from deeplab import train, eval, vis, export_model
from sacred import Experiment
from labwatch.assistant import LabAssistant
from labwatch.optimizers import RandomSearch
import os
ex = Experiment()
a = LabAssistant(experiment=ex,
database_name="labwatch",
optimizer=RandomSearch)
@ex.config
def config():
num_iterations = 100
train_batch_size = 4
model_variants = "xception_65"
atrous_rates_0 = 6
atrous_rates_1 = 12
atrous_rates_2 = 18
output_stride = 16
decoder_output_stride = 4
crop_size = "42, 42"
fine_tune_batch_norm = True
exp_id = 0
OM_DIR = "/om/user/amineh/exp/exp_id"
INIT_DIR = "${OM_DIR}/deeplabv3_pascal_trainval/model.ckpt"
TRAIN_LOGDIR = "${OM_DIR}/train"
VIS_LOGDIR = "${OM_DIR}/vis"
import sacred
from sacred.stflow import LogFileWriter
from labwatch.assistant import LabAssistant
from labwatch.optimizers import RandomSearch
from labwatch.hyperparameters import UniformFloat, UniformNumber
from tensorflow.examples.tutorials.mnist import input_data
from hyperparam_opt.tensorflow.dnn_mnist import HyperParams, train
ex = sacred.Experiment(name='MINST')
a = LabAssistant(ex,
database_name='labwatch-db',
optimizer=RandomSearch)
@ex.config
def cfg():
lr = 0.001
batch_size = 100
n_hidden = 32
keep_prob = 0.5
data_dir = '../../data/tmp/mnist/'
log_dir = './logs/'
@a.search_space
def search_space():
lr = UniformFloat(0.0001, 0.01, default=0.001, log_scale=True)
batch_size = UniformNumber(8, 256, default=100, type=int)
from keras.models import Sequential, Model
from keras.layers import Dropout, Flatten, Dense, GlobalAveragePooling2D
from keras import backend as K
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, TensorBoard, EarlyStopping, TensorBoard
import os, os.path
import sys
from sacred import Experiment
from sacred.observers import MongoObserver
from labwatch.assistant import LabAssistant
from labwatch.optimizers.random_search import RandomSearch
from labwatch.hyperparameters import UniformNumber, UniformFloat
ex = Experiment()
a = LabAssistant(ex, optimizer=RandomSearch)
@a.search_space
def search_space():
num_units_first_dense = UniformNumber(lower=950,
upper=1450,
default=1024,
type=int,
log_scale=True)
num_units_second_dense = UniformNumber(lower=900,
upper=1600,
default=1024,
type=int,
log_scale=True)
dropout_rate = UniformFloat(lower=.33, upper=.55, default=.45)
#!/usr/bin/env python
# coding=utf-8
from __future__ import division, print_function, unicode_literals
from sacred import Experiment
from labwatch.assistant import LabAssistant
from labwatch.hyperparameters import UniformFloat
import numpy as np
ex = Experiment()
a = LabAssistant(ex)
@ex.config
def cfg():
x = (0., 5.)
@a.search_space
def search_space():
x = (UniformFloat(-5, 10), UniformFloat(0, 15))
@ex.automain
def branin(x):
x1, x2 = x
print("{:.2f}, {:.2f}".format(x1, x2))
y = (x2 - (5.1 / (4 * np.pi ** 2)) * x1 ** 2 + 5 * x1 / np.pi - 6) ** 2
y += 10 * (1 - 1 / (8 * np.pi)) * np.cos(x1) + 10
#!/usr/bin/env python
# coding=utf-8
from __future__ import division, print_function, unicode_literals
from labwatch.optimizers.random_search import RandomSearch
from sacred import Experiment
from labwatch.assistant import LabAssistant
from labwatch.hyperparameters import UniformFloat
import numpy as np
ex = Experiment()
a = LabAssistant(ex, database_name='branin', optimizer=RandomSearch)
@ex.config
def cfg():
x = (0., 5.)
@a.search_space
def search_space():
x = (UniformFloat(-5, 10), UniformFloat(0, 15))
@ex.automain
def branin(x):
x1, x2 = x
print("{:.2f}, {:.2f}".format(x1, x2))
y = (x2 - (5.1 / (4 * np.pi**2)) * x1**2 + 5 * x1 / np.pi - 6)**2
y += 10 * (1 - 1 / (8 * np.pi)) * np.cos(x1) + 10
from __future__ import print_function
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import RMSprop
from sacred import Experiment
from labwatch.assistant import LabAssistant
from labwatch.hyperparameters import UniformInt, UniformFloat
from labwatch.optimizers.random_search import RandomSearch
ex = Experiment()
a = LabAssistant(ex, "labwatch_demo_keras", optimizer=RandomSearch)
@ex.config
def cfg():
batch_size = 128
num_units_first_layer = 512
num_units_second_layer = 512
dropout_first_layer = 0.2
dropout_second_layer = 0.2
learning_rate = 0.001
@a.search_space
def small_search_space():
batch_size = UniformInt(lower=32, upper=64, default=32, log_scale=True)
learning_rate = UniformFloat(lower=10e-3,