mirror of
https://github.com/jung-geun/PSO.git
synced 2025-12-19 20:44:39 +09:00
23-07-08
mnist 4, 8, 4-1.1 시도
This commit is contained in:
jung-geun
2
mnist.py
2
mnist.py
@@ -73,7 +73,7 @@ if __name__ == "__main__":
|
||||
n_particles=100,
|
||||
c0=0.35,
|
||||
c1=0.8,
|
||||
w_min=0.7,
|
||||
w_min=0.4,
|
||||
w_max=1.1,
|
||||
negative_swarm=0.2,
|
||||
mutation_swarm=0.1,
|
||||
|
||||
@@ -1,14 +0,0 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""PSOkeras - Particle Swarm Optimizer for Keras models
|
||||
|
||||
This module implements a particle swarm optimizer for training the weights of Keras models. The
|
||||
|
||||
"""
|
||||
|
||||
|
||||
from .version import __version__
|
||||
from .optimizer import Optimizer
|
||||
|
||||
__all__ = [
|
||||
'Optimizer',
|
||||
]
|
||||
@@ -1,67 +0,0 @@
|
||||
BIG_SCORE = 1.e6 # type: float
|
||||
|
||||
import keras
|
||||
from psokeras.particle import Particle
|
||||
from .util import ProgressBar
|
||||
|
||||
|
||||
class Optimizer:
|
||||
def __init__(self, model, loss,
|
||||
n=10,
|
||||
acceleration=0.1,
|
||||
local_rate=1.0,
|
||||
global_rate=1.0):
|
||||
|
||||
self.n_particles = n
|
||||
self.structure = model.to_json()
|
||||
self.particles = [None] * n
|
||||
self.loss = loss
|
||||
self.length = len(model.get_weights())
|
||||
|
||||
params = {'acc': acceleration, 'local_acc': local_rate, 'global_acc': global_rate}
|
||||
|
||||
for i in range(n-1):
|
||||
m = keras.models.model_from_json(self.structure)
|
||||
m.compile(loss=loss,optimizer='sgd')
|
||||
self.particles[i] = Particle(m, params)
|
||||
|
||||
self.particles[n-1] = Particle(model, params)
|
||||
|
||||
self.global_best_weights = None
|
||||
self.global_best_score = BIG_SCORE
|
||||
|
||||
def fit(self, x, y, steps=0, batch_size=32):
|
||||
num_batches = x.shape[0] // batch_size
|
||||
|
||||
for i, p in enumerate(self.particles):
|
||||
local_score = p.get_score(x, y)
|
||||
|
||||
if local_score < self.global_best_score:
|
||||
self.global_best_score = local_score
|
||||
self.global_best_weights = p.get_best_weights()
|
||||
|
||||
print("PSO -- Initial best score {:0.4f}".format(self.global_best_score))
|
||||
|
||||
bar = ProgressBar(steps, updates=20)
|
||||
|
||||
for i in range(steps):
|
||||
for j in range(num_batches):
|
||||
x_ = x[j*batch_size:(j+1)*batch_size,:]
|
||||
y_ = y[j*batch_size:(j+1)*batch_size]
|
||||
|
||||
for p in self.particles:
|
||||
local_score = p.step(x_, y_, self.global_best_weights)
|
||||
|
||||
if local_score < self.global_best_score:
|
||||
self.global_best_score = local_score
|
||||
self.global_best_weights = p.get_best_weights()
|
||||
|
||||
bar.update(i)
|
||||
|
||||
bar.done()
|
||||
|
||||
def get_best_model(self):
|
||||
best_model = keras.models.model_from_json(self.structure)
|
||||
best_model.set_weights(self.global_best_weights)
|
||||
best_model.compile(loss=self.loss,optimizer='sgd')
|
||||
return best_model
|
||||
@@ -1,66 +0,0 @@
|
||||
import random
|
||||
|
||||
import numpy as np
|
||||
|
||||
from psokeras.optimizer import BIG_SCORE
|
||||
|
||||
|
||||
class Particle:
|
||||
def __init__(self, model, params):
|
||||
self.model = model
|
||||
self.params = params
|
||||
self.init_weights = model.get_weights()
|
||||
self.velocities = [None] * len(self.init_weights)
|
||||
self.length = len(self.init_weights)
|
||||
for i, layer in enumerate(self.init_weights):
|
||||
self.velocities[i] = np.random.rand(*layer.shape) / 5 - 0.10
|
||||
# self.velocities[i] = np.zeros(layer.shape)
|
||||
|
||||
self.best_weights = None
|
||||
self.best_score = BIG_SCORE
|
||||
|
||||
def get_score(self, x, y, update=True):
|
||||
local_score = self.model.evaluate(x, y, verbose=0)
|
||||
if local_score < self.best_score and update:
|
||||
