions or issues, please post it at [here](https://github.com/D-X-Y/AutoDL-Projects/issues) or email me.**
|
||||
|
||||
### Preparation and Download
|
||||
|
||||
[deprecated] The **old** benchmark file of NAS-Bench-201 can be downloaded from [Google Drive](https://drive.google.com/file/d/1SKW0Cu0u8-gb18zDpaAGi0f74UdXeGKs/view?usp=sharing) or [Baidu-Wangpan (code:6u5d)](https://pan.baidu.com/s/1CiaNH6C12zuZf7q-Ilm09w).
|
||||
|
||||
[recommended] The **latest** benchmark file of NAS-Bench-201 (`NAS-Bench-201-v1_1-096897.pth`) can be downloaded from [Google Drive](https://drive.google.com/file/d/16Y0UwGisiouVRxW-W5hEtbxmcHw_0hF_/view?usp=sharing). The files for model weight are too large (431G) and I need some time to upload it. Please be patient, thanks for your understanding.
|
||||
|
||||
You can move it to anywhere you want and send its path to our API for initialization.
|
||||
- [2020.02.25] APIv1.0/FILEv1.0: [`NAS-Bench-201-v1_0-e61699.pth`](https://drive.google.com/open?id=1SKW0Cu0u8-gb18zDpaAGi0f74UdXeGKs) (2.2G), where `e61699` is the last six digits for this file. It contains all information except for the trained weights of each trial.
|
||||
- [2020.02.25] APIv1.0/FILEv1.0: The full data of each architecture can be download from [
|
||||
NAS-BENCH-201-4-v1.0-archive.tar](https://drive.google.com/open?id=1X2i-JXaElsnVLuGgM4tP-yNwtsspXgdQ) (about 226GB). This compressed folder has 15625 files containing the the trained weights.
|
||||
- [2020.02.25] APIv1.0/FILEv1.0: Checkpoints for 3 runs of each baseline NAS algorithm are provided in [Google Drive](https://drive.google.com/open?id=1eAgLZQAViP3r6dA0_ZOOGG9zPLXhGwXi).
|
||||
- [2020.03.09] APIv1.2/FILEv1.0: More robust API with more functions and descriptions
|
||||
- [2020.03.16] APIv1.3/FILEv1.1: [`NAS-Bench-201-v1_1-096897.pth`](https://drive.google.com/open?id=16Y0UwGisiouVRxW-W5hEtbxmcHw_0hF_) (4.7G), where `096897` is the last six digits for this file. It contains information of more trials compared to `NAS-Bench-201-v1_0-e61699.pth`, especially all models trained by 12 epochs on all datasets are avaliable.
|
||||
- [2020.06.30] APIv2.0: Use abstract class (NASBenchMetaAPI) for APIs of NAS-Bench-x0y.
|
||||
- [2020.06.30] FILEv2.0: coming soon!
|
||||
|
||||
**We recommend to use `NAS-Bench-201-v1_1-096897.pth`**
|
||||
|
||||
|
||||
The training and evaluation data used in NAS-Bench-201 can be downloaded from [Google Drive](https://drive.google.com/open?id=1L0Lzq8rWpZLPfiQGd6QR8q5xLV88emU7) or [Baidu-Wangpan (code:4fg7)](https://pan.baidu.com/s/1XAzavPKq3zcat1yBA1L2tQ).
|
||||
It is recommended to put these data into `$TORCH_HOME` (`~/.torch/` by default). If you want to generate NAS-Bench-201 or similar NAS datasets or training models by yourself, you need these data.
|
||||
|
||||
## How to Use NAS-Bench-201
|
||||
|
||||
**More usage can be found in [our test codes](https://github.com/D-X-Y/AutoDL-Projects/blob/master/exps/NAS-Bench-201/test-nas-api.py)**.
|
||||
|
||||
1. Creating an API instance from a file:
|
||||
```
|
||||
from nas_201_api import NASBench201API as API
|
||||
api = API('$path_to_meta_nas_bench_file')
|
||||
# Create an API without the verbose log
|
||||
api = API('NAS-Bench-201-v1_1-096897.pth', verbose=False)
|
||||
# The default path for benchmark file is '{:}/{:}'.format(os.environ['TORCH_HOME'], 'NAS-Bench-201-v1_1-096897.pth')
|
||||
api = API(None)
|
||||
```
|
||||
|
||||
2. Show the number of architectures `len(api)` and each architecture `api[i]`:
|
||||
```
|
||||
num = len(api)
|
||||
for i, arch_str in enumerate(api):
|
||||
print ('{:5d}/{:5d} : {:}'.format(i, len(api), arch_str))
|
||||
```
|
||||
|
||||
3. Show the results of all trials for a single architecture:
|
||||
```
|
||||
# show all information for a specific architecture
|
||||
api.show(1)
|
||||
api.show(2)
|
||||
|
||||
# show the mean loss and accuracy of an architecture
|
||||
info = api.query_meta_info_by_index(1) # This is an instance of `ArchResults`
|
||||
res_metrics = info.get_metrics('cifar10', 'train') # This is a dict with metric names as keys
|
||||
cost_metrics = info.get_comput_costs('cifar100') # This is a dict with metric names as keys, e.g., flops, params, latency
|
||||
|
||||
# get the detailed information
|
||||
results = api.query_by_index(1, 'cifar100') # a dict of all trials for 1st net on cifar100, where the key is the seed
|
||||
print ('There are {:} trials for this architecture [{:}] on cifar100'.format(len(results), api[1]))
|
||||
for seed, result in results.items():
|
||||
print ('Latency : {:}'.format(result.get_latency()))
|
||||
print ('Train Info : {:}'.format(result.get_train()))
|
||||
print ('Valid Info : {:}'.format(result.get_eval('x-valid')))
|
||||
print ('Test Info : {:}'.format(result.get_eval('x-test')))
|
||||
# for the metric after a specific epoch
|
||||
print ('Train Info [10-th epoch] : {:}'.format(result.get_train(10)))
|
||||
```
|
||||
|
||||
4. Query the index of an architecture by string
|
||||
```
|
||||
index = api.query_index_by_arch('|nor_conv_3x3~0|+|nor_conv_3x3~0|avg_pool_3x3~1|+|skip_connect~0|nor_conv_3x3~1|skip_connect~2|')
|
||||
api.show(index)
|
||||
```
|
||||
This string `|nor_conv_3x3~0|+|nor_conv_3x3~0|avg_pool_3x3~1|+|skip_connect~0|nor_conv_3x3~1|skip_connect~2|` means:
|
||||
```
|
||||
node-0: the input tensor
|
||||
node-1: conv-3x3( node-0 )
|
||||
node-2: conv-3x3( node-0 ) + avg-pool-3x3( node-1 )
|
||||
node-3: skip-connect( node-0 ) + conv-3x3( node-1 ) + skip-connect( node-2 )
|
||||
```
|
||||
|
||||
5. Create the network from api:
|
||||
```
|
||||
config = api.get_net_config(123, 'cifar10') # obtain the network configuration for the 123-th architecture on the CIFAR-10 dataset
|
||||
from models import get_cell_based_tiny_net # this module is in AutoDL-Projects/lib/models
|
||||
network = get_cell_based_tiny_net(config) # create the network from configurration
|
||||
print(network) # show the structure of this architecture
|
||||
```
|
||||
If you want to load the trained weights of this created network, you need to use `api.get_net_param(123, ...)` to obtain the weights and then load it to the network.
|
||||
|
||||
6. `api.get_more_info(...)` can return the loss / accuracy / time on training / validation / test sets, which is very helpful. For more details, please look at the comments in the get_more_info function.
|
||||
|
||||
7. For other usages, please see `lib/nas_201_api/api.py`. We provide some usage information in the comments for the corresponding functions. If what you want is not provided, please feel free to open an issue for discussion, and I am happy to answer any questions regarding NAS-Bench-201.
|
||||
|
||||
|
||||
### Detailed Instruction
|
||||
|
||||
In `nas_201_api`, we define three classes: `NASBench201API`, `ArchResults`, `ResultsCount`.
|
||||
|
||||
`ResultsCount` maintains all information of a specific trial. One can instantiate ResultsCount and get the info via the following codes (`000157-FULL.pth` saves all information of all trials of 157-th architecture):
|
||||
```
|
||||
from nas_201_api import ResultsCount
|
||||
xdata = torch.load('000157-FULL.pth')
|
||||
odata = xdata['full']['all_results'][('cifar10-valid', 777)]
|
||||
result = ResultsCount.create_from_state_dict( odata )
|
||||
print(result) # print it
|
||||
print(result.get_train()) # print the final training loss/accuracy/[optional:time-cost-of-a-training-epoch]
|
||||
print(result.get_train(11)) # print the training info of the 11-th epoch
|
||||
print(result.get_eval('x-valid')) # print the final evaluation info on the validation set
|
||||
print(result.get_eval('x-valid', 11)) # print the info on the validation set of the 11-th epoch
|
||||
print(result.get_latency()) # print the evaluation latency [in batch]
|
||||
result.get_net_param() # the trained parameters of this trial
|
||||
arch_config = result.get_config(CellStructure.str2structure) # create the network with params
|
||||
net_config = dict2config(arch_config, None)
|
||||
network = get_cell_based_tiny_net(net_config)
|
||||
network.load_state_dict(result.get_net_param())
|
||||
```
|
||||
|
||||
`ArchResults` maintains all information of all trials of an architecture. Please see the following usages:
|
||||
```
|
||||
from nas_201_api import ArchResults
|
||||
xdata = torch.load('000157-FULL.pth')
|
||||
archRes = ArchResults.create_from_state_dict(xdata['less']) # load trials trained with 12 epochs
|
||||
archRes = ArchResults.create_from_state_dict(xdata['full']) # load trials trained with 200 epochs
|
||||
|
||||
print(archRes.arch_idx_str()) # print the index of this architecture
|
||||
print(archRes.get_dataset_names()) # print the supported training data
|
||||
print(archRes.get_compute_costs('cifar10-valid')) # print all computational info when training on cifar10-valid
|
||||
print(archRes.get_metrics('cifar10-valid', 'x-valid', None, False)) # print the average loss/accuracy/time on all trials
|
||||
print(archRes.get_metrics('cifar10-valid', 'x-valid', None, True)) # print loss/accuracy/time of a randomly selected trial
|
||||
```
|
||||
|
||||
`NASBench201API` is the topest level api. Please see the following usages:
|
||||
```
|
||||
from nas_201_api import NASBench201API as API
|
||||
api = API('NAS-Bench-201-v1_1-096897.pth') # This will load all the information of NAS-Bench-201 except the trained weights
|
||||
api = API('{:}/{:}'.format(os.environ['TORCH_HOME'], 'NAS-Bench-201-v1_1-096897.pth')) # The same as the above line while I usually save NAS-Bench-201-v1_1-096897.pth in ~/.torch/.
|
||||
api.show(-1) # show info of all architectures
|
||||
api.reload('{:}/{:}'.format(os.environ['TORCH_HOME'], 'NAS-BENCH-201-4-v1.0-archive'), 3) # This code will reload the information 3-th architecture with the trained weights
|
||||
|
||||
weights = api.get_net_param(3, 'cifar10', None) # Obtaining the weights of all trials for the 3-th architecture on cifar10. It will returns a dict, where the key is the seed and the value is the trained weights.
|
||||
```
|
||||
|
||||
To obtain the training and evaluation information (please see the comments [here](https://github.com/D-X-Y/AutoDL-Projects/blob/master/lib/nas_201_api/api_201.py#L142)):
|
||||
```
|
||||
api.get_more_info(112, 'cifar10', None, hp='200', is_random=True)
|
||||
# Query info of last training epoch for 112-th architecture
|
||||
# using 200-epoch-hyper-parameter and randomly select a trial.
|
||||
api.get_more_info(112, 'ImageNet16-120', None, hp='200', is_random=True)
|
||||
```
|
||||
|
||||
# Citation
|
||||
|
||||
If you find that NAS-Bench-201 helps your research, please consider citing it:
|
||||
```
|
||||
@inproceedings{dong2020nasbench201,
|
||||
title = {NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search},
|
||||
author = {Dong, Xuanyi and Yang, Yi},
|
||||
booktitle = {International Conference on Learning Representations (ICLR)},
|
||||
url = {https://openreview.net/forum?id=HJxyZkBKDr},
|
||||
year = {2020}
|
||||
}
|
||||
```
|
42
NAS-Bench-201/nas_201_api/__init__.py
Normal file
42
NAS-Bench-201/nas_201_api/__init__.py
Normal file
@ -0,0 +1,42 @@
|
||||
#####################################################
|
||||
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.08 #
|
||||
#####################################################
|
||||
from .api_utils import ArchResults, ResultsCount
|
||||
from .api_201 import NASBench201API
|
||||
|
||||
# NAS_BENCH_201_API_VERSION="v1.1" # [2020.02.25]
|
||||
# NAS_BENCH_201_API_VERSION="v1.2" # [2020.03.09]
|
||||
# NAS_BENCH_201_API_VERSION="v1.3" # [2020.03.16]
|
||||
NAS_BENCH_201_API_VERSION="v2.0" # [2020.06.30]
|
||||
|
||||
|
||||
def test_api(path):
|
||||
"""This is used to test the API of NAS-Bench-201."""
|
||||
api = NASBench201API(path)
|
||||
num = len(api)
|
||||
for i, arch_str in enumerate(api):
|
||||
print ('{:5d}/{:5d} : {:}'.format(i, len(api), arch_str))
|
||||
indexes = [1, 2, 11, 301]
|
||||
for index in indexes:
|
||||
print('\n--- index={:} ---'.format(index))
|
||||
api.show(index)
|
||||
# show the mean loss and accuracy of an architecture
|
||||
info = api.query_meta_info_by_index(index) # This is an instance of `ArchResults`
|
||||
res_metrics = info.get_metrics('cifar10', 'train') # This is a dict with metric names as keys
|
||||
cost_metrics = info.get_compute_costs('cifar100') # This is a dict with metric names as keys, e.g., flops, params, latency
|
||||
|
||||
# get the detailed information
|
||||
results = api.query_by_index(index, 'cifar100') # a dict of all trials for 1st net on cifar100, where the key is the seed
|
||||
print ('There are {:} trials for this architecture [{:}] on cifar100'.format(len(results), api[1]))
|
||||
for seed, result in results.items():
|
||||
print ('Latency : {:}'.format(result.get_latency()))
|
||||
print ('Train Info : {:}'.format(result.get_train()))
|
||||
print ('Valid Info : {:}'.format(result.get_eval('x-valid')))
|
||||
print ('Test Info : {:}'.format(result.get_eval('x-test')))
|
||||
# for the metric after a specific epoch
|
||||
print ('Train Info [10-th epoch] : {:}'.format(result.get_train(10)))
|
||||
config = api.get_net_config(index, 'cifar10')
|
||||
print ('config={:}'.format(config))
|
||||
index = api.query_index_by_arch('|nor_conv_3x3~0|+|nor_conv_3x3~0|avg_pool_3x3~1|+|skip_connect~0|nor_conv_3x3~1|skip_connect~2|')
|
||||
api.show(index)
|
||||
print('TEST NAS-BENCH-201 DONE.')
|
274
NAS-Bench-201/nas_201_api/api_201.py
Normal file
274
NAS-Bench-201/nas_201_api/api_201.py
Normal file
@ -0,0 +1,274 @@
|
||||
#####################################################
|
||||
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.08 #
|
||||
############################################################################################
|
||||
# NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search, ICLR 2020 #
|
||||
############################################################################################
|
||||
# The history of benchmark files:
|
||||
# [2020.02.25] NAS-Bench-201-v1_0-e61699.pth : 6219 architectures are trained once, 1621 architectures are trained twice, 7785 architectures are trained three times. `LESS` only supports CIFAR10-VALID.
|
||||
# [2020.03.16] NAS-Bench-201-v1_1-096897.pth : 2225 architectures are trained once, 5439 archiitectures are trained twice, 7961 architectures are trained three times on all training sets. For the hyper-parameters with the total epochs of 12, each model is trained on CIFAR-10, CIFAR-100, ImageNet16-120 once, and is trained on CIFAR-10-VALID twice.
|
||||
#
|
||||
# I'm still actively enhancing this benchmark, while it is now maintained at https://github.com/D-X-Y/NATS-Bench
|
||||
#
|
||||
import os, copy, random, torch, numpy as np
|
||||
from pathlib import Path
|
||||
from typing import List, Text, Union, Dict, Optional
|
||||
from collections import OrderedDict, defaultdict
|
||||
|
||||
from .api_utils import ArchResults
|
||||
from .api_utils import NASBenchMetaAPI
|
||||
from .api_utils import remap_dataset_set_names
|
||||
|
||||
|
||||
ALL_BENCHMARK_FILES = ['NAS-Bench-201-v1_0-e61699.pth', 'NAS-Bench-201-v1_1-096897.pth']
|
||||
ALL_ARCHIVE_DIRS = ['NAS-Bench-201-v1_1-archive']
|
||||
|
||||
|
||||
def print_information(information, extra_info=None, show=False):
|
||||
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 ida, dataset in enumerate(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
|
||||
|
||||
|
||||
"""
|
||||
This is the class for the API of NAS-Bench-201.
