def run(gParameters):
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.keras')
candle.verify_path(gParameters['save_path'])
prefix = '{}{}'.format(gParameters['save_path'], ext)
logfile = gParameters['logfile'] if gParameters[
'logfile'] else prefix + '.log'
#candle.set_up_logger(logfile, p1b2.logger, gParameters['verbose'])
#p1b2.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = candle.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
(X_train, y_train), (X_test, y_test) = p1b2.load_data2(gParameters, seed)
print("Shape X_test: ", X_test.shape)
print("Shape y_test: ", y_test.shape)
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
print("Range y_test --> Min: ", np.min(y_test), ", max: ", np.max(y_test))
# Define optimizer
optimizer = candle.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# load json and create model
json_file = open('p1b2.model.json', 'r')
loaded_model_json = json_file.read()
json_file.close()
loaded_model_json = model_from_json(loaded_model_json)
# load weights into new model
loaded_model_json.load_weights('p1b2.model.h5')
print("Loaded model from disk")
# evaluate loaded model on test data
loaded_model_json.compile(loss=gParameters['loss'],
optimizer=optimizer,
metrics=['accuracy'])
y_pred = loaded_model_json.predict(X_test)
scores = p1b2.evaluate_accuracy_one_hot(y_pred, y_test)
print('Evaluation on test data:', scores)
def run(gParameters):
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.keras')
logfile = gParameters['logfile'] if gParameters[
'logfile'] else gParameters['output_dir'] + ext + '.log'
p1b2.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = candle.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
#(X_train, y_train), (X_test, y_test) = p1b2.load_data(gParameters, seed)
(X_train,
y_train), (X_val,
y_val), (X_test,
y_test) = p1b2.load_data_one_hot(gParameters, seed)
print("Shape X_train: ", X_train.shape)
print("Shape X_val: ", X_val.shape)
print("Shape X_test: ", X_test.shape)
print("Shape y_train: ", y_train.shape)
print("Shape y_val: ", y_val.shape)
print("Shape y_test: ", y_test.shape)
print("Range X_train --> Min: ", np.min(X_train), ", max: ",
np.max(X_train))
print("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
print("Range y_train --> Min: ", np.min(y_train), ", max: ",
np.max(y_train))
print("Range y_val --> Min: ", np.min(y_val), ", max: ", np.max(y_val))
print("Range y_test --> Min: ", np.min(y_test), ", max: ", np.max(y_test))
input_dim = X_train.shape[1]
input_vector = Input(shape=(input_dim, ))
output_dim = y_train.shape[1]
# Initialize weights and learning rule
initializer_weights = candle.build_initializer(
gParameters['initialization'], kerasDefaults, seed)
initializer_bias = candle.build_initializer('constant', kerasDefaults, 0.)
activation = gParameters['activation']
# Define MLP architecture
layers = gParameters['dense']
if layers != None:
if type(layers) != list:
layers = list(layers)
for i, l in enumerate(layers):
if i == 0:
x = Dense(l,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias,
kernel_regularizer=l2(gParameters['penalty']),
activity_regularizer=l2(
gParameters['penalty']))(input_vector)
else:
x = Dense(l,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias,
kernel_regularizer=l2(gParameters['penalty']),
activity_regularizer=l2(gParameters['penalty']))(x)
if gParameters['drop']:
x = Dropout(gParameters['drop'])(x)
output = Dense(output_dim,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(x)
else:
output = Dense(output_dim,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(input_vector)
# Build MLP model
mlp = Model(outputs=output, inputs=input_vector)
p1b2.logger.debug('Model: {}'.format(mlp.to_json()))
# Define optimizer
optimizer = candle.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# Compile and display model
mlp.compile(loss=gParameters['loss'],
optimizer=optimizer,
metrics=['accuracy'])
mlp.summary()
# Seed random generator for training
np.random.seed(seed)