self.best_score = local_score
|
||||
self.best_weights = self.model.get_weights()
|
||||
|
||||
return local_score
|
||||
|
||||
def _update_velocities(self, global_best_weights, depth):
|
||||
new_velocities = [None] * len(self.init_weights)
|
||||
weights = self.model.get_weights()
|
||||
local_rand, global_rand = random.random(), random.random()
|
||||
|
||||
for i, layer in enumerate(weights):
|
||||
if i >= depth:
|
||||
new_velocities[i] = self.velocities[i]
|
||||
continue
|
||||
new_v = self.params['acc'] * self.velocities[i]
|
||||
new_v = new_v + self.params['local_acc'] * local_rand * (self.best_weights[i] - layer)
|
||||
new_v = new_v + self.params['global_acc'] * global_rand * (global_best_weights[i] - layer)
|
||||
new_velocities[i] = new_v
|
||||
|
||||
self.velocities = new_velocities
|
||||
|
||||
def _update_weights(self, depth):
|
||||
old_weights = self.model.get_weights()
|
||||
new_weights = [None] * len(old_weights)
|
||||
for i, layer in enumerate(old_weights):
|
||||
if i>= depth:
|
||||
new_weights[i] = layer
|
||||
continue
|
||||
new_w = layer + self.velocities[i]
|
||||
new_weights[i] = new_w
|
||||
|
||||
self.model.set_weights(new_weights)
|
||||
|
||||
def step(self, x, y, global_best_weights,depth=None):
|
||||
if depth is None:
|
||||
depth = self.length
|
||||
self._update_velocities(global_best_weights, depth)
|
||||
self._update_weights(depth)
|
||||
return self.get_score(x, y)
|
||||
|
||||
def get_best_weights(self):
|
||||
return self.best_weights
|
||||
@@ -1,31 +0,0 @@
|
||||
class ProgressBar:
|
||||
def __init__(self, steps, updates=10):
|
||||
self.step = 0
|
||||
self.step_size = (steps // updates)
|
||||
self.total_steps = steps
|
||||
self.updates = updates
|
||||
|
||||
bar = self._make_bar(0)
|
||||
print(bar, end=' ')
|
||||
|
||||
def update(self, i):
|
||||
if i % self.step_size > 0:
|
||||
return
|
||||
|
||||
self.step = i // self.step_size
|
||||
bar = self._make_bar(i)
|
||||
|
||||
print(bar, end=' ')
|
||||
|
||||
def done(self):
|
||||
self.step = self.total_steps
|
||||
bar = self._make_bar(self.updates)
|
||||
print(bar)
|
||||
|
||||
def _make_bar(self, x):
|
||||
bar = "["
|
||||
for x in range(self.updates):
|
||||
print("\r", end=' ')
|
||||
bar += "=" if x < self.step else " "
|
||||
bar += "]"
|
||||
return bar
|
||||
@@ -1 +0,0 @@
|
||||
__version__ = '0.2.0'
|
||||
File diff suppressed because one or more lines are too long
BIN
pyswarms/pso.gif
BIN
pyswarms/pso.gif
Binary file not shown.
|
Before Width: | Height: | Size: 4.1 KiB |
@@ -1,93 +0,0 @@
|
||||
from sklearn.datasets import load_iris
|
||||
from sklearn.model_selection import train_test_split
|
||||
from sklearn.preprocessing import OneHotEncoder, StandardScaler
|
||||
|
||||
import tensorflow as tf
|
||||
from tensorflow import keras
|
||||
from tensorflow.keras.models import Sequential
|
||||
from tensorflow.keras.layers import Dense, Dropout, Flatten
|
||||
|
||||
import time as time
|
||||
import numpy as np
|
||||
|
||||
|
||||
iris = load_iris()
|
||||
iris = load_iris()
|
||||
X = iris['data']
|
||||
y = iris['target']
|
||||
names = iris['target_names']
|
||||
feature_names = iris['feature_names']
|
||||
enc = OneHotEncoder()
|
||||
Y = enc.fit_transform(y[:, np.newaxis]).toarray()
|
||||
scaler = StandardScaler()
|
||||
X_scaled = scaler.fit_transform(X)
|
||||
X_train, X_test, Y_train, Y_test = train_test_split(
|
||||
X_scaled, Y, test_size=0.5, random_state=2)
|
||||
n_features = X.shape[1]
|
||||
n_classes = Y.shape[1]
|
||||
|
||||
def create_custom_model(input_dim, output_dim, nodes, n=1, name='model'):
|
||||
model = Sequential(name=name)
|
||||
for i in range(n):
|
||||
model.add(Dense(nodes, input_dim=input_dim, activation='relu'))
|
||||
model.add(Dense(output_dim, activation='softmax'))
|
||||
model.compile(loss='categorical_crossentropy',
|
||||
optimizer='adam',
|
||||
metrics=['accuracy'])
|
||||
return model
|
||||
|
||||
|
||||
# n_layers = 1
|
||||
# model = create_custom_model(n_features, n_classes,
|
||||
# 4, n_layers)
|
||||
# model.summary()
|
||||
|
||||
# start_time = time.time()
|
||||
# print('Model name:', model.name)
|
||||
# history_callback = model.fit(X_train, Y_train,
|
||||
# batch_size=5,
|
||||
# epochs=400,
|
||||
# verbose=0,
|
||||
# validation_data=(X_test, Y_test)
|
||||
# )
|
||||
# score = model.evaluate(X_test, Y_test)
|
||||
# print('Test loss:', score[0])
|
||||
# print('Test accuracy:', score[1])
|
||||
# print("--- %s seconds ---" % (time.time() - start_time))
|
||||
|
||||
|
||||
def get_shape(model):
|
||||
weights_layer = model.get_weights()
|
||||
shapes = []
|
||||
for weights in weights_layer:
|
||||
shapes.append(weights.shape)
|
||||
return shapes
|
||||
|
||||
def set_shape(weights,shapes):
|
||||
new_weights = []
|
||||
index=0
|
||||
for shape in shapes:
|
||||
if(len(shape)>1):
|
||||
n_nodes = np.prod(shape)+index
|
||||
else:
|
||||
n_nodes=shape[0]+index
|
||||
tmp = np.array(weights[index:n_nodes]).reshape(shape)
|
||||
new_weights.append(tmp)
|
||||
index=n_nodes
|
||||
return new_weights
|
||||
|
||||
def evaluate_nn(W, shape,X_train=X_train, Y_train=Y_train):
|
||||
results = []
|
||||
for weights in W:
|
||||
model.set_weights(set_shape(weights,shape))
|
||||
score = model.evaluate(X_train, Y_train, verbose=0)
|
||||
results.append(1-score[1])
|
||||
return results
|
||||
|
||||
shape = get_shape(model)
|
||||
x_max = 1.0 * np.ones(83)
|
||||
x_min = -1.0 * x_max
|
||||
bounds = (x_min, x_max)
|
||||
options = {'c1': 0.4, 'c2': 0.8, 'w': 0.4}
|
||||
optimizer = GlobalBestPSO(n_particles=25, dimensions=83,
|
||||
options=options, bounds=bounds)
|
||||
@@ -1,11 +0,0 @@
|
||||
2023-05-28 17:29:35,386 - pyswarms.single.global_best - INFO - Optimize for 20 iters with {'c1': 0.4, 'c2': 0.6, 'w': 0.4}
|
||||
2023-05-28 17:30:07,637 - pyswarms.single.global_best - INFO - Optimization finished | best cost: 0.013333320617675781, best pos: [ 0.17027965 0.17696722 -0.07395054 0.31544984 0.17052408 -0.37810479
|
||||
0.24267479 0.16931148 0.65606942 -0.24207116 -0.66562722 0.02191478
|
||||
0.5870387 0.78966943 -0.4457816 0.0907434 -0.1808341 0.29282655
|
||||
0.61472003 0.90660508 0.16469465 -0.55057763 0.54702005 -0.22636745
|
||||
0.01125538 0.62431828 0.02128613 -0.26723577 -0.43527016 0.51223244
|
||||
0.76388399 -0.02073011 0.15949622 0.45878514 0.01787211]
|
||||
2023-05-28 17:30:08,140 - matplotlib.animation - WARNING - MovieWriter pillowwritter unavailable; using Pillow instead.
|
||||
2023-05-28 17:30:08,141 - matplotlib.animation - INFO - Animation.save using <class 'matplotlib.animation.PillowWriter'>
|
||||
2023-05-28 17:31:01,885 - tensorflow - WARNING - 5 out of the last 3010 calls to <function Model.make_test_function.<locals>.test_function at 0x7fee6622df70> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.
|
||||
2023-05-28 17:31:08,794 - tensorflow - WARNING - 6 out of the last 3011 calls to <function Model.make_test_function.<locals>.test_function at 0x7fee66257b80> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.
|
||||
@@ -46,10 +46,6 @@ $$
|
||||
| |-- __init__.py # pso 모듈을 사용하기 위한 초기화 파일
|
||||
| |-- optimizer.py # pso 알고리즘 이용을 위한 기본 코드
|
||||
| |-- particle.py # 각 파티클의 정보 및 위치를 저장하는 코드
|
||||
|-- /psokeras # keras 모델을 이용가능한 PSO 알고리즘 - 다른 사람의 코드
|
||||
| |-- ***
|
||||
|-- /pyswarms # pyswarms 라이브러리를 이용가능한 PSO 알고리즘 - 다른 사람의 코드
|
||||
| |-- ***
|
||||
|-- examples.py # psokeras 코드를 이용한 예제
|
||||
|-- xor.ipynb # pso 를 이용한 xor 문제 풀이
|
||||
|-- iris.py # pso 를 이용한 iris 문제 풀이
|
||||
|
||||
Reference in New Issue
Block a user