|
||||
"""
|
||||
class NASBench201API(NASBenchMetaAPI):
|
||||
|
||||
""" The initialization function that takes the dataset file path (or a dict loaded from that path) as input. """
|
||||
def __init__(self, file_path_or_dict: Optional[Union[Text, Dict]]=None,
|
||||
verbose: bool=True):
|
||||
self.filename = None
|
||||
self.reset_time()
|
||||
if file_path_or_dict is None:
|
||||
file_path_or_dict = os.path.join(os.environ['TORCH_HOME'], ALL_BENCHMARK_FILES[-1])
|
||||
print ('Try to use the default NAS-Bench-201 path from {:}.'.format(file_path_or_dict))
|
||||
if isinstance(file_path_or_dict, str) or isinstance(file_path_or_dict, Path):
|
||||
file_path_or_dict = str(file_path_or_dict)
|
||||
if verbose: print('try to create the NAS-Bench-201 api from {:}'.format(file_path_or_dict))
|
||||
assert os.path.isfile(file_path_or_dict), 'invalid path : {:}'.format(file_path_or_dict)
|
||||
self.filename = Path(file_path_or_dict).name
|
||||
file_path_or_dict = torch.load(file_path_or_dict, map_location='cpu')
|
||||
elif isinstance(file_path_or_dict, dict):
|
||||
file_path_or_dict = copy.deepcopy(file_path_or_dict)
|
||||
else: raise ValueError('invalid type : {:} not in [str, dict]'.format(type(file_path_or_dict)))
|
||||
assert isinstance(file_path_or_dict, dict), 'It should be a dict instead of {:}'.format(type(file_path_or_dict))
|
||||
self.verbose = verbose # [TODO] a flag indicating whether to print more logs
|
||||
keys = ('meta_archs', 'arch2infos', 'evaluated_indexes')
|
||||
for key in keys: assert key in file_path_or_dict, 'Can not find key[{:}] in the dict'.format(key)
|
||||
self.meta_archs = copy.deepcopy( file_path_or_dict['meta_archs'] )
|
||||
# This is a dict mapping each architecture to a dict, where the key is #epochs and the value is ArchResults
|
||||
self.arch2infos_dict = OrderedDict()
|
||||
self._avaliable_hps = set(['12', '200'])
|
||||
for xkey in sorted(list(file_path_or_dict['arch2infos'].keys())):
|
||||
all_info = file_path_or_dict['arch2infos'][xkey]
|
||||
hp2archres = OrderedDict()
|
||||
# self.arch2infos_less[xkey] = ArchResults.create_from_state_dict( all_info['less'] )
|
||||
# self.arch2infos_full[xkey] = ArchResults.create_from_state_dict( all_info['full'] )
|
||||
hp2archres['12'] = ArchResults.create_from_state_dict(all_info['less'])
|
||||
hp2archres['200'] = ArchResults.create_from_state_dict(all_info['full'])
|
||||
self.arch2infos_dict[xkey] = hp2archres
|
||||
self.evaluated_indexes = sorted(list(file_path_or_dict['evaluated_indexes']))
|
||||
self.archstr2index = {}
|
||||
for idx, arch in enumerate(self.meta_archs):
|
||||
assert arch not in self.archstr2index, 'This [{:}]-th arch {:} already in the dict ({:}).'.format(idx, arch, self.archstr2index[arch])
|
||||
self.archstr2index[ arch ] = idx
|
||||
|
||||
def reload(self, archive_root: Text = None, index: int = None):
|
||||
"""Overwrite all information of the 'index'-th architecture in the search space.
|
||||
It will load its data from 'archive_root'.
|
||||
"""
|
||||
if archive_root is None:
|
||||
archive_root = os.path.join(os.environ['TORCH_HOME'], ALL_ARCHIVE_DIRS[-1])
|
||||
assert os.path.isdir(archive_root), 'invalid directory : {:}'.format(archive_root)
|
||||
if index is None:
|
||||
indexes = list(range(len(self)))
|
||||
else:
|
||||
indexes = [index]
|
||||
for idx in indexes:
|
||||
assert 0 <= idx < len(self.meta_archs), 'invalid index of {:}'.format(idx)
|
||||
xfile_path = os.path.join(archive_root, '{:06d}-FULL.pth'.format(idx))
|
||||
assert os.path.isfile(xfile_path), 'invalid data path : {:}'.format(xfile_path)
|
||||
xdata = torch.load(xfile_path, map_location='cpu')
|
||||
assert isinstance(xdata, dict) and 'full' in xdata and 'less' in xdata, 'invalid format of data in {:}'.format(xfile_path)
|
||||
hp2archres = OrderedDict()
|
||||
hp2archres['12'] = ArchResults.create_from_state_dict(xdata['less'])
|
||||
hp2archres['200'] = ArchResults.create_from_state_dict(xdata['full'])
|
||||
self.arch2infos_dict[idx] = hp2archres
|
||||
|
||||
def query_info_str_by_arch(self, arch, hp: Text='12'):
|
||||
""" This function is used to query the information of a specific architecture
|
||||
'arch' can be an architecture index or an architecture string
|
||||
When hp=12, the hyper-parameters used to train a model are in 'configs/nas-benchmark/hyper-opts/12E.config'
|
||||
When hp=200, the hyper-parameters used to train a model are in 'configs/nas-benchmark/hyper-opts/200E.config'
|
||||
The difference between these three configurations are the number of training epochs.
|
||||
"""
|
||||
if self.verbose:
|
||||
print('Call query_info_str_by_arch with arch={:} and hp={:}'.format(arch, hp))
|
||||
return self._query_info_str_by_arch(arch, hp, print_information)
|
||||
|
||||
# obtain the metric for the `index`-th architecture
|
||||
# `dataset` indicates the 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` indicates 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)
|
||||
# `use_12epochs_result` indicates different hyper-parameters for training
|
||||
# When use_12epochs_result=True, it trains the network with 12 epochs and the LR decayed from 0.1 to 0 within 12 epochs
|
||||
# When use_12epochs_result=False, it trains the network with 200 epochs and the LR decayed from 0.1 to 0 within 200 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.
|
||||
def get_more_info(self, index, dataset, iepoch=None, hp='12', is_random=True):
|
||||
if self.verbose:
|
||||
print('Call the get_more_info function with index={:}, dataset={:}, iepoch={:}, hp={:}, and is_random={:}.'.format(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
|
||||
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:
|
||||
test_info = None
|
||||
valtest_info = None
|
||||
else:
|
||||
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:
|
||||
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:
|
||||
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:
|
||||
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[tuple]:
|
||||
"""
|
||||
This function shows how to read the string-based architecture encoding.
|
||||
It is the same as the `str2structure` func in `AutoDL-Projects/lib/models/cell_searchs/genotypes.py`
|
||||
|
||||
:param
|
||||
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|
|
||||
:return: a list of tuple, contains multiple (op, input_node_index) pairs.
|
||||
|
||||
:usage
|
||||
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 i, node_str in enumerate(node_strs):
|
||||
inputs = list(filter(lambda x: x != '', node_str.split('|')))
|
||||
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:
|
||||
"""
|
||||
This func shows how to convert the string-based architecture encoding to the encoding strategy in NAS-Bench-101.
|
||||
|
||||
:param
|
||||
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 search space for NAS-Bench-201
|
||||
the default value should be be consistent with this line https://github.com/D-X-Y/AutoDL-Projects/blob/master/lib/models/cell_operations.py#L24
|
||||
:return
|
||||
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 NAS-Bench-201 search space, 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('|')))
|
||||
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
|
||||
|
750
NAS-Bench-201/nas_201_api/api_utils.py
Normal file
750
NAS-Bench-201/nas_201_api/api_utils.py
Normal file
@ -0,0 +1,750 @@
|
||||
#####################################################
|
||||
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.08 #
|
||||
############################################################################################
|
||||
# NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search, ICLR 2020 #
|
||||
############################################################################################
|
||||
# In this Python file, we define NASBenchMetaAPI, the abstract class for benchmark APIs.
|
||||
# We also define the class ArchResults, which contains all information of a single architecture trained by one kind of hyper-parameters on three datasets.
