mirror of
https://github.com/jung-geun/PSO.git
synced 2026-09-20 14:11:48 +09:00
feat: modernize PSO and add convergence research
Migrate the package and examples to the tensor-native PyTorch implementation, add benchmark evidence, and add the guarded post-training convergence protocol with TensorBoard progress monitoring and hash-verified recovery. Constraint: Preserve one-shot official-test sealing and auditable research artifacts Rejected: Commit local .omc runs and downloaded datasets | multi-gigabyte runtime state is machine-local Confidence: high Scope-risk: broad Not-tested: Production CUDA run on pieroot-server
This commit is contained in:
+94
-71
@@ -1,88 +1,111 @@
|
||||
# %%
|
||||
import os
|
||||
import sys
|
||||
import argparse
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
|
||||
from pso import optimizer
|
||||
|
||||
import tensorflow as tf
|
||||
from keras.datasets import mnist
|
||||
from keras.layers import Conv2D, Dense, Dropout, Flatten, MaxPooling2D
|
||||
from keras.models import Sequential
|
||||
from pso import Optimizer
|
||||
from cli import add_pso_args, build_optimizer_kwargs
|
||||
|
||||
|
||||
os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2"
|
||||
def get_data(seed: int = 42):
|
||||
from sklearn.decomposition import PCA
|
||||
from torchvision.datasets import MNIST
|
||||
|
||||
train_dataset = MNIST(root="./data", train=True, download=True)
|
||||
test_dataset = MNIST(root="./data", train=False, download=True)
|
||||
|
||||
def get_data():
|
||||
(x_train, y_train), (x_test, y_test) = mnist.load_data()
|
||||
x_train_raw = (train_dataset.data[:3000].float() / 255.0).reshape(3000, -1).numpy()
|
||||
y_train = train_dataset.targets[:3000].long()
|
||||
|
||||
x_train, x_test = x_train / 255.0, x_test / 255.0
|
||||
x_train = x_train.reshape((60000, 28, 28, 1))
|
||||
x_test = x_test.reshape((10000, 28, 28, 1))
|
||||
x_test_raw = (test_dataset.data[:1000].float() / 255.0).reshape(1000, -1).numpy()
|
||||
y_test = test_dataset.targets[:1000].long()
|
||||
|
||||
y_train, y_test = tf.one_hot(y_train, 10), tf.one_hot(y_test, 10)
|
||||
pca = PCA(n_components=32, whiten=True, random_state=seed)
|
||||
x_train_pca = pca.fit_transform(x_train_raw)
|
||||
x_test_pca = pca.transform(x_test_raw)
|
||||
|
||||
x_train, x_test = tf.convert_to_tensor(x_train), tf.convert_to_tensor(x_test)
|
||||
y_train, y_test = tf.convert_to_tensor(y_train), tf.convert_to_tensor(y_test)
|
||||
x_train = torch.tensor(x_train_pca, dtype=torch.float32)
|
||||
x_test = torch.tensor(x_test_pca, dtype=torch.float32)
|
||||
|
||||
print(f"x_train : {x_train[0].shape} | y_train : {y_train[0].shape}")
|
||||
print(f"x_test : {x_test[0].shape} | y_test : {y_test[0].shape}")
|
||||
print(f"x_train : {x_train.shape} | y_train : {y_train.shape}")
|
||||
print(f"x_test : {x_test.shape} | y_test : {y_test.shape}")
|
||||
|
||||
return x_train, y_train, x_test, y_test
|
||||
|
||||
|
||||
def make_model():
|
||||
model = Sequential()
|
||||
model.add(
|
||||
Conv2D(32, kernel_size=(5, 5), activation="relu", input_shape=(28, 28, 1))
|
||||
def make_model(seed: int = 42):
|
||||
torch.manual_seed(seed)
|
||||
return nn.Linear(32, 10)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="PSO MNIST Benchmark Script")
|
||||
add_pso_args(
|
||||
