from search_algorithms import AgingEvoSearch
def lr_schedule(epoch):
if 0 <= epoch < 90:
return 0.01
if 90 <= epoch < 105:
return 0.005
return 0.001
search_algorithm = AgingEvoSearch
training_config = TrainingConfig(
dataset=CIFAR10(),
optimizer=lambda: tfa.optimizers.SGDW(
learning_rate=0.01, momentum=0.9, weight_decay=1e-5),
batch_size=128,
epochs=130,
callbacks=lambda: [LearningRateScheduler(lr_schedule)],
)
search_config = AgingEvoConfig(search_space=CnnSearchSpace(dropout=0.15),
rounds=6000,
checkpoint_dir="artifacts/cnn_cifar10")
bound_config = BoundConfig(error_bound=0.18,
peak_mem_bound=75000,
model_size_bound=75000,
mac_bound=30000000)
from search_algorithms import AgingEvoSearch
search_algorithm = AgingEvoSearch
def lr_schedule(epoch):
if 0 <= epoch < 35:
return 0.01
return 0.005
training_config = TrainingConfig(
dataset=Chars74K("/datasets/chars74k", img_size=(48, 48)),
epochs=60,
batch_size=80,
optimizer=lambda: tfa.optimizers.SGDW(learning_rate=0.01, momentum=0.9, weight_decay=0.0001),
callbacks=lambda: [LearningRateScheduler(lr_schedule)]
)
search_config = AgingEvoConfig(
search_space=CnnSearchSpace(dropout=0.15),
checkpoint_dir="artifacts/cnn_chars74k"
)
bound_config = BoundConfig(
error_bound=0.3,
peak_mem_bound=10000,
model_size_bound=20000,
mac_bound=1000000
)
def lr_schedule(epoch):
if 0 <= epoch < 20:
return 0.0005
if 20 <= epoch < 40:
return 0.0001
return 0.00002
training_config = TrainingConfig(
dataset=SpeechCommands("/datasets/speech_commands_v0.02"),
epochs=45,
batch_size=50,
optimizer=lambda: AdamW(lr=0.0005, weight_decay=1e-5),
callbacks=lambda: [
LearningRateScheduler(lr_schedule)
]
)
search_config = AgingEvoConfig(
search_space=CnnSearchSpace(),
rounds=2000,
checkpoint_dir="artifacts/cnn_speech_commands"
)
bound_config = BoundConfig(
error_bound=0.085,
peak_mem_bound=60000,
model_size_bound=40000,
mac_bound=20000000,
)
import tensorflow_addons as tfa
from cnn import CnnSearchSpace
from config import AgingEvoConfig, TrainingConfig, BoundConfig
from dataset import MNIST
from search_algorithms import AgingEvoSearch
search_algorithm = AgingEvoSearch
training_config = TrainingConfig(
dataset=MNIST(),
epochs=30,
batch_size=128,
optimizer=lambda: tfa.optimizers.SGDW(learning_rate=0.005, momentum=0.9, weight_decay=4e-5),
callbacks=lambda: [],
)
search_config = AgingEvoConfig(
search_space=CnnSearchSpace(),
checkpoint_dir="artifacts/cnn_mnist"
)
bound_config = BoundConfig(
error_bound=0.035,
peak_mem_bound=2500,
model_size_bound=4500,
mac_bound=30000000
)