|
||||
# We also define the class ResultsCount, which contains all information of a single trial for a single architecture.
|
||||
############################################################################################
|
||||
# History:
|
||||
# [2020.06.30] The first version.
|
||||
#
|
||||
import os, abc, copy, random, torch, numpy as np
|
||||
from pathlib import Path
|
||||
from typing import List, Text, Union, Dict, Optional
|
||||
from collections import OrderedDict, defaultdict
|
||||
|
||||
|
||||
def remap_dataset_set_names(dataset, metric_on_set, verbose=False):
|
||||
"""re-map the metric_on_set to internal keys"""
|
||||
if verbose:
|
||||
print('Call internal function _remap_dataset_set_names with dataset={:} and metric_on_set={:}'.format(dataset, metric_on_set))
|
||||
if dataset == 'cifar10' and metric_on_set == 'valid':
|
||||
dataset, metric_on_set = 'cifar10-valid', 'x-valid'
|
||||
elif dataset == 'cifar10' and metric_on_set == 'test':
|
||||
dataset, metric_on_set = 'cifar10', 'ori-test'
|
||||
elif dataset == 'cifar10' and metric_on_set == 'train':
|
||||
dataset, metric_on_set = 'cifar10', 'train'
|
||||
elif (dataset == 'cifar100' or dataset == 'ImageNet16-120') and metric_on_set == 'valid':
|
||||
metric_on_set = 'x-valid'
|
||||
elif (dataset == 'cifar100' or dataset == 'ImageNet16-120') and metric_on_set == 'test':
|
||||
metric_on_set = 'x-test'
|
||||
if verbose:
|
||||
print(' return dataset={:} and metric_on_set={:}'.format(dataset, metric_on_set))
|
||||
return dataset, metric_on_set
|
||||
|
||||
|
||||
class NASBenchMetaAPI(metaclass=abc.ABCMeta):
|
||||
|
||||
@abc.abstractmethod
|
||||
def __init__(self, file_path_or_dict: Optional[Union[Text, Dict]]=None, verbose: bool=True):
|
||||
"""The initialization function that takes the dataset file path (or a dict loaded from that path) as input."""
|
||||
|
||||
def __getitem__(self, index: int):
|
||||
return copy.deepcopy(self.meta_archs[index])
|
||||
|
||||
def arch(self, index: int):
|
||||
"""Return the topology structure of the `index`-th architecture."""
|
||||
if self.verbose:
|
||||
print('Call the arch function with index={:}'.format(index))
|
||||
assert 0 <= index < len(self.meta_archs), 'invalid index : {:} vs. {:}.'.format(index, len(self.meta_archs))
|
||||
return copy.deepcopy(self.meta_archs[index])
|
||||
|
||||
def __len__(self):
|
||||
return len(self.meta_archs)
|
||||
|
||||
def __repr__(self):
|
||||
return ('{name}({num}/{total} architectures, file={filename})'.format(name=self.__class__.__name__, num=len(self.evaluated_indexes), total=len(self.meta_archs), filename=self.filename))
|
||||
|
||||
@property
|
||||
def avaliable_hps(self):
|
||||
return list(copy.deepcopy(self._avaliable_hps))
|
||||
|
||||
@property
|
||||
def used_time(self):
|
||||
return self._used_time
|
||||
|
||||
def reset_time(self):
|
||||
self._used_time = 0
|
||||
|
||||
def simulate_train_eval(self, arch, dataset, hp='12', account_time=True):
|
||||
index = self.query_index_by_arch(arch)
|
||||
all_names = ('cifar10', 'cifar100', 'ImageNet16-120')
|
||||
assert dataset in all_names, 'Invalid dataset name : {:} vs {:}'.format(dataset, all_names)
|
||||
if dataset == 'cifar10':
|
||||
info = self.get_more_info(index, 'cifar10-valid', iepoch=None, hp=hp, is_random=True)
|
||||
else:
|
||||
info = self.get_more_info(index, dataset, iepoch=None, hp=hp, is_random=True)
|
||||
valid_acc, time_cost = info['valid-accuracy'], info['train-all-time'] + info['valid-per-time']
|
||||
latency = self.get_latency(index, dataset)
|
||||
if account_time:
|
||||
self._used_time += time_cost
|
||||
return valid_acc, latency, time_cost, self._used_time
|
||||
|
||||
def random(self):
|
||||
"""Return a random index of all architectures."""
|
||||
return random.randint(0, len(self.meta_archs)-1)
|
||||
|
||||
def query_index_by_arch(self, arch):
|
||||
""" This function is used to query the index of an architecture in the search space.
|
||||
In the topology search space, the input arch can be an architecture string such as '|nor_conv_3x3~0|+|nor_conv_3x3~0|avg_pool_3x3~1|+|skip_connect~0|nor_conv_3x3~1|skip_connect~2|';
|
||||
or an instance that has the 'tostr' function that can generate the architecture string;
|
||||
or it is directly an architecture index, in this case, we will check whether it is valid or not.
|
||||
This function will return the index.
|
||||
If return -1, it means this architecture is not in the search space.
|
||||
Otherwise, it will return an int in [0, the-number-of-candidates-in-the-search-space).
|
||||
"""
|
||||
if self.verbose:
|
||||
print('Call query_index_by_arch with arch={:}'.format(arch))
|
||||
if isinstance(arch, int):
|
||||
if 0 <= arch < len(self):
|
||||
return arch
|
||||
else:
|
||||
raise ValueError('Invalid architecture index {:} vs [{:}, {:}].'.format(arch, 0, len(self)))
|
||||
elif isinstance(arch, str):
|
||||
if arch in self.archstr2index: arch_index = self.archstr2index[ arch ]
|
||||
else : arch_index = -1
|
||||
elif hasattr(arch, 'tostr'):
|
||||
if arch.tostr() in self.archstr2index: arch_index = self.archstr2index[ arch.tostr() ]
|
||||
else : arch_index = -1
|
||||
else: arch_index = -1
|
||||
return arch_index
|
||||
|
||||
def query_by_arch(self, arch, hp):
|
||||
# This is to make the current version be compatible with the old version.
|
||||
return self.query_info_str_by_arch(arch, hp)
|
||||
|
||||
@abc.abstractmethod
|
||||
def reload(self, archive_root: Text = None, index: int = None):
|
||||
"""Overwrite all information of the 'index'-th architecture in the search space, where the data will be loaded from 'archive_root'.
|
||||
If index is None, overwrite all ckps.
|
||||
"""
|
||||
|
||||
def clear_params(self, index: int, hp: Optional[Text]=None):
|
||||
"""Remove the architecture's weights to save memory.
|
||||
:arg
|
||||
index: the index of the target architecture
|
||||
hp: a flag to controll how to clear the parameters.
|
||||
-- None: clear all the weights in '01'/'12'/'90', which indicates the number of training epochs.
|
||||
-- '01' or '12' or '90': clear all the weights in arch2infos_dict[index][hp].
|
||||
"""
|
||||
if self.verbose:
|
||||
print('Call clear_params with index={:} and hp={:}'.format(index, hp))
|
||||
if hp is None:
|
||||
for key, result in self.arch2infos_dict[index].items():
|
||||
result.clear_params()
|
||||
else:
|
||||
if str(hp) not in self.arch2infos_dict[index]:
|
||||
raise ValueError('The {:}-th architecture only has hyper-parameters of {:} instead of {:}.'.format(index, list(self.arch2infos_dict[index].keys()), hp))
|
||||
self.arch2infos_dict[index][str(hp)].clear_params()
|
||||
|
||||
@abc.abstractmethod
|
||||
def query_info_str_by_arch(self, arch, hp: Text='12'):
|
||||
"""This function is used to query the information of a specific architecture."""
|
||||
|
||||
def _query_info_str_by_arch(self, arch, hp: Text='12', print_information=None):
|
||||
arch_index = self.query_index_by_arch(arch)
|
||||
if arch_index in self.arch2infos_dict:
|
||||
if hp not in self.arch2infos_dict[arch_index]:
|
||||
raise ValueError('The {:}-th architecture only has hyper-parameters of {:} instead of {:}.'.format(index, list(self.arch2infos_dict[arch_index].keys()), hp))
|
||||
info = self.arch2infos_dict[arch_index][hp]
|
||||
strings = print_information(info, 'arch-index={:}'.format(arch_index))
|
||||
return '\n'.join(strings)
|
||||
else:
|
||||
print ('Find this arch-index : {:}, but this arch is not evaluated.'.format(arch_index))
|
||||
return None
|
||||
|
||||
def query_meta_info_by_index(self, arch_index, hp: Text = '12'):
|
||||
"""Return the ArchResults for the 'arch_index'-th architecture. This function is similar to query_by_index."""
|
||||
if self.verbose:
|
||||
print('Call query_meta_info_by_index with arch_index={:}, hp={:}'.format(arch_index, hp))
|
||||
if arch_index in self.arch2infos_dict:
|
||||
if hp not in self.arch2infos_dict[arch_index]:
|
||||
raise ValueError('The {:}-th architecture only has hyper-parameters of {:} instead of {:}.'.format(arch_index, list(self.arch2infos_dict[arch_index].keys()), hp))
|
||||
info = self.arch2infos_dict[arch_index][hp]
|
||||
else:
|
||||
raise ValueError('arch_index [{:}] does not in arch2infos'.format(arch_index))
|
||||
return copy.deepcopy(info)
|
||||
|
||||
def query_by_index(self, arch_index: int, dataname: Union[None, Text] = None, hp: Text = '12'):
|
||||
""" This 'query_by_index' function is used to query information with the training of 01 epochs, 12 epochs, 90 epochs, or 200 epochs.
|
||||
------
|
||||
If hp=01, we train the model by 01 epochs (see config in configs/nas-benchmark/hyper-opts/01E.config)
|
||||
If hp=12, we train the model by 01 epochs (see config in configs/nas-benchmark/hyper-opts/12E.config)
|
||||
If hp=90, we train the model by 01 epochs (see config in configs/nas-benchmark/hyper-opts/90E.config)
|
||||
If hp=200, we train the model by 01 epochs (see config in configs/nas-benchmark/hyper-opts/200E.config)
|
||||
------
|
||||
If dataname is None, return the ArchResults
|
||||
else, return a dict with all trials on that dataset (the key is the seed)
|
||||
Options are 'cifar10-valid', 'cifar10', 'cifar100', 'ImageNet16-120'.
|
||||
-- cifar10-valid : training the model on the CIFAR-10 training set.
|
||||
-- cifar10 : training the model on the CIFAR-10 training + validation set.
|
||||
-- cifar100 : training the model on the CIFAR-100 training set.
|
||||
-- ImageNet16-120 : training the model on the ImageNet16-120 training set.
|
||||
"""
|
||||
if self.verbose:
|
||||
print('Call query_by_index with arch_index={:}, dataname={:}, hp={:}'.format(arch_index, dataname, hp))
|
||||
info = self.query_meta_info_by_index(arch_index, hp)
|
||||
if dataname is None: return info
|
||||
else:
|
||||
if dataname not in info.get_dataset_names():
|
||||
raise ValueError('invalid dataset-name : {:} vs. {:}'.format(dataname, info.get_dataset_names()))
|
||||
return info.query(dataname)
|
||||
|
||||
def find_best(self, dataset, metric_on_set, FLOP_max=None, Param_max=None, hp: Text = '12'):
|
||||
"""Find the architecture with the highest accuracy based on some constraints."""
|
||||
if self.verbose:
|
||||
print('Call find_best with dataset={:}, metric_on_set={:}, hp={:} | with #FLOPs < {:} and #Params < {:}'.format(dataset, metric_on_set, hp, FLOP_max, Param_max))
|
||||
dataset, metric_on_set = remap_dataset_set_names(dataset, metric_on_set, self.verbose)
|
||||
best_index, highest_accuracy = -1, None
|
||||
for i, arch_index in enumerate(self.evaluated_indexes):
|
||||
arch_info = self.arch2infos_dict[arch_index][hp]
|
||||
info = arch_info.get_compute_costs(dataset) # the information of costs
|
||||
flop, param, latency = info['flops'], info['params'], info['latency']
|
||||
if FLOP_max is not None and flop > FLOP_max : continue
|
||||
if Param_max is not None and param > Param_max: continue
|
||||
xinfo = arch_info.get_metrics(dataset, metric_on_set) # the information of loss and accuracy
|
||||
loss, accuracy = xinfo['loss'], xinfo['accuracy']
|
||||
if best_index == -1:
|
||||
best_index, highest_accuracy = arch_index, accuracy
|
||||
elif highest_accuracy < accuracy:
|
||||
best_index, highest_accuracy = arch_index, accuracy
|
||||
if self.verbose:
|
||||
print(' the best architecture : [{:}] {:} with accuracy={:.3f}%'.format(best_index, self.arch(best_index), highest_accuracy))
|
||||
return best_index, highest_accuracy
|
||||
|
||||
def get_net_param(self, index, dataset, seed: Optional[int], hp: Text = '12'):
|
||||
"""
|
||||
This function is used to obtain the trained weights of the `index`-th architecture on `dataset` with the seed of `seed`
|
||||
Args [seed]:
|
||||
-- None : return a dict containing the trained weights of all trials, where each key is a seed and its corresponding value is the weights.
|
||||
-- a interger : return the weights of a specific trial, whose seed is this interger.
|
||||
Args [hp]:
|
||||
-- 01 : train the model by 01 epochs
|
||||
-- 12 : train the model by 12 epochs
|
||||
-- 90 : train the model by 90 epochs
|
||||
-- 200 : train the model by 200 epochs
|
||||
"""
|
||||
if self.verbose:
|
||||
print('Call the get_net_param function with index={:}, dataset={:}, seed={:}, hp={:}'.format(index, dataset, seed, hp))
|
||||
info = self.query_meta_info_by_index(index, hp)
|
||||
return info.get_net_param(dataset, seed)
|
||||
|
||||
def get_net_config(self, index: int, dataset: Text):
|
||||
"""
|
||||
This function is used to obtain the configuration for the `index`-th architecture on `dataset`.
|
||||
Args [dataset] (4 possible options):
|
||||
-- cifar10-valid : training the model on the CIFAR-10 training set.
|
||||
-- cifar10 : training the model on the CIFAR-10 training + validation set.
|
||||
-- cifar100 : training the model on the CIFAR-100 training set.
|
||||
-- ImageNet16-120 : training the model on the ImageNet16-120 training set.
|
||||
This function will return a dict.
|
||||
========= Some examlpes for using this function:
|
||||
config = api.get_net_config(128, 'cifar10')
|
||||
"""
|
||||
if self.verbose:
|
||||
print('Call the get_net_config function with index={:}, dataset={:}.'.format(index, dataset))
|
||||
if index in self.arch2infos_dict:
|
||||
info = self.arch2infos_dict[index]
|
||||
else:
|
||||
raise ValueError('The arch_index={:} is not in arch2infos_dict.'.format(arch_index))
|
||||
info = next(iter(info.values()))
|
||||
results = info.query(dataset, None)
|
||||
results = next(iter(results.values()))
|
||||
return results.get_config(None)
|
||||
|
||||
def get_cost_info(self, index: int, dataset: Text, hp: Text = '12') -> Dict[Text, float]:
|
||||
"""To obtain the cost metric for the `index`-th architecture on a dataset."""
|
||||
if self.verbose:
|
||||
print('Call the get_cost_info function with index={:}, dataset={:}, and hp={:}.'.format(index, dataset, hp))
|
||||
info = self.query_meta_info_by_index(index, hp)
|
||||
return info.get_compute_costs(dataset)
|
||||
|
||||
def get_latency(self, index: int, dataset: Text, hp: Text = '12') -> float:
|
||||
"""
|
||||
To obtain the latency of the network (by default it will return the latency with the batch size of 256).
|
||||
:param index: the index of the target architecture
|
||||
:param dataset: the dataset name (cifar10-valid, cifar10, cifar100, ImageNet16-120)
|
||||
:return: return a float value in seconds
|
||||
"""
|
||||
if self.verbose:
|
||||
print('Call the get_latency function with index={:}, dataset={:}, and hp={:}.'.format(index, dataset, hp))
|
||||
cost_dict = self.get_cost_info(index, dataset, hp)
|
||||
return cost_dict['latency']
|
||||
|
||||
@abc.abstractmethod
|
||||
def show(self, index=-1):
|
||||
"""This function will print the information of a specific (or all) architecture(s)."""
|
||||
|
||||
def _show(self, index=-1, print_information=None) -> None:
|
||||
"""
|
||||
This function will print the information of a specific (or all) architecture(s).
|
||||
|
||||
:param index: If the index < 0: it will loop for all architectures and print their information one by one.
|
||||
else: it will print the information of the 'index'-th architecture.
|
||||
:return: nothing
|
||||
"""
|
||||
if index < 0: # show all architectures
|
||||
print(self)
|
||||
for i, idx in enumerate(self.evaluated_indexes):
|
||||
print('\n' + '-' * 10 + ' The ({:5d}/{:5d}) {:06d}-th architecture! '.format(i, len(self.evaluated_indexes), idx) + '-'*10)
|
||||
print('arch : {:}'.format(self.meta_archs[idx]))
|
||||
for key, result in self.arch2infos_dict[index].items():
|
||||
strings = print_information(result)
|
||||
print('>' * 40 + ' {:03d} epochs '.format(result.get_total_epoch()) + '>' * 40)
|
||||
print('\n'.join(strings))
|
||||
print('<' * 40 + '------------' + '<' * 40)
|
||||
else:
|
||||
if 0 <= index < len(self.meta_archs):
|
||||
if index not in self.evaluated_indexes: print('The {:}-th architecture has not been evaluated or not saved.'.format(index))
|
||||
else:
|
||||
arch_info = self.arch2infos_dict[index]
|
||||
for key, result in self.arch2infos_dict[index].items():
|
||||
strings = print_information(result)
|
||||
print('>' * 40 + ' {:03d} epochs '.format(result.get_total_epoch()) + '>' * 40)
|
||||
print('\n'.join(strings))
|
||||
print('<' * 40 + '------------' + '<' * 40)
|
||||
else:
|
||||
print('This index ({:}) is out of range (0~{:}).'.format(index, len(self.meta_archs)))
|
||||
|
||||
def statistics(self, dataset: Text, hp: Union[Text, int]) -> Dict[int, int]:
|
||||
"""This function will count the number of total trials."""