parser,
|
||||
defaults={
|
||||
"method": "inertia",
|
||||
"initialization": "model_noise",
|
||||
"evaluation": "fixed_subset",
|
||||
"convergence": "none",
|
||||
"refinement": "adam",
|
||||
"n_particles": 30,
|
||||
"c0": None,
|
||||
"c1": None,
|
||||
"w_min": None,
|
||||
"w_max": None,
|
||||
"negative_swarm": 0.0,
|
||||
"mutation_swarm": 0.02,
|
||||
"particle_min": -3.0,
|
||||
"particle_max": 3.0,
|
||||
"velocity_limit_ratio": 0.025,
|
||||
"boundary_strategy": "reflect",
|
||||
"initial_position_noise": 0.05,
|
||||
"seed": 42,
|
||||
"epochs": 80,
|
||||
"batch_size": 1000,
|
||||
"fitness_size": 2000,
|
||||
"renewal": "loss",
|
||||
"output_dir": "output/mnist",
|
||||
"checkpoint_interval": 25,
|
||||
"refinement_epochs": 100,
|
||||
"refinement_lr": 0.01,
|
||||
},
|
||||
)
|
||||
model.add(MaxPooling2D(pool_size=(2, 2)))
|
||||
model.add(Dropout(0.5))
|
||||
model.add(Conv2D(64, kernel_size=(3, 3), activation="relu"))
|
||||
model.add(MaxPooling2D(pool_size=(2, 2)))
|
||||
model.add(Flatten())
|
||||
model.add(Dropout(0.5))
|
||||
model.add(Dense(256, activation="relu"))
|
||||
model.add(Dense(128, activation="relu"))
|
||||
model.add(Dense(10, activation="softmax"))
|
||||
args = parser.parse_args()
|
||||
|
||||
return model
|
||||
model = make_model(seed=args.seed)
|
||||
x_train, y_train, x_test, y_test = get_data(seed=args.seed)
|
||||
|
||||
fitness_size = args.fitness_size if args.evaluation == "fixed_subset" else None
|
||||
refinement_epochs = args.refinement_epochs if args.refinement == "adam" else 0
|
||||
|
||||
kwargs = build_optimizer_kwargs(
|
||||
args,
|
||||
model=model,
|
||||
loss=nn.CrossEntropyLoss(),
|
||||
task="multiclass",
|
||||
inertia_profile={"c0": 1.49618, "c1": 1.49618, "w_min": 0.7298, "w_max": 0.7298},
|
||||
)
|
||||
pso_mnist = Optimizer(**kwargs)
|
||||
|
||||
print(f"Optimizer device: {pso_mnist.device}")
|
||||
|
||||
best_score = pso_mnist.fit(
|
||||
x_train,
|
||||
y_train,
|
||||
epochs=args.epochs,
|
||||
batch_size=args.batch_size,
|
||||
fitness_size=fitness_size,
|
||||
renewal=args.renewal,
|
||||
validation_data=(x_test, y_test),
|
||||
output_dir=args.output_dir,
|
||||
checkpoint_interval=25,
|
||||
save_info=True,
|
||||
refinement_epochs=refinement_epochs,
|
||||
refinement_lr=args.refinement_lr,
|
||||
)
|
||||
|
||||
print(f"Done! Best score: {best_score}")
|
||||
|
||||
|
||||
# %%
|
||||
model = make_model()
|
||||
x_train, y_train, x_test, y_test = get_data()
|
||||
|
||||
|
||||
pso_mnist = optimizer(
|
||||
model,
|
||||
loss="categorical_crossentropy",
|
||||
n_particles=200,
|
||||
c0=0.7,
|
||||
c1=0.4,
|
||||
w_min=0.1,
|
||||
w_max=0.9,
|
||||
negative_swarm=0.0,
|
||||
mutation_swarm=0.05,
|
||||
convergence_reset=True,
|
||||
convergence_reset_patience=10,
|
||||
convergence_reset_monitor="loss",
|
||||
convergence_reset_min_delta=0.005,
|
||||
)
|
||||
|
||||
best_score = pso_mnist.fit(
|
||||
x_train,
|
||||
y_train,
|
||||
epochs=1000,
|
||||
save_info=True,
|
||||
log=2,
|
||||
log_name="mnist",
|
||||
renewal="loss",
|
||||
check_point=25,
|
||||
batch_size=5000,
|
||||
validate_data=(x_test, y_test),
|
||||
)
|
||||
|
||||
print("Done!")
|
||||
|
||||
sys.exit(0)
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
|
||||
Reference in New Issue
Block a user