def run(params):
args = candle.ArgumentStruct(**params)
seed = args.rng_seed
candle.set_seed(seed)
# # Construct extension to save model
# ext = p1b1.extension_from_parameters(params, '.keras')
# candle.verify_path(params['save_path'])
# prefix = '{}{}'.format(params['save_path'], ext)
# logfile = params['logfile'] if params['logfile'] else prefix+'.log'
# candle.set_up_logger(logfile, p1b1.logger, params['verbose'])
#p1b1.logger.info('Params: {}'.format(params))
# Get default parameters for initialization and optimizer functions
keras_defaults = candle.keras_default_config()
# Load dataset
x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels = p1b1.load_data(
params, seed)
# cache_file = 'data_l1000_cache.h5'
# save_cache(cache_file, x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels)
# x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels = load_cache(cache_file)
# p1b1.logger.info("Shape x_train: {}".format(x_train.shape))
# p1b1.logger.info("Shape x_val: {}".format(x_val.shape))
#p1b1.logger.info("Shape x_test: {}".format(x_test.shape))
# p1b1.logger.info("Range x_train: [{:.3g}, {:.3g}]".format(np.min(x_train), np.max(x_train)))
# p1b1.logger.info("Range x_val: [{:.3g}, {:.3g}]".format(np.min(x_val), np.max(x_val)))
#p1b1.logger.info("Range x_test: [{:.3g}, {:.3g}]".format(np.min(x_test), np.max(x_test)))
# p1b1.logger.debug('Class labels')
# for i, label in enumerate(y_labels):
# p1b1.logger.debug(' {}: {}'.format(i, label))
# clf = build_type_classifier(x_train, y_train, x_val, y_val)
n_classes = len(y_labels)
cond_train = y_train
cond_val = y_val
cond_test = y_test
input_dim = x_train.shape[1]
cond_dim = cond_train.shape[1]
latent_dim = params['latent_dim']
activation = params['activation']
dropout = params['dropout']
dense_layers = params['dense']
dropout_layer = AlphaDropout if params['alpha_dropout'] else Dropout
# Initialize weights and learning rule
initializer_weights = candle.build_initializer(params['initialization'],
keras_defaults, seed)
initializer_bias = candle.build_initializer('constant', keras_defaults, 0.)
if dense_layers is not None:
if type(dense_layers) != list:
dense_layers = list(dense_layers)
else:
dense_layers = []
# Encoder Part
x_input = Input(shape=(input_dim, ))
cond_input = Input(shape=(cond_dim, ))
h = x_input
if params['model'] == 'cvae':
h = keras.layers.concatenate([x_input, cond_input])
for i, layer in enumerate(dense_layers):
if layer > 0:
x = h
h = Dense(layer,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
if params['residual']:
try:
h = keras.layers.add([h, x])
except ValueError:
pass
if params['batch_normalization']:
h = BatchNormalization()(h)
if dropout > 0:
h = dropout_layer(dropout)(h)
if params['model'] == 'ae':
encoded = Dense(latent_dim,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
else:
epsilon_std = params['epsilon_std']
z_mean = Dense(latent_dim, name='z_mean')(h)
z_log_var = Dense(latent_dim, name='z_log_var')(h)
encoded = z_mean
def vae_loss(x, x_decoded_mean):
xent_loss = binary_crossentropy(x, x_decoded_mean)
kl_loss = -0.5 * K.sum(
1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
return K.mean(xent_loss + kl_loss / input_dim)
def sampling(params):
z_mean_, z_log_var_ = params
batch_size = K.shape(z_mean_)[0]
epsilon = K.random_normal(shape=(batch_size, latent_dim),
mean=0.,
stddev=epsilon_std)
return z_mean_ + K.exp(z_log_var_ / 2) * epsilon
z = Lambda(sampling, output_shape=(latent_dim, ))([z_mean, z_log_var])
if params['model'] == 'cvae':
z_cond = keras.layers.concatenate([z, cond_input])
# Build autoencoder model
if params['model'] == 'cvae':
# encoder = Model([x_input, cond_input], encoded)
# decoder = Model([decoder_input, cond_input], decoded)
# model = Model([x_input, cond_input], decoder([z, cond_input]))
loss = vae_loss
metrics = [xent, corr, mse]
elif params['model'] == 'vae':
# encoder = Model(x_input, encoded)
# decoder = Model(decoder_input, decoded)
# model = Model(x_input, decoder(z))
loss = vae_loss
metrics = [xent, corr, mse]
else:
# encoder = Model(x_input, encoded)
# decoder = Model(decoder_input, decoded)
# model = Model(x_input, decoder(encoded))
loss = params['loss']
metrics = [xent, corr]
# Define optimizer
# optimizer = candle.build_optimizer(params['optimizer'],
# params['learning_rate'],
# keras_defaults)
optimizer = optimizers.deserialize({
'class_name': params['optimizer'],
'config': {}
})
base_lr = params['base_lr'] or K.get_value(optimizer.lr)
if params['learning_rate']:
K.set_value(optimizer.lr, params['learning_rate'])
if params['model'] == 'cvae':
# inputs = [x_train, cond_train]
# val_inputs = [x_val, cond_val]
test_inputs = [x_test, cond_test]
else:
# inputs = x_train
# val_inputs = x_val
test_inputs = x_test
test_outputs = x_test
model_name = params['model_name']
# load json and create model
json_file = open('{}.{}.model.json'.format(model_name, params['model']),
'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('{}.{}.weights.h5'.format(
model_name, params['model']))
print("Loaded model from disk")
# evaluate loaded model on test data
loaded_model_json.compile(loss=loss, optimizer=optimizer, metrics=metrics)
x_pred = loaded_model_json.predict(test_inputs)
scores = p1b1.evaluate_autoencoder(x_pred, x_test)
# p1b1.logger.info('\nEvaluation on test data: {}'.format(scores))
print('Evaluation on test data: {}'.format(scores))
# load encoder
encoder = load_model('{}.{}.encoder.h5'.format(model_name,
params['model']))
print("Loaded encoder from disk")
x_test_encoded = encoder.predict(test_inputs,
batch_size=params['batch_size'])
y_test_classes = np.argmax(y_test, axis=1)
candle.plot_scatter(x_test_encoded, y_test_classes,
'{}.{}.latent'.format(model_name, params['model']))
if params['tsne']:
tsne = TSNE(n_components=2, random_state=seed)
x_test_encoded_tsne = tsne.fit_transform(x_test_encoded)
candle.plot_scatter(
x_test_encoded_tsne, y_test_classes,
'{}.{}.latent.tsne'.format(model_name, params['model']))
def run(params):
args = candle.ArgumentStruct(**params)
seed = args.rng_seed
candle.set_seed(seed)
# Construct extension to save model
ext = p1b1.extension_from_parameters(params, '.keras')
candle.verify_path(params['save'])
prefix = '{}{}'.format(params['save'], ext)
logfile = params['logfile'] if params['logfile'] else prefix + '.log'
candle.set_up_logger(logfile, p1b1.logger, params['verbose'])
p1b1.logger.info('Params: {}'.format(params))
# Get default parameters for initialization and optimizer functions
keras_defaults = candle.keras_default_config()
# Load dataset
x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels = p1b1.load_data(
params, seed)
# cache_file = 'data_l1000_cache.h5'
# save_cache(cache_file, x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels)
# x_train, y_train, x_val, y_val, x_test, y_test, x_labels, y_labels = load_cache(cache_file)
p1b1.logger.info("Shape x_train: {}".format(x_train.shape))
p1b1.logger.info("Shape x_val: {}".format(x_val.shape))
p1b1.logger.info("Shape x_test: {}".format(x_test.shape))
p1b1.logger.info("Range x_train: [{:.3g}, {:.3g}]".format(
np.min(x_train), np.max(x_train)))
p1b1.logger.info("Range x_val: [{:.3g}, {:.3g}]".format(
np.min(x_val), np.max(x_val)))
p1b1.logger.info("Range x_test: [{:.3g}, {:.3g}]".format(
np.min(x_test), np.max(x_test)))
p1b1.logger.debug('Class labels')
for i, label in enumerate(y_labels):
p1b1.logger.debug(' {}: {}'.format(i, label))
# clf = build_type_classifier(x_train, y_train, x_val, y_val)
n_classes = len(y_labels)
cond_train = y_train
cond_val = y_val
cond_test = y_test
input_dim = x_train.shape[1]
cond_dim = cond_train.shape[1]
latent_dim = params['latent_dim']
activation = params['activation']
dropout = params['drop']
dense_layers = params['dense']
dropout_layer = keras.layers.noise.AlphaDropout if params[
'alpha_dropout'] else Dropout
# Initialize weights and learning rule
initializer_weights = candle.build_initializer(params['initialization'],
keras_defaults, seed)
initializer_bias = candle.build_initializer('constant', keras_defaults, 0.)