|
||||
if self.verbose:
|
||||
print('Call the statistics function with dataset={:} and hp={:}.'.format(dataset, hp))
|
||||
valid_datasets = ['cifar10-valid', 'cifar10', 'cifar100', 'ImageNet16-120']
|
||||
if dataset not in valid_datasets:
|
||||
raise ValueError('{:} not in {:}'.format(dataset, valid_datasets))
|
||||
nums, hp = defaultdict(lambda: 0), str(hp)
|
||||
for index in range(len(self)):
|
||||
archInfo = self.arch2infos_dict[index][hp]
|
||||
dataset_seed = archInfo.dataset_seed
|
||||
if dataset not in dataset_seed:
|
||||
nums[0] += 1
|
||||
else:
|
||||
nums[len(dataset_seed[dataset])] += 1
|
||||
return dict(nums)
|
||||
|
||||
|
||||
class ArchResults(object):
|
||||
|
||||
def __init__(self, arch_index, arch_str):
|
||||
self.arch_index = int(arch_index)
|
||||
self.arch_str = copy.deepcopy(arch_str)
|
||||
self.all_results = dict()
|
||||
self.dataset_seed = dict()
|
||||
self.clear_net_done = False
|
||||
|
||||
def get_compute_costs(self, dataset):
|
||||
x_seeds = self.dataset_seed[dataset]
|
||||
results = [self.all_results[ (dataset, seed) ] for seed in x_seeds]
|
||||
|
||||
flops = [result.flop for result in results]
|
||||
params = [result.params for result in results]
|
||||
latencies = [result.get_latency() for result in results]
|
||||
latencies = [x for x in latencies if x > 0]
|
||||
mean_latency = np.mean(latencies) if len(latencies) > 0 else None
|
||||
time_infos = defaultdict(list)
|
||||
for result in results:
|
||||
time_info = result.get_times()
|
||||
for key, value in time_info.items(): time_infos[key].append( value )
|
||||
|
||||
info = {'flops' : np.mean(flops),
|
||||
'params' : np.mean(params),
|
||||
'latency': mean_latency}
|
||||
for key, value in time_infos.items():
|
||||
if len(value) > 0 and value[0] is not None:
|
||||
info[key] = np.mean(value)
|
||||
else: info[key] = None
|
||||
return info
|
||||
|
||||
def get_metrics(self, dataset, setname, iepoch=None, is_random=False):
|
||||
"""
|
||||
This `get_metrics` function is used to obtain obtain the loss, accuracy, etc information on a specific dataset.
|
||||
If not specify, each set refer to the proposed split in NAS-Bench-201 paper.
|
||||
If some args return None or raise error, then it is not avaliable.
|
||||
========================================
|
||||
Args [dataset] (4 possible options):
|
||||
-- cifar10-valid : training the model on the CIFAR-10 training set.
|
||||
-- cifar10 : training the model on the CIFAR-10 training + validation set.
|
||||
-- cifar100 : training the model on the CIFAR-100 training set.
|
||||
-- ImageNet16-120 : training the model on the ImageNet16-120 training set.
|
||||
Args [setname] (each dataset has different setnames):
|
||||
-- When dataset = cifar10-valid, you can use 'train', 'x-valid', 'ori-test'
|
||||
------ 'train' : the metric on the training set.
|
||||
------ 'x-valid' : the metric on the validation set.
|
||||
------ 'ori-test' : the metric on the test set.
|
||||
-- When dataset = cifar10, you can use 'train', 'ori-test'.
|
||||
------ 'train' : the metric on the training + validation set.
|
||||
------ 'ori-test' : the metric on the test set.
|
||||
-- When dataset = cifar100 or ImageNet16-120, you can use 'train', 'ori-test', 'x-valid', 'x-test'
|
||||
------ 'train' : the metric on the training set.
|
||||
------ 'x-valid' : the metric on the validation set.
|
||||
------ 'x-test' : the metric on the test set.
|
||||
------ 'ori-test' : the metric on the validation + test set.
|
||||
Args [iepoch] (None or an integer in [0, the-number-of-total-training-epochs)
|
||||
------ None : return the metric after the last training epoch.
|
||||
------ an integer i : return the metric after the i-th training epoch.
|
||||
Args [is_random]:
|
||||
------ True : return the metric of a randomly selected trial.
|
||||
------ False : return the averaged metric of all avaliable trials.
|
||||
------ an integer indicating the 'seed' value : return the metric of a specific trial (whose random seed is 'is_random').
|
||||
"""
|
||||
x_seeds = self.dataset_seed[dataset]
|
||||
results = [self.all_results[ (dataset, seed) ] for seed in x_seeds]
|
||||
infos = defaultdict(list)
|
||||
for result in results:
|
||||
if setname == 'train':
|
||||
info = result.get_train(iepoch)
|
||||
else:
|
||||
info = result.get_eval(setname, iepoch)
|
||||
for key, value in info.items(): infos[key].append( value )
|
||||
return_info = dict()
|
||||
if isinstance(is_random, bool) and is_random: # randomly select one
|
||||
index = random.randint(0, len(results)-1)
|
||||
for key, value in infos.items(): return_info[key] = value[index]
|
||||
elif isinstance(is_random, bool) and not is_random: # average
|
||||
for key, value in infos.items():
|
||||
if len(value) > 0 and value[0] is not None:
|
||||
return_info[key] = np.mean(value)
|
||||
else: return_info[key] = None
|
||||
elif isinstance(is_random, int): # specify the seed
|
||||
if is_random not in x_seeds: raise ValueError('can not find random seed ({:}) from {:}'.format(is_random, x_seeds))
|
||||
index = x_seeds.index(is_random)
|
||||
for key, value in infos.items(): return_info[key] = value[index]
|
||||
else:
|
||||
raise ValueError('invalid value for is_random: {:}'.format(is_random))
|
||||
return return_info
|
||||
|
||||
def show(self, is_print=False):
|
||||
return print_information(self, None, is_print)
|
||||
|
||||
def get_dataset_names(self):
|
||||
return list(self.dataset_seed.keys())
|
||||
|
||||
def get_dataset_seeds(self, dataset):
|
||||
return copy.deepcopy( self.dataset_seed[dataset] )
|
||||
|
||||
def get_net_param(self, dataset: Text, seed: Union[None, int] =None):
|
||||
"""
|
||||
This function will return the trained network's weights on the 'dataset'.
|
||||
:arg
|
||||
dataset: one of 'cifar10-valid', 'cifar10', 'cifar100', and 'ImageNet16-120'.
|
||||
seed: an integer indicates the seed value or None that indicates returing all trials.
|
||||
"""
|
||||
if seed is None:
|
||||
x_seeds = self.dataset_seed[dataset]
|
||||
return {seed: self.all_results[(dataset, seed)].get_net_param() for seed in x_seeds}
|
||||
else:
|
||||
xkey = (dataset, seed)
|
||||
if xkey in self.all_results:
|
||||
return self.all_results[xkey].get_net_param()
|
||||
else:
|
||||
raise ValueError('key={:} not in {:}'.format(xkey, list(self.all_results.keys())))
|
||||
|
||||
def reset_latency(self, dataset: Text, seed: Union[None, Text], latency: float) -> None:
|
||||
"""This function is used to reset the latency in all corresponding ResultsCount(s)."""
|
||||
if seed is None:
|
||||
for seed in self.dataset_seed[dataset]:
|
||||
self.all_results[(dataset, seed)].update_latency([latency])
|
||||
else:
|
||||
self.all_results[(dataset, seed)].update_latency([latency])
|
||||
|
||||
def reset_pseudo_train_times(self, dataset: Text, seed: Union[None, Text], estimated_per_epoch_time: float) -> None:
|
||||
"""This function is used to reset the train-times in all corresponding ResultsCount(s)."""
|
||||
if seed is None:
|
||||
for seed in self.dataset_seed[dataset]:
|
||||
self.all_results[(dataset, seed)].reset_pseudo_train_times(estimated_per_epoch_time)
|
||||
else:
|
||||
self.all_results[(dataset, seed)].reset_pseudo_train_times(estimated_per_epoch_time)
|
||||
|
||||
def reset_pseudo_eval_times(self, dataset: Text, seed: Union[None, Text], eval_name: Text, estimated_per_epoch_time: float) -> None:
|
||||
"""This function is used to reset the eval-times in all corresponding ResultsCount(s)."""
|
||||
if seed is None:
|
||||
for seed in self.dataset_seed[dataset]:
|
||||
self.all_results[(dataset, seed)].reset_pseudo_eval_times(eval_name, estimated_per_epoch_time)
|
||||
else:
|
||||
self.all_results[(dataset, seed)].reset_pseudo_eval_times(eval_name, estimated_per_epoch_time)
|
||||
|
||||
def get_latency(self, dataset: Text) -> float:
|
||||
"""Get the latency of a model on the target dataset. [Timestamp: 2020.03.09]"""
|
||||
latencies = []
|
||||
for seed in self.dataset_seed[dataset]:
|
||||
latency = self.all_results[(dataset, seed)].get_latency()
|
||||
if not isinstance(latency, float) or latency <= 0:
|
||||
raise ValueError('invalid latency of {:} with seed={:} : {:}'.format(dataset, seed, latency))
|
||||
latencies.append(latency)
|
||||
return sum(latencies) / len(latencies)
|
||||
|
||||
def get_total_epoch(self, dataset=None):
|
||||
"""Return the total number of training epochs."""
|
||||
if dataset is None:
|
||||
epochss = []
|
||||
for xdata, x_seeds in self.dataset_seed.items():
|
||||
epochss += [self.all_results[(xdata, seed)].get_total_epoch() for seed in x_seeds]
|
||||
elif isinstance(dataset, str):
|
||||
x_seeds = self.dataset_seed[dataset]
|
||||
epochss = [self.all_results[(dataset, seed)].get_total_epoch() for seed in x_seeds]
|
||||
else:
|
||||
raise ValueError('invalid dataset={:}'.format(dataset))
|
||||
if len(set(epochss)) > 1: raise ValueError('Each trial mush have the same number of training epochs : {:}'.format(epochss))
|
||||
return epochss[-1]
|
||||
|
||||
def query(self, dataset, seed=None):
|
||||
"""Return the ResultsCount object (containing all information of a single trial) for 'dataset' and 'seed'"""
|
||||
if seed is None:
|
||||
x_seeds = self.dataset_seed[dataset]
|
||||
return {seed: self.all_results[(dataset, seed)] for seed in x_seeds}
|
||||
else:
|
||||
return self.all_results[(dataset, seed)]
|
||||
|
||||
def arch_idx_str(self):
|
||||
return '{:06d}'.format(self.arch_index)
|
||||
|
||||
def update(self, dataset_name, seed, result):
|
||||
if dataset_name not in self.dataset_seed:
|
||||
self.dataset_seed[dataset_name] = []
|
||||
assert seed not in self.dataset_seed[dataset_name], '{:}-th arch alreadly has this seed ({:}) on {:}'.format(self.arch_index, seed, dataset_name)
|
||||
self.dataset_seed[ dataset_name ].append( seed )
|
||||
self.dataset_seed[ dataset_name ] = sorted( self.dataset_seed[ dataset_name ] )
|
||||
assert (dataset_name, seed) not in self.all_results
|
||||
self.all_results[ (dataset_name, seed) ] = result
|
||||
self.clear_net_done = False
|
||||
|
||||
def state_dict(self):
|
||||
state_dict = dict()
|
||||
for key, value in self.__dict__.items():
|
||||
if key == 'all_results': # contain the class of ResultsCount
|
||||
xvalue = dict()
|
||||
assert isinstance(value, dict), 'invalid type of value for {:} : {:}'.format(key, type(value))
|
||||
for _k, _v in value.items():
|
||||
assert isinstance(_v, ResultsCount), 'invalid type of value for {:}/{:} : {:}'.format(key, _k, type(_v))
|
||||
xvalue[_k] = _v.state_dict()
|
||||
else:
|
||||
xvalue = value
|
||||
state_dict[key] = xvalue
|
||||
return state_dict
|
||||
|
||||
def load_state_dict(self, state_dict):
|
||||
new_state_dict = dict()
|
||||
for key, value in state_dict.items():
|
||||
if key == 'all_results': # to convert to the class of ResultsCount
|
||||
xvalue = dict()
|
||||
assert isinstance(value, dict), 'invalid type of value for {:} : {:}'.format(key, type(value))
|
||||
for _k, _v in value.items():
|
||||
xvalue[_k] = ResultsCount.create_from_state_dict(_v)
|
||||
else: xvalue = value
|
||||
new_state_dict[key] = xvalue
|
||||
self.__dict__.update(new_state_dict)
|
||||
|
||||
@staticmethod
|
||||
def create_from_state_dict(state_dict_or_file):
|
||||
x = ArchResults(-1, -1)
|
||||
if isinstance(state_dict_or_file, str): # a file path
|
||||
state_dict = torch.load(state_dict_or_file, map_location='cpu')
|
||||
elif isinstance(state_dict_or_file, dict):
|
||||
state_dict = state_dict_or_file
|
||||
else:
|
||||
raise ValueError('invalid type of state_dict_or_file : {:}'.format(type(state_dict_or_file)))
|
||||
x.load_state_dict(state_dict)
|
||||
return x
|
||||
|
||||
# This function is used to clear the weights saved in each 'result'
|
||||
# This can help reduce the memory footprint.
|
||||
def clear_params(self):
|
||||
for key, result in self.all_results.items():
|
||||
del result.net_state_dict
|
||||
result.net_state_dict = None
|
||||
self.clear_net_done = True
|
||||
|
||||
def debug_test(self):
|
||||
"""This function is used for me to debug and test, which will call most methods."""
|
||||
all_dataset = ['cifar10-valid', 'cifar10', 'cifar100', 'ImageNet16-120']
|
||||
for dataset in all_dataset:
|
||||
print('---->>>> {:}'.format(dataset))
|
||||
print('The latency on {:} is {:} s'.format(dataset, self.get_latency(dataset)))
|
||||
for seed in self.dataset_seed[dataset]:
|
||||
result = self.all_results[(dataset, seed)]
|
||||
print(' ==>> result = {:}'.format(result))
|
||||
print(' ==>> cost = {:}'.format(result.get_times()))
|
||||
|
||||
def __repr__(self):
|
||||
return ('{name}(arch-index={index}, arch={arch}, {num} runs, clear={clear})'.format(name=self.__class__.__name__, index=self.arch_index, arch=self.arch_str, num=len(self.all_results), clear=self.clear_net_done))
|
||||
|
||||
|
||||
"""
|
||||
This class (ResultsCount) is used to save the information of one trial for a single architecture.
|
||||
I did not write much comment for this class, because it is the lowest-level class in NAS-Bench-201 API, which will be rarely called.
|
||||
If you have any question regarding this class, please open an issue or email me.
|
||||
"""
|
||||
class ResultsCount(object):
|
||||
|
||||
def __init__(self, name, state_dict, train_accs, train_losses, params, flop, arch_config, seed, epochs, latency):
|
||||
self.name = name
|
||||
self.net_state_dict = state_dict
|
||||
self.train_acc1es = copy.deepcopy(train_accs)
|
||||
self.train_acc5es = None
|
||||
self.train_losses = copy.deepcopy(train_losses)
|
||||
self.train_times = None
|
||||
self.arch_config = copy.deepcopy(arch_config)
|
||||
self.params = params
|
||||
self.flop = flop
|
||||
self.seed = seed
|
||||
self.epochs = epochs
|
||||
self.latency = latency
|
||||
# evaluation results
|
||||
self.reset_eval()
|
||||
|
||||
def update_train_info(self, train_acc1es, train_acc5es, train_losses, train_times) -> None:
|
||||
self.train_acc1es = train_acc1es
|
||||
self.train_acc5es = train_acc5es
|
||||
self.train_losses = train_losses
|
||||
self.train_times = train_times
|
||||
|
||||
def reset_pseudo_train_times(self, estimated_per_epoch_time: float) -> None:
|
||||
"""Assign the training times."""
|
||||
train_times = OrderedDict()
|
||||
for i in range(self.epochs):
|
||||
train_times[i] = estimated_per_epoch_time
|
||||
self.train_times = train_times
|
||||
|
||||
def reset_pseudo_eval_times(self, eval_name: Text, estimated_per_epoch_time: float) -> None:
|
||||
"""Assign the evaluation times."""