mlp.fit(X_train,
y_train,
batch_size=gParameters['batch_size'],
epochs=gParameters['epochs'],
validation_data=(X_val, y_val))
# model save
#save_filepath = "model_mlp_W_" + ext
#mlp.save_weights(save_filepath)
# Evalute model on test set
y_pred = mlp.predict(X_test)
scores = p1b2.evaluate_accuracy_one_hot(y_pred, y_test)
print('Evaluation on test data:', scores)
def main():
# Get command-line parameters
parser = get_p1b2_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b2.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.mx')
logfile = args.logfile if args.logfile else args.save + ext + '.log'
p1b2.logger.info('Params: {}'.format(gParameters))
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
#(X_train, y_train), (X_val, y_val), (X_test, y_test) = p1b2.load_data(gParameters, seed)
(X_train,
y_train), (X_val,
y_val), (X_test,
y_test) = p1b2.load_data_one_hot(gParameters, seed)
print("Shape X_train: ", X_train.shape)
print("Shape X_val: ", X_val.shape)
print("Shape X_test: ", X_test.shape)
print("Shape y_train: ", y_train.shape)
print("Shape y_val: ", y_val.shape)
print("Shape y_test: ", y_test.shape)
print("Range X_train --> Min: ", np.min(X_train), ", max: ",
np.max(X_train))
print("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
print("Range y_train --> Min: ", np.min(y_train), ", max: ",
np.max(y_train))
print("Range y_val --> Min: ", np.min(y_val), ", max: ", np.max(y_val))
print("Range y_test --> Min: ", np.min(y_test), ", max: ", np.max(y_test))
# Set input and target to X_train
train_iter = mx.io.NDArrayIter(X_train,
y_train,
gParameters['batch_size'],
shuffle=gParameters['shuffle'])
val_iter = mx.io.NDArrayIter(X_val, y_val, gParameters['batch_size'])
test_iter = mx.io.NDArrayIter(X_test, y_test, gParameters['batch_size'])
net = mx.sym.Variable('data') #X')
out = mx.sym.Variable('softmax_label') #y')
num_classes = y_train.shape[1]
# Initialize weights and learning rule
initializer_weights = p1_common_mxnet.build_initializer(
gParameters['initialization'], kerasDefaults)
initializer_bias = p1_common_mxnet.build_initializer(
'constant', kerasDefaults, 0.)
init = mx.initializer.Mixed(['bias', '.*'],
[initializer_bias, initializer_weights])
activation = gParameters['activation']
# Define MLP architecture
layers = gParameters['dense']
if layers != None:
if type(layers) != list:
layers = list(layers)
for i, l in enumerate(layers):
net = mx.sym.FullyConnected(data=net, num_hidden=l)
net = mx.sym.Activation(data=net, act_type=activation)
if gParameters['drop']:
net = mx.sym.Dropout(data=net, p=gParameters['drop'])
net = mx.sym.FullyConnected(data=net, num_hidden=num_classes) # 1)
net = mx.symbol.SoftmaxOutput(data=net, label=out)
# Display model
p1_common_mxnet.plot_network(net, 'net' + ext)
devices = mx.cpu()
if gParameters['gpus']:
devices = [mx.gpu(i) for i in gParameters['gpus']]
# Build MLP model
mlp = mx.mod.Module(symbol=net, context=devices)
# Define optimizer
optimizer = p1_common_mxnet.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
metric = p1_common_mxnet.get_function(gParameters['loss'])()
# Seed random generator for training
mx.random.seed(seed)
mlp.fit(
train_iter,
eval_data=val_iter,
# eval_metric=metric,
optimizer=optimizer,
num_epoch=gParameters['epochs'],
initializer=init)
# model save
#save_filepath = "model_mlp_" + ext
#mlp.save(save_filepath)
# Evalute model on test set
y_pred = mlp.predict(test_iter).asnumpy()
#print ("Shape y_pred: ", y_pred.shape)
scores = p1b2.evaluate_accuracy_one_hot(y_pred, y_test)
print('Evaluation on test data:', scores)
def main():
# Get command-line parameters
parser = get_p1b2_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b2.read_config_file(args.config_file)
#print ('Params:', fileParameters)
# Correct for arguments set by default by neon parser
# (i.e. instead of taking the neon parser default value fall back to the config file,
# if effectively the command-line was used, then use the command-line value)
# This applies to conflictive parameters: batch_size, epochs and rng_seed
if not any("--batch_size" in ag or "-z" in ag for ag in sys.argv):