if dense_layers is not None:
if type(dense_layers) != list:
dense_layers = list(dense_layers)
else:
dense_layers = []
# Encoder Part
x_input = Input(shape=(input_dim, ))
cond_input = Input(shape=(cond_dim, ))
h = x_input
if params['model'] == 'cvae':
h = keras.layers.concatenate([x_input, cond_input])
for i, layer in enumerate(dense_layers):
if layer > 0:
x = h
h = Dense(layer,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
if params['residual']:
try:
h = keras.layers.add([h, x])
except ValueError:
pass
if params['batch_normalization']:
h = BatchNormalization()(h)
if dropout > 0:
h = dropout_layer(dropout)(h)
if params['model'] == 'ae':
encoded = Dense(latent_dim,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
else:
epsilon_std = params['epsilon_std']
z_mean = Dense(latent_dim, name='z_mean')(h)
z_log_var = Dense(latent_dim, name='z_log_var')(h)
encoded = z_mean
def vae_loss(x, x_decoded_mean):
xent_loss = binary_crossentropy(x, x_decoded_mean)
kl_loss = -0.5 * K.sum(
1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
return K.mean(xent_loss + kl_loss / input_dim)
def sampling(params):
z_mean_, z_log_var_ = params
batch_size = K.shape(z_mean_)[0]
epsilon = K.random_normal(shape=(batch_size, latent_dim),
mean=0.,
stddev=epsilon_std)
return z_mean_ + K.exp(z_log_var_ / 2) * epsilon
z = Lambda(sampling, output_shape=(latent_dim, ))([z_mean, z_log_var])
if params['model'] == 'cvae':
z_cond = keras.layers.concatenate([z, cond_input])
# Decoder Part
decoder_input = Input(shape=(latent_dim, ))
h = decoder_input
if params['model'] == 'cvae':
h = keras.layers.concatenate([decoder_input, cond_input])
for i, layer in reversed(list(enumerate(dense_layers))):
if layer > 0:
x = h
h = Dense(layer,
activation=activation,
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
if params['residual']:
try:
h = keras.layers.add([h, x])
except ValueError:
pass
if params['batch_normalization']:
h = BatchNormalization()(h)
if dropout > 0:
h = dropout_layer(dropout)(h)
decoded = Dense(input_dim,
activation='sigmoid',
kernel_initializer=initializer_weights,
bias_initializer=initializer_bias)(h)
# Build autoencoder model
if params['model'] == 'cvae':
encoder = Model([x_input, cond_input], encoded)
decoder = Model([decoder_input, cond_input], decoded)
model = Model([x_input, cond_input], decoder([z, cond_input]))
loss = vae_loss
metrics = [xent, corr, mse]
elif params['model'] == 'vae':
encoder = Model(x_input, encoded)
decoder = Model(decoder_input, decoded)
model = Model(x_input, decoder(z))
loss = vae_loss
metrics = [xent, corr, mse]
else:
encoder = Model(x_input, encoded)
decoder = Model(decoder_input, decoded)
model = Model(x_input, decoder(encoded))
loss = params['loss']
metrics = [xent, corr]
model.summary()
decoder.summary()
if params['cp']:
model_json = model.to_json()
with open(prefix + '.model.json', 'w') as f:
print(model_json, file=f)
# Define optimizer
# optimizer = candle.build_optimizer(params['optimizer'],
# params['learning_rate'],
# keras_defaults)
optimizer = optimizers.deserialize({
'class_name': params['optimizer'],
'config': {}
})
base_lr = params['base_lr'] or K.get_value(optimizer.lr)
if params['learning_rate']:
K.set_value(optimizer.lr, params['learning_rate'])
model.compile(loss=loss, optimizer=optimizer, metrics=metrics)
# calculate trainable and non-trainable params
params.update(candle.compute_trainable_params(model))
def warmup_scheduler(epoch):
lr = params['learning_rate'] or base_lr * params['batch_size'] / 100
if epoch <= 5:
K.set_value(model.optimizer.lr,