|
||||
if eval_name not in self.eval_names: raise ValueError('invalid eval name : {:}'.format(eval_name))
|
||||
for i in range(self.epochs):
|
||||
self.eval_times['{:}@{:}'.format(eval_name,i)] = estimated_per_epoch_time
|
||||
|
||||
def reset_eval(self):
|
||||
self.eval_names = []
|
||||
self.eval_acc1es = {}
|
||||
self.eval_times = {}
|
||||
self.eval_losses = {}
|
||||
|
||||
def update_latency(self, latency):
|
||||
self.latency = copy.deepcopy( latency )
|
||||
|
||||
def get_latency(self) -> float:
|
||||
"""Return the latency value in seconds. -1 represents not avaliable ; otherwise it should be a float value"""
|
||||
if self.latency is None: return -1.0
|
||||
else: return sum(self.latency) / len(self.latency)
|
||||
|
||||
def update_eval(self, accs, losses, times): # new version
|
||||
data_names = set([x.split('@')[0] for x in accs.keys()])
|
||||
for data_name in data_names:
|
||||
assert data_name not in self.eval_names, '{:} has already been added into eval-names'.format(data_name)
|
||||
self.eval_names.append( data_name )
|
||||
for iepoch in range(self.epochs):
|
||||
xkey = '{:}@{:}'.format(data_name, iepoch)
|
||||
self.eval_acc1es[ xkey ] = accs[ xkey ]
|
||||
self.eval_losses[ xkey ] = losses[ xkey ]
|
||||
self.eval_times [ xkey ] = times[ xkey ]
|
||||
|
||||
def update_OLD_eval(self, name, accs, losses): # old version
|
||||
assert name not in self.eval_names, '{:} has already added'.format(name)
|
||||
self.eval_names.append( name )
|
||||
for iepoch in range(self.epochs):
|
||||
if iepoch in accs:
|
||||
self.eval_acc1es['{:}@{:}'.format(name,iepoch)] = accs[iepoch]
|
||||
self.eval_losses['{:}@{:}'.format(name,iepoch)] = losses[iepoch]
|
||||
|
||||
def __repr__(self):
|
||||
num_eval = len(self.eval_names)
|
||||
set_name = '[' + ', '.join(self.eval_names) + ']'
|
||||
return ('{name}({xname}, arch={arch}, FLOP={flop:.2f}M, Param={param:.3f}MB, seed={seed}, {num_eval} eval-sets: {set_name})'.format(name=self.__class__.__name__, xname=self.name, arch=self.arch_config['arch_str'], flop=self.flop, param=self.params, seed=self.seed, num_eval=num_eval, set_name=set_name))
|
||||
|
||||
def get_total_epoch(self):
|
||||
return copy.deepcopy(self.epochs)
|
||||
|
||||
def get_times(self):
|
||||
"""Obtain the information regarding both training and evaluation time."""
|
||||
if self.train_times is not None and isinstance(self.train_times, dict):
|
||||
train_times = list( self.train_times.values() )
|
||||
time_info = {'T-train@epoch': np.mean(train_times), 'T-train@total': np.sum(train_times)}
|
||||
else:
|
||||
time_info = {'T-train@epoch': None, 'T-train@total': None }
|
||||
for name in self.eval_names:
|
||||
try:
|
||||
xtimes = [self.eval_times['{:}@{:}'.format(name,i)] for i in range(self.epochs)]
|
||||
time_info['T-{:}@epoch'.format(name)] = np.mean(xtimes)
|
||||
time_info['T-{:}@total'.format(name)] = np.sum(xtimes)
|
||||
except:
|
||||
time_info['T-{:}@epoch'.format(name)] = None
|
||||
time_info['T-{:}@total'.format(name)] = None
|
||||
return time_info
|
||||
|
||||
def get_eval_set(self):
|
||||
return self.eval_names
|
||||
|
||||
# get the training information
|
||||
def get_train(self, iepoch=None):
|
||||
if iepoch is None: iepoch = self.epochs-1
|
||||
assert 0 <= iepoch < self.epochs, 'invalid iepoch={:} < {:}'.format(iepoch, self.epochs)
|
||||
if self.train_times is not None:
|
||||
xtime = self.train_times[iepoch]
|
||||
atime = sum([self.train_times[i] for i in range(iepoch+1)])
|
||||
else: xtime, atime = None, None
|
||||
return {'iepoch' : iepoch,
|
||||
'loss' : self.train_losses[iepoch],
|
||||
'accuracy': self.train_acc1es[iepoch],
|
||||
'cur_time': xtime,
|
||||
'all_time': atime}
|
||||
|
||||
def get_eval(self, name, iepoch=None):
|
||||
"""Get the evaluation information ; there could be multiple evaluation sets (identified by the 'name' argument)."""
|
||||
if iepoch is None: iepoch = self.epochs-1
|
||||
assert 0 <= iepoch < self.epochs, 'invalid iepoch={:} < {:}'.format(iepoch, self.epochs)
|
||||
def _internal_query(xname):
|
||||
if isinstance(self.eval_times,dict) and len(self.eval_times) > 0:
|
||||
xtime = self.eval_times['{:}@{:}'.format(xname, iepoch)]
|
||||
atime = sum([self.eval_times['{:}@{:}'.format(xname, i)] for i in range(iepoch+1)])
|
||||
else:
|
||||
xtime, atime = None, None
|
||||
return {'iepoch' : iepoch,
|
||||
'loss' : self.eval_losses['{:}@{:}'.format(xname, iepoch)],
|
||||
'accuracy': self.eval_acc1es['{:}@{:}'.format(xname, iepoch)],
|
||||
'cur_time': xtime,
|
||||
'all_time': atime}
|
||||
if name == 'valid':
|
||||
return _internal_query('x-valid')
|
||||
else:
|
||||
return _internal_query(name)
|
||||
|
||||
def get_net_param(self, clone=False):
|
||||
if clone: return copy.deepcopy(self.net_state_dict)
|
||||
else: return self.net_state_dict
|
||||
|
||||
def get_config(self, str2structure):
|
||||
"""This function is used to obtain the config dict for this architecture."""
|
||||
if str2structure is None:
|
||||
# In this case, this is NAS-Bench-301
|
||||
if 'name' in self.arch_config and self.arch_config['name'] == 'infer.shape.tiny':
|
||||
return {'name': 'infer.shape.tiny', 'channels': self.arch_config['channels'],
|
||||
'genotype': self.arch_config['genotype'], 'num_classes': self.arch_config['class_num']}
|
||||
# In this case, this is NAS-Bench-201
|
||||
else:
|
||||
return {'name': 'infer.tiny', 'C': self.arch_config['channel'],
|
||||
'N' : self.arch_config['num_cells'],
|
||||
'arch_str': self.arch_config['arch_str'], 'num_classes': self.arch_config['class_num']}
|
||||
else:
|
||||
# In this case, this is NAS-Bench-301
|
||||
if 'name' in self.arch_config and self.arch_config['name'] == 'infer.shape.tiny':
|
||||
return {'name': 'infer.shape.tiny', 'channels': self.arch_config['channels'],
|
||||
'genotype': str2structure(self.arch_config['genotype']), 'num_classes': self.arch_config['class_num']}
|
||||
# In this case, this is NAS-Bench-201
|
||||
else:
|
||||
return {'name': 'infer.tiny', 'C': self.arch_config['channel'],
|
||||
'N' : self.arch_config['num_cells'],
|
||||
'genotype': str2structure(self.arch_config['arch_str']), 'num_classes': self.arch_config['class_num']}
|
||||
|
||||
def state_dict(self):
|
||||
_state_dict = {key: value for key, value in self.__dict__.items()}
|
||||
return _state_dict
|
||||
|
||||
def load_state_dict(self, state_dict):
|
||||
self.__dict__.update(state_dict)
|
||||
|
||||
@staticmethod
|
||||
def create_from_state_dict(state_dict):
|
||||
x = ResultsCount(None, None, None, None, None, None, None, None, None, None)
|
||||
x.load_state_dict(state_dict)
|
||||
return x
|
36
NAS-Bench-201/setup.py
Normal file
36
NAS-Bench-201/setup.py
Normal file
@ -0,0 +1,36 @@
|
||||
#####################################################
|
||||
# Copyright (c) Xuanyi Dong [GitHub D-X-Y], 2019.08 #
|
||||
#####################################################
|
||||
# [2020.02.25] Initialize the API as v1.1
|
||||
# [2020.03.09] Upgrade the API to v1.2
|
||||
# [2020.03.16] Upgrade the API to v1.3
|
||||
# [2020.06.30] Upgrade the API to v2.0
|
||||
# [2020.10.12] Upgrade the API to v2.1 -- deprecate this repo, switch to NATS-Bench.
|
||||
import os
|
||||
from setuptools import setup
|
||||
|
||||
|
||||
def read(fname='README.md'):
|
||||
with open(os.path.join(os.path.dirname(__file__), fname), encoding='utf-8') as cfile:
|
||||
return cfile.read()
|
||||
|
||||
|
||||
setup(
|
||||
name = "nas_bench_201",
|
||||
version = "2.1",
|
||||
author = "Xuanyi Dong",
|
||||
author_email = "dongxuanyi888@gmail.com",
|
||||
description = "API for NAS-Bench-201 (a benchmark for neural architecture search).",
|
||||
license = "MIT",
|
||||
keywords = "NAS Dataset API DeepLearning",
|
||||
url = "https://github.com/D-X-Y/NAS-Bench-201",
|
||||
packages=['nas_201_api'],
|
||||
long_description=read('README.md'),
|
||||
long_description_content_type='text/markdown',
|
||||
classifiers=[
|
||||
"Programming Language :: Python",
|
||||
"Topic :: Database",
|
||||
"Topic :: Scientific/Engineering :: Artificial Intelligence",
|
||||
"License :: OSI Approved :: MIT License",
|
||||
],
|
||||
)
|
Loading…
Reference in New Issue
Block a user