args.batch_size = fileParameters['batch_size']
if not any("--epochs" in ag or "-e" in ag for ag in sys.argv):
args.epochs = fileParameters['epochs']
if not any("--rng_seed" in ag or "-r" in ag for ag in sys.argv):
args.rng_seed = fileParameters['rng_seed']
# Consolidate parameter set. Command-line parameters overwrite file configuration
gParameters = p1_common.args_overwrite_config(args, fileParameters)
print('Params:', gParameters)
# Determine verbosity level
loggingLevel = logging.DEBUG if args.verbose else logging.INFO
logging.basicConfig(level=loggingLevel, format='')
# Construct extension to save model
ext = p1b2.extension_from_parameters(gParameters, '.neon')
# Get default parameters for initialization and optimizer functions
kerasDefaults = p1_common.keras_default_config()
seed = gParameters['rng_seed']
# Load dataset
#(X_train, y_train), (X_test, y_test) = p1b2.load_data(gParameters, seed)
(X_train, y_train), (X_val,
y_val), (X_test,
y_test) = p1b2.load_data(gParameters, seed)
print("Shape X_train: ", X_train.shape)
print("Shape X_val: ", X_val.shape)
print("Shape X_test: ", X_test.shape)
print("Shape y_train: ", y_train.shape)
print("Shape y_val: ", y_val.shape)
print("Shape y_test: ", y_test.shape)
print("Range X_train --> Min: ", np.min(X_train), ", max: ",
np.max(X_train))
print("Range X_val --> Min: ", np.min(X_val), ", max: ", np.max(X_val))
print("Range X_test --> Min: ", np.min(X_test), ", max: ", np.max(X_test))
print("Range y_train --> Min: ", np.min(y_train), ", max: ",
np.max(y_train))
print("Range y_val --> Min: ", np.min(y_val), ", max: ", np.max(y_val))
print("Range y_test --> Min: ", np.min(y_test), ", max: ", np.max(y_test))
input_dim = X_train.shape[1]
num_classes = int(np.max(y_train)) + 1
output_dim = num_classes # The backend will represent the classes using one-hot representation (but requires an integer class as input !)
# Re-generate the backend after consolidating parsing and file config
gen_backend(backend=args.backend,
rng_seed=seed,
device_id=args.device_id,
batch_size=gParameters['batch_size'],
datatype=gParameters['data_type'],
max_devices=args.max_devices,
compat_mode=args.compat_mode)
train = ArrayIterator(X=X_train, y=y_train, nclass=num_classes)
val = ArrayIterator(X=X_val, y=y_val, nclass=num_classes)
test = ArrayIterator(X=X_test, y=y_test, nclass=num_classes)
# Initialize weights and learning rule
initializer_weights = p1_common_neon.build_initializer(
gParameters['initialization'], kerasDefaults, seed)
initializer_bias = p1_common_neon.build_initializer(
'constant', kerasDefaults, 0.)
activation = p1_common_neon.get_function(gParameters['activation'])()
# Define MLP architecture
layers = []
reshape = None
for layer in gParameters['dense']:
if layer:
layers.append(
Affine(nout=layer,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
if gParameters['dropout']:
layers.append(Dropout(keep=(1 - gParameters['dropout'])))
layers.append(
Affine(nout=output_dim,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
# Build MLP model
mlp = Model(layers=layers)
# Define cost and optimizer
cost = GeneralizedCost(p1_common_neon.get_function(gParameters['loss'])())
optimizer = p1_common_neon.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
callbacks = Callbacks(mlp, eval_set=val, metric=Accuracy(), eval_freq=1)
# Seed random generator for training
np.random.seed(seed)
mlp.fit(train,
optimizer=optimizer,
num_epochs=gParameters['epochs'],
cost=cost,
callbacks=callbacks)
# model save
#save_fname = "model_mlp_W_" + ext
#mlp.save_params(save_fname)
# Evalute model on test set
print('Model evaluation by neon: ', mlp.eval(test, metric=Accuracy()))
y_pred = mlp.get_outputs(test)
#print ("Shape y_pred: ", y_pred.shape)
scores = p1b2.evaluate_accuracy(p1_common.convert_to_class(y_pred), y_test)
print('Evaluation on test data:', scores)