(base_lr * (5 - epoch) + lr * epoch) / 5)
p1b1.logger.debug('Epoch {}: lr={}'.format(
epoch, K.get_value(model.optimizer.lr)))
return K.get_value(model.optimizer.lr)
reduce_lr = ReduceLROnPlateau(monitor='val_loss',
factor=0.5,
patience=5,
min_lr=0.00001)
warmup_lr = LearningRateScheduler(warmup_scheduler)
checkpointer = ModelCheckpoint(params['save'] + ext + '.weights.h5',
save_best_only=True,
save_weights_only=True)
tensorboard = TensorBoard(log_dir="tb/tb{}".format(ext))
candle_monitor = candle.CandleRemoteMonitor(params=params)
timeout_monitor = candle.TerminateOnTimeOut(params['timeout'])
history_logger = LoggingCallback(p1b1.logger.debug)
callbacks = [candle_monitor, timeout_monitor, history_logger]
if params['reduce_lr']:
callbacks.append(reduce_lr)
if params['warmup_lr']:
callbacks.append(warmup_lr)
if params['cp']:
callbacks.append(checkpointer)
if params['tb']:
callbacks.append(tensorboard)
x_val2 = np.copy(x_val)
np.random.shuffle(x_val2)
start_scores = p1b1.evaluate_autoencoder(x_val, x_val2)
p1b1.logger.info('\nBetween random pairs of validation samples: {}'.format(
start_scores))
if params['model'] == 'cvae':
inputs = [x_train, cond_train]
val_inputs = [x_val, cond_val]
test_inputs = [x_test, cond_test]
else:
inputs = x_train
val_inputs = x_val
test_inputs = x_test
outputs = x_train
val_outputs = x_val
test_outputs = x_test
history = model.fit(inputs,
outputs,
verbose=2,
batch_size=params['batch_size'],
epochs=params['epochs'],
callbacks=callbacks,
validation_data=(val_inputs, val_outputs))
if params['cp']:
encoder.save(prefix + '.encoder.h5')
decoder.save(prefix + '.decoder.h5')
plot_history(prefix, history, 'loss')
plot_history(prefix, history, 'corr', 'streaming pearson correlation')
# Evalute model on test set
x_pred = model.predict(test_inputs)
scores = p1b1.evaluate_autoencoder(x_pred, x_test)
p1b1.logger.info('\nEvaluation on test data: {}'.format(scores))
x_test_encoded = encoder.predict(test_inputs,
batch_size=params['batch_size'])
y_test_classes = np.argmax(y_test, axis=1)
plot_scatter(x_test_encoded, y_test_classes, prefix + '.latent')
if params['tsne']:
tsne = TSNE(n_components=2, random_state=seed)
x_test_encoded_tsne = tsne.fit_transform(x_test_encoded)
plot_scatter(x_test_encoded_tsne, y_test_classes,
prefix + '.latent.tsne')
# diff = x_pred - x_test
# plt.hist(diff.ravel(), bins='auto')
# plt.title("Histogram of Errors with 'auto' bins")
# plt.savefig('histogram_keras.png')
# generate synthetic data
# epsilon_std = 1.0
# for i in range(1000):
# z_sample = np.random.normal(size=(1, 2)) * epsilon_std
# x_decoded = decoder.predict(z_sample)
p1b1.logger.handlers = []
return history
def main():
# Get command-line parameters
parser = get_p1b1_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b1.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 = p1b1.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, X_val, X_test = p1b1.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("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))
input_dim = X_train.shape[1]
output_dim = input_dim
# 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['datatype'],
max_devices=args.max_devices,
compat_mode=args.compat_mode)
# Set input and target to X_train
train = ArrayIterator(X_train)
val = ArrayIterator(X_val)
test = ArrayIterator(X_test)
# Initialize weights and learning rule
initializer_weights = p1_common_neon.build_initializer(
gParameters['initialization'], kerasDefaults)
initializer_bias = p1_common_neon.build_initializer(
'constant', kerasDefaults, 0.)
activation = p1_common_neon.get_function(gParameters['activation'])()
# Define Autoencoder architecture
layers = []
reshape = None
# Autoencoder
layers_params = gParameters['dense']
if layers_params != None:
if type(layers_params) != list:
layers_params = list(layers_params)
# Encoder Part
for i, l in enumerate(layers_params):
layers.append(
Affine(nout=l,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
# Decoder Part
for i, l in reversed(list(enumerate(layers_params))):
if i < len(layers) - 1:
layers.append(
Affine(nout=l,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
layers.append(
Affine(nout=output_dim,
init=initializer_weights,
bias=initializer_bias,
activation=activation))
# Build Autoencoder model
ae = 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(ae, eval_set=val, eval_freq=1)
# Seed random generator for training
np.random.seed(seed)
ae.fit(train,
optimizer=optimizer,
num_epochs=gParameters['epochs'],
cost=cost,
callbacks=callbacks)
# model save
#save_fname = "model_ae_W" + ext
#ae.save_params(save_fname)
# Compute errors
X_pred = ae.get_outputs(test)
scores = p1b1.evaluate_autoencoder(X_pred, X_test)
print('Evaluation on test data:', scores)
diff = X_pred - X_test
# Plot histogram of errors comparing input and output of autoencoder
plt.hist(diff.ravel(), bins='auto')
plt.title("Histogram of Errors with 'auto' bins")
plt.savefig('histogram_neon.png')
def main():
# Get command-line parameters
parser = get_p1b1_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b1.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 = p1b1.extension_from_parameters(gParameters, '.pt')
logfile = args.logfile if args.logfile else args.save + ext + '.log'
p1b1.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, X_val, X_test = p1b1.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("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))
# Set input and target to X_train
train_data = torch.from_numpy(X_train)
train_tensor = data.TensorDataset(train_data, train_data)
train_iter = data.DataLoader(train_tensor,
batch_size=gParameters['batch_size'],
shuffle=gParameters['shuffle'])
# Validation set
val_data = torch.from_numpy(X_val)
val_tensor = torch.utils.data.TensorDataset(val_data, val_data)
val_iter = torch.utils.data.DataLoader(
val_tensor,
batch_size=gParameters['batch_size'],
shuffle=gParameters['shuffle'])
# Test set
test_data = torch.from_numpy(X_test)
test_tensor = torch.utils.data.TensorDataset(test_data, test_data)
test_iter = torch.utils.data.DataLoader(
test_tensor,
batch_size=gParameters['batch_size'],
shuffle=gParameters['shuffle'])
#net = mx.sym.Variable('data')
#out = mx.sym.Variable('softmax_label')
input_dim = X_train.shape[1]
output_dim = input_dim
# Define Autoencoder architecture
layers = gParameters['dense']
activation = p1_common_pytorch.build_activation(gParameters['activation'])
loss_fn = p1_common_pytorch.get_function(gParameters['loss'])
'''
N1 = layers[0]
NE = layers[1]
net = nn.Sequential(
nn.Linear(input_dim,N1),
activation,
nn.Linear(N1,NE),
activation,
nn.Linear(NE,N1),
activation,
nn.Linear(N1,output_dim),
activation,
)
'''
# Documentation indicates this should work
net = nn.Sequential()
if layers != None:
if type(layers) != list:
layers = list(layers)
# Encoder Part
for i, l in enumerate(layers):
if i == 0:
net.add_module('in_dense', nn.Linear(input_dim, l))
net.add_module('in_act', activation)
insize = l
else:
net.add_module('en_dense%d' % i, nn.Linear(insize, l))
net.add_module('en_act%d' % i, activation)
insize = l
# Decoder Part
for i, l in reversed(list(enumerate(layers))):
if i < len(layers) - 1:
net.add_module('de_dense%d' % i, nn.Linear(insize, l))
net.add_module('de_act%d' % i, activation)
insize = l
net.add_module('out_dense', nn.Linear(insize, output_dim))
net.add_module('out_act', activation)
# Initialize weights
for m in net.modules():
if isinstance(m, nn.Linear):
p1_common_pytorch.build_initializer(m.weight,
gParameters['initialization'],
kerasDefaults)
p1_common_pytorch.build_initializer(m.bias, 'constant',
kerasDefaults, 0.0)
# Display model
print(net)
# Define context
# Define optimizer
optimizer = p1_common_pytorch.build_optimizer(net,
gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# Seed random generator for training
torch.manual_seed(seed)
#use_gpu = torch.cuda.is_available()
use_gpu = 0
train_loss = 0
freq_log = 1
for epoch in range(gParameters['epochs']):
for batch, (in_train, _) in enumerate(train_iter):
