def initialize_parameters():
print('Initializing parameters...')
import os
# Obtain the path of the directory of this script
file_path = os.path.dirname(os.path.realpath(__file__))
# Import the CANDLE library
import sys
sys.path.append(candle_lib)
import candle_keras as candle
# Instantiate the candle.Benchmark class
mymodel_common = candle.Benchmark(file_path,
os.getenv("DEFAULT_PARAMS_FILE"),
'keras',
prog='myprog',
desc='My model')
# Get a dictionary of the model hyperparamters
hyperparams = candle.initialize_parameters(mymodel_common)
# Return the dictionary of the hyperparameters
return (hyperparams)
def initialize_parameters():
unet_common = unet.UNET(unet.file_path,
'unet_params.txt',
'keras',
prog='unet_example',
desc='UNET example')
# Initialize parameters
gParameters = candle.initialize_parameters(unet_common)
return gParameters
def initialize_parameters():
# Build benchmark object
unoBmk = benchmark.BenchmarkUno(benchmark.file_path, 'uno_default_model.txt', 'keras',
prog='uno_baseline', desc='Build neural network based models to predict tumor response to single and paired drugs.')
# Initialize parameters
gParameters = candle.initialize_parameters(unoBmk)
#benchmark.logger.info('Params: {}'.format(gParameters))
return gParameters
def initialize_parameters():
# Build benchmark object
nt3Bmk = bmk.BenchmarkNT3(bmk.file_path, 'nt3_default_model.txt', 'keras',
prog='nt3_baseline', desc='Multi-task (DNN) for data extraction from clinical reports - Pilot 3 Benchmark 1')
# Initialize parameters
gParameters = candle.initialize_parameters(nt3Bmk)
#benchmark.logger.info('Params: {}'.format(gParameters))
return gParameters
def initialize_parameters():
gae_common = gae(file_path,
'gae_params.txt',
'keras',
prog='gae_baseline_keras2',
desc='GAE Network'
)
# Initialize parameters
gParameters = candle.initialize_parameters(gae_common)
return gParameters
def initialize_parameters():
mnist_common = mnist.MNIST(mnist.file_path,
'mnist_params.txt',
'keras',
prog='mnist_cnn',
desc='MNIST CNN example')
# Initialize parameters
gParameters = candle.initialize_parameters(mnist_common)
csv_logger = CSVLogger('{}/params.log'.format(gParameters))
return gParameters
def initialize_parameters():
# Build benchmark object
mnist_common = mnist_uq.MNIST(mnist_uq.file_path,
'mnist_complex.txt',
'keras',
prog='mnist_mlp',
desc='MNIST example')
# Initialize parameters
gParameters = candle.initialize_parameters(mnist_common)
return gParameters
def initialize_parameters():
# Build benchmark object
p1b2Bmk = p1b2.BenchmarkP1B2(p1b2.file_path,
'p1b2_default_model.txt',
'keras',
prog='p1b2_baseline',
desc='Train Classifier - Pilot 1 Benchmark 2')
# Initialize parameters
gParameters = candle.initialize_parameters(p1b2Bmk)
#p1b2.logger.info('Params: {}'.format(gParameters))
return gParameters
def initialize_parameters():
mnist_common = mnist.MNIST(mnist.file_path,
os.getenv("DEFAULT_PARAMS_FILE"),
'keras',
prog='mnist_mlp',
desc='MNIST example')
import candle_keras as candle
# Initialize parameters
gParameters = candle.initialize_parameters(mnist_common)
csv_logger = CSVLogger('{}/params.log'.format(gParameters))
return gParameters
def initialize_parameters():
# Build benchmark object
comboBmk = combo.BenchmarkCombo(
combo.file_path,
'combo_default_model.txt',
'keras',
prog='combo_baseline',
desc=
'Build neural network based models to predict tumor response to drug pairs.'
)
# Initialize parameters
gParameters = candle.initialize_parameters(comboBmk)
#combo.logger.info('Params: {}'.format(gParameters))
return gParameters
def initialize_parameters():
# Build benchmark object
p1b1Bmk = p1b1.BenchmarkP1B1(
p1b1.file_path,
'p1b1_default_model.txt',
'keras',
prog='p1b1_baseline',
desc=
'Multi-task (DNN) for data extraction from clinical reports - Pilot 3 Benchmark 1'
)
# Initialize parameters
gParameters = candle.initialize_parameters(p1b1Bmk)
#p1b1.logger.info('Params: {}'.format(gParameters))
return gParameters
def initialize_parameters():
t29_common = candle_keras.Benchmark(file_path,
't29_default_model.txt',
'keras',
prog='t29res.py',
desc='resnet')
# Need a pointer to the docs showing what is provided
# by default
additional_definitions = [{
'name': 'connections',
'default': 1,
'type': int,
'help': 'The number of residual connections.'
}, {
'name':
'distance',
'default':
1,
'type':
int,
'help':
'Residual connection distance between dense layers.'
}, {
'name': 'model',
'default': 'model.json',
'type': str,
'help': 'Name of json model description file.'
}, {
'name': 'weights',
'default': 'model.h5',
'type': str,
'help': 'Name of h5 weights file.'
}, {
'name':
'n_pred',
'default':
1,
'type':
int,
'help':
'Number of predictions to do on each sample.'
}]
t29_common.additional_definitions = additional_definitions
gParameters = candle_keras.initialize_parameters(t29_common)
return gParameters
def initialize_parameters():
# Build benchmark object
#mymodel_common = candle.Benchmark(file_path,os.getenv("DEFAULT_PARAMS_FILE"),'keras',prog='myprog',desc='My model')
unoBmk = benchmark.BenchmarkUno(
benchmark.file_path,
os.getenv("DEFAULT_PARAMS_FILE"),
'keras',
prog='uno_baseline',
desc=
'Build neural network based models to predict tumor response to single and paired drugs.'
)
# Initialize parameters
hyperparams = candle.initialize_parameters(unoBmk)
#benchmark.logger.info('Params: {}'.format(hyperparams))
return hyperparams
def initialize_parameters():
t29_common = candle_keras.Benchmark(file_path, 't29_default_model.txt','keras',
prog='t29res.py',desc='resnet')
# Need a pointer to the docs showing what is provided
# by default
additional_definitions = [
{'name':'connections',
'default':1,
'type':int,
'help':'The number of residual connections.'},
{'name':'distance',
'default':1,
'type':int,
'help':'Residual connection distance between dense layers.'}
]
t29_common.additional_definitions = additional_definitions
gParameters = candle_keras.initialize_parameters(t29_common)
return gParameters
def initialize_parameters():
t29_common = candle_keras.Benchmark(file_path, 't29_default_model.txt','keras',
prog='/t29res.py',desc='resnet')
#A list common parsed parameters are available here: https://ecp-candle.github.io/Candle/html/_modules/default_utils.html#get_common_parser
additional_definitions = [
{'name':'connections',
'default':1,
'type':int,
'help':'The number of residual connections.'},
{'name':'distance',
'default':1,
'type':int,
'help':'Residual connection distance between dense layers.'}
]
t29_common.additional_definitions = additional_definitions
gParameters = candle_keras.initialize_parameters(t29_common)
return gParameters
def initialize_parameters():
# Add the candle_keras library to the Python path
import sys, os
sys.path.append(os.getenv("CANDLE") + '/Candle/common')
# Instantiate the Benchmark class (the values of the prog and desc parameters don't really matter)
import candle_keras as candle
mymodel_common = candle.Benchmark(os.path.dirname(
os.path.realpath(__file__)),
os.getenv("DEFAULT_PARAMS_FILE"),
'keras',
prog='myprogram',
desc='My CANDLE example')
# Read the parameters (in a dictionary format) pointed to by the environment variable DEFAULT_PARAMS_FILE
gParameters = candle.initialize_parameters(mymodel_common)
# Return this dictionary of parameters
return (gParameters)
def initialize_parameters():
# Build benchmark object
p2b1Bmk = p2b1.BenchmarkP2B1(
p2b1.file_path,
'p2b1_default_model.txt',
'keras',
prog='p2b1_baseline',
desc='Train Molecular Frame Autoencoder - Pilot 2 Benchmark 1')
# Initialize parameters
GP = candle.initialize_parameters(p2b1Bmk)
#p2b1.logger.info('Params: {}'.format(gParameters))
print('\nTraining parameters:')
for key in sorted(GP):
print("\t%s: %s" % (key, GP[key]))
# print json.dumps(GP, indent=4, skipkeys=True, sort_keys=True)
if GP['backend'] != 'theano' and GP['backend'] != 'tensorflow':
sys.exit('Invalid backend selected: %s' % GP['backend'])
os.environ['KERAS_BACKEND'] = GP['backend']
reload(K)
'''
if GP['backend'] == 'theano':
K.set_image_dim_ordering('th')
elif GP['backend'] == 'tensorflow':
K.set_image_dim_ordering('tf')
'''
K.set_image_data_format('channels_last')
#"th" format means that the convolutional kernels will have the shape (depth, input_depth, rows, cols)
#"tf" format means that the convolutional kernels will have the shape (rows, cols, input_depth, depth)
print("Image data format: ", K.image_data_format())
# print "Image ordering: ", K.image_dim_ordering()
return GP
