def test_create_structure():
from random import random, seed
from deephyper.search.nas.model.space.structure import KerasStructure
from deephyper.search.nas.model.baseline.anl_mlp_2 import create_structure
from deephyper.core.model_utils import number_parameters
seed(10)
structure = create_structure([(10, 1), (10, 1)], (1, ), 5)
assert type(structure) is KerasStructure
ops = [random() for i in range(structure.num_nodes)]
structure.set_ops(ops)
structure.draw_graphviz('graph_anl_mlp_2_test.dot')
model = structure.create_model()
import numpy as np
x = np.zeros((1, 10, 1))
y = model.predict([x, x])
print(f'shape(x): {np.shape(x)}')
print(f'shape(y): {np.shape(y)}')
nparameters = number_parameters()
print('number of parameters: ', nparameters)
assert np.shape(y) == (
1, 1), f'Wrong output shape {np.shape(y)} should be {(1, 1)}'
def test_create_structure():
from random import random, seed
from deephyper.search.nas.model.space.structure import KerasStructure
from deephyper.core.model_utils import number_parameters
from tensorflow.keras.utils import plot_model
import tensorflow as tf
# seed(10)
shapes = [(942, ), (3820, ), (3820, )]
structure = create_structure(shapes, (1, ))
assert type(structure) is KerasStructure
ops = [random() for i in range(structure.num_nodes)]
# ops = [
# 0.07692307692307693,
# 0.5384615384615384,
# 0.07692307692307693,
# 0.07692307692307693,
# 0.07692307692307693,
# 0.5384615384615384,
# 0.5384615384615384,
# 0.07692307692307693,
# 0.5384615384615384,
# 0.0
# ]
print('num ops: ', len(ops))
print('size: ', structure.size)
structure.set_ops(ops)
structure.draw_graphviz('graph_candle_mlp_5.dot')
model = structure.create_model()
print('depth: ', structure.depth)
model = structure.create_model()
plot_model(model, to_file='graph_candle_mlp_5.png', show_shapes=True)
import numpy as np
x0 = np.zeros((1, *shapes[0]))
x1 = np.zeros((1, *shapes[1]))
x2 = np.zeros((1, *shapes[2]))
inpts = [x0, x1, x2]
y = model.predict(inpts)
for x in inpts:
print(f'shape(x): {np.shape(x)}')
print(f'shape(y): {np.shape(y)}')
total_parameters = number_parameters()
print('total_parameters: ', total_parameters)
model.summary()
def main(config):
num_epochs = NUM_EPOCHS
load_data = config['load_data']['func']
print('[PARAM] Loading data')
# Loading data
kwargs = config['load_data'].get('kwargs')
sig_load_data = signature(load_data)
if len(sig_load_data.parameters) == 0:
data = load_data()
else:
if 'prop' in sig_load_data.parameters:
if kwargs is None:
data = load_data(prop=PROP)
else:
kwargs['prop'] = PROP
data = load_data(**kwargs)
else:
if kwargs is None:
data = load_data()
else:
data = load_data(**kwargs)
print('[PARAM] Data loaded')
# Set data shape
if type(data) is tuple:
if len(data) != 2:
raise RuntimeError(
f'Loaded data are tuple, should ((training_input, training_output), (validation_input, validation_output)) but length=={len(data)}'
)
(t_X, t_y), (v_X, v_y) = data
if type(t_X) is np.ndarray and type(t_y) is np.ndarray and \
type(v_X) is np.ndarray and type(v_y) is np.ndarray:
input_shape = np.shape(t_X)[1:]
elif type(t_X) is list and type(t_y) is np.ndarray and \
type(v_X) is list and type(v_y) is np.ndarray:
input_shape = [np.shape(itX)[1:] for itX in t_X
] # interested in shape of data not in length
else:
raise RuntimeError(
f'Data returned by load_data function are of a wrong type: type(t_X)=={type(t_X)}, type(t_y)=={type(t_y)}, type(v_X)=={type(v_X)}, type(v_y)=={type(v_y)}'
)
output_shape = np.shape(t_y)[1:]
config['data'] = {
'train_X': t_X,
'train_Y': t_y,
'valid_X': v_X,
'valid_Y': v_y
}
elif type(data) is dict:
config['data'] = data
input_shape = [
data['shapes'][0][f'input_{i}']
for i in range(len(data['shapes'][0]))
]
output_shape = data['shapes'][1]
else:
raise RuntimeError(
f'Data returned by load_data function are of an unsupported type: {type(data)}'
)
cs_kwargs = config['create_structure'].get('kwargs')
if cs_kwargs is None:
structure = config['create_structure']['func'](input_shape,
output_shape)
else:
structure = config['create_structure']['func'](input_shape,
output_shape,
**cs_kwargs)
arch_seq = ARCH_SEQ
structure.set_ops(arch_seq)
try:
structure.draw_graphviz('graph_full.dot')
except:
pass
print('Model operations set.')
if config.get('preprocessing') is not None:
preprocessing = util.load_attr_from(config['preprocessing']['func'])
config['preprocessing']['func'] = preprocessing
print(f"Preprocessing set with: {config['preprocessing']}")
else:
print('No preprocessing...')
config['preprocessing'] = None
model_created = False
if config['regression']:
try:
model = structure.create_model()
model_created = True
except:
model_created = False
print('Error: Model creation failed...')
print('INFO STACKTRACE: ', traceback.format_exc())
if model_created:
try:
plot_model(model, to_file='model.png', show_shapes=True)
model.summary()
except Exception as err:
print('can\t create model.png file...')
print('INFO STACKTRACE: ', traceback.format_exc())
try:
model.load_weights("model_weights.h5")
print('model weights loaded!')
except Exception as err:
print('failed to load model weights...')
print('INFO STACKTRACE: ', traceback.format_exc())
trainer = TrainerRegressorTrainValid(config=config, model=model)
else:
try:
model = structure.create_model(activation='softmax')
model_created = True
except Exception as err:
model_created = False
print('Error: Model creation failed...')
print('INFO STACKTRACE: ', traceback.format_exc())
if model_created:
try:
plot_model(model, to_file='model.png', show_shapes=True)
except Exception as err:
print('can\t create model.png file...')
print('INFO STACKTRACE: ', traceback.format_exc())
try:
model.load_weights("model_weights.h5")
print('model weights loaded!')
except Exception as err:
print('failed to load model weights...')
print('INFO STACKTRACE: ', traceback.format_exc())
trainer = TrainerClassifierTrainValid(config=config, model=model)
tb_cb = keras.callbacks.TensorBoard(histogram_freq=0,
batch_size=256,
write_grads=True)
trainer.add_callback(tb_cb)
print('Trainer is ready.')
print(f'Start training... num_epochs={num_epochs}')
nparams = number_parameters()
print('model number of parameters: ', nparams)
if NUM_EPOCHS > 0:
trainer.train(num_epochs=num_epochs)
# serialize weights to HDF5
model.save_weights("model_weights.h5")
print("Saved model weight to disk: model_weights.h5")
if config['regression']:
y_orig, y_pred = trainer.predict('valid')
r_list = list()
for dim in range(np.shape(y_orig)[1]):
r, _ = stats.pearsonr(y_orig[:, dim], y_pred[:, dim])
r_list.append(r)
print('r_list: ', r_list)