in_train = Variable(in_train)
#print(in_train.data.shape())
if use_gpu:
in_train = in_train.cuda()
optimizer.zero_grad()
output = net(in_train)
loss = loss_fn(output, in_train)
loss.backward()
train_loss += loss.data[0]
optimizer.step()
if batch % freq_log == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch * len(in_train), len(train_iter.dataset),
100. * batch / len(train_iter),
loss.data[0])) # / len(in_train)))
print('====> Epoch: {} Average loss: {:.4f}'.format(
epoch, train_loss / len(train_iter.dataset)))
# model save
#save_filepath = "model_ae_" + ext
#ae.save(save_filepath)
# Evalute model on valdation set
for i, (in_val, _) in enumerate(val_iter):
in_val = Variable(in_val)
X_pred = net(in_val).data.numpy()
if i == 0:
in_all = in_val.data.numpy()
out_all = X_pred
else:
in_all = np.append(in_all, in_val.data.numpy(), axis=0)
out_all = np.append(out_all, X_pred, axis=0)
#print ("Shape in_all: ", in_all.shape)
#print ("Shape out_all: ", out_all.shape)
scores = p1b1.evaluate_autoencoder(in_all, out_all)
print('Evaluation on validation data:', scores)
# Evalute model on test set
for i, (in_test, _) in enumerate(test_iter):
in_test = Variable(in_test)
X_pred = net(in_test).data.numpy()
if i == 0:
in_all = in_test.data.numpy()
out_all = X_pred
else:
in_all = np.append(in_all, in_test.data.numpy(), axis=0)
out_all = np.append(out_all, X_pred, axis=0)
#print ("Shape in_all: ", in_all.shape)
#print ("Shape out_all: ", out_all.shape)
scores = p1b1.evaluate_autoencoder(in_all, out_all)
print('Evaluation on test data:', scores)
diff = in_all - out_all
plt.hist(diff.ravel(), bins='auto')
plt.title("Histogram of Errors with 'auto' bins")
plt.savefig('histogram_mx.pdf')
def main():
# Get command-line parameters
parser = get_p1b1_parser()
args = parser.parse_args()
#print('Args:', args)
# Get parameters from configuration file
fileParameters = p1b1.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 = p1b1.extension_from_parameters(gParameters, '.mx')
logfile = args.logfile if args.logfile else args.save+ext+'.log'
p1b1.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, X_val, X_test = p1b1.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 ("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))
# Set input and target to X_train
train_iter = mx.io.NDArrayIter(X_train, X_train, gParameters['batch_size'], shuffle=gParameters['shuffle'])
val_iter = mx.io.NDArrayIter(X_val, X_val, gParameters['batch_size'])
test_iter = mx.io.NDArrayIter(X_test, X_test, gParameters['batch_size'])
net = mx.sym.Variable('data')
out = mx.sym.Variable('softmax_label')
input_dim = X_train.shape[1]
output_dim = input_dim
# 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 Autoencoder architecture
layers = gParameters['dense']
if layers != None:
if type(layers) != list:
layers = list(layers)
# Encoder Part
for i,l in enumerate(layers):
net = mx.sym.FullyConnected(data=net, num_hidden=l)
net = mx.sym.Activation(data=net, act_type=activation)
# Decoder Part
for i,l in reversed( list(enumerate(layers)) ):
if i < len(layers)-1:
net = mx.sym.FullyConnected(data=net, num_hidden=l)
net = mx.sym.Activation(data=net, act_type=activation)
net = mx.sym.FullyConnected(data=net, num_hidden=output_dim)
#net = mx.sym.Activation(data=net, act_type=activation)
net = mx.symbol.LinearRegressionOutput(data=net, label=out)
# Display model
p1_common_mxnet.plot_network(net, 'net'+ext)
# Define context
devices = mx.cpu()
if gParameters['gpus']:
devices = [mx.gpu(i) for i in gParameters['gpus']]
# Build Autoencoder model
ae = mx.mod.Module(symbol=net, context=devices)
# Define optimizer
optimizer = p1_common_mxnet.build_optimizer(gParameters['optimizer'],
gParameters['learning_rate'],
kerasDefaults)
# Seed random generator for training
mx.random.seed(seed)
freq_log = 1
ae.fit(train_iter, eval_data=val_iter,
eval_metric=gParameters['loss'],
optimizer=optimizer,
num_epoch=gParameters['epochs'])#,
#epoch_end_callback = mx.callback.Speedometer(gParameters['batch_size'], freq_log))
# model save
#save_filepath = "model_ae_" + ext
#ae.save(save_filepath)
# Evalute model on test set
X_pred = ae.predict(test_iter).asnumpy()
#print ("Shape X_pred: ", X_pred.shape)
scores = p1b1.evaluate_autoencoder(X_pred, X_test)
print('Evaluation on test data:', scores)
diff = X_pred - X_test
plt.hist(diff.ravel(), bins='auto')
plt.title("Histogram of Errors with 'auto' bins")
plt.savefig('histogram_mx.png')