def train_AE(X_train, X_test, encoder_size, decoder_size, epochs, lr):
model = autoencoder.AutoEncoder(encoder_size, decoder_size).to(device)
autoencoder.train(model,
dataset=X_train,
num_epochs=epochs,
batch_size=batch_size,
lr=lr)
# Calculate training error
AE_reconstruction = model(X_train)
training_error = np.mean(
((X_train - AE_reconstruction[0])**2).cpu().detach().numpy())
# Calculate test error
AE_reconstruction = model(X_test)
test_error = np.mean(
((X_test - AE_reconstruction[0])**2).cpu().detach().numpy())
return model, training_error, test_error
def main():
parser = argparse.ArgumentParser()
parser.add_argument(
"--dataset_ratio",
type=float,
default=1,
help="the purcentage of data used in the dataset (default: 1)")
parser.add_argument("--image_size",
type=int,
default=512,
help="size of the input image (default: 512)")
parser.add_argument("--depth",
type=int,
default=6,
help="depth of the autoencoder (default: 6)")
parser.add_argument(
"--num_block",
type=int,
default=3,
help="number of blocks of the autoencoder (default: 3)")
parser.add_argument("--epoch",
type=int,
default=1,
help="number of epoch (default: 1)")
parser.add_argument("--batch",
type=int,
default=100,
help="number of batch (default: 100)")
parser.add_argument("--valpct",
type=float,
default=0.2,
help="proportion of test data (default: 0.2)")
parser.add_argument("--num_threads",
type=int,
default=1,
help="number of thread used (default: 1)")
parser.add_argument("--create_csv",
type=bool,
default=False,
help="create or not csv file (default: False)")
parser.add_argument("--log",
default=False,
action='store_true',
help="Write log or not (default: False)")
parser.add_argument("--l2_reg",
type=int,
default=0.001,
help="L2 regularisation (default: 0.001)")
args = parser.parse_args()
# if args.create_csv:
# g_csv.generate_csv(DATA_PATH + CSV_NAME, args.num_var,
# args.num_const, args.num_prob)
valid_ratio = args.valpct # Going to use 80%/20% split for train/valid
data_transforms = transforms.Compose([ToTensor(), Normalize()])
full_dataset = ImageLoader(csv_file_path=LABEL_FILE_PATH,
image_directory=IMAGE_FOLDER_PATH,
mask_directory=MASK_FOLDER_PATH,
dataset_size=int(args.dataset_ratio *
DATASET_SIZE),
image_size=args.image_size,
transform=data_transforms)
nb_train = int((1.0 - valid_ratio) * len(full_dataset))
nb_test = len(full_dataset) - nb_train
print("Size of full data set: ", len(full_dataset))
print("Size of training data: ", nb_train)
print("Size of testing data: ", nb_test)
train_dataset, test_dataset = torch.utils.data.dataset.random_split(
full_dataset, [nb_train, nb_test])
train_loader = DataLoader(dataset=train_dataset,
batch_size=args.batch,
shuffle=True,
num_workers=args.num_threads)
test_loader = DataLoader(dataset=test_dataset,
batch_size=args.batch,
shuffle=True,
num_workers=args.num_threads)
# TODO params
# num_param = args.num_var + args.num_const + (args.num_var*args.num_const)
model = AutoEncoder(num_block=args.num_block, depth=args.depth)
# print("Network architechture:\n", model)
use_gpu = torch.cuda.is_available()
if use_gpu:
device = torch.device('cuda')
else:
device = torch.device('cpu')
model.to(device)
# f_loss = nn.BCEWithLogitsLoss()
f_loss = loss.Custom_loss()
# define optimizer
optimizer = torch.optim.Adam(model.parameters(), weight_decay=args.l2_reg)
# Make run directory
run_name = "run-"
LogManager = lw.LogManager(LOG_DIR, run_name)
run_dir_path, num_run = LogManager.generate_unique_dir()
# setup model checkpoint
path_model_check_point = run_dir_path + MODEL_DIR
if not os.path.exists(path_model_check_point):
os.mkdir(path_model_check_point)
model_checkpoint = ModelCheckpoint(path_model_check_point + BEST_MODELE,
model)
# top_logdir = LOG_DIR + FC1
# if not os.path.exists(top_logdir):
# os.mkdir(top_logdir)
# model_checkpoint = ModelCheckpoint(top_logdir + BEST_MODELE, model)
if args.log:
print("Writing log")
# generate unique folder for new run
tensorboard_writer = SummaryWriter(log_dir=run_dir_path,
filename_suffix=".log")
LogManager.set_tensorboard_writer(tensorboard_writer)
LogManager.summary_writer(model, optimizer)
# write short description of the run
run_desc = "Epoch{}".format(args.epoch)
log_file_path = LOG_DIR + run_desc + "Run{}".format(num_run) + ".log"
# LogManager.summary_writer(model, optimizer)
# write short description of the run
# run_desc = "Epoch{}Reg{}Var{}Const{}CLoss{}Dlayer{}Alpha{}".format(
# args.num_epoch,
# args.l2_reg,
# args.num_var,
# args.num_const,
# args.custom_loss,
# args.num_deep_layer,
# args.alpha)
# log_file_path = LOG_DIR + "Run{}".format(num_run) + run_desc + ".log"
# log_file_path = lw.generate_unique_logpath(LOG_DIR, "Linear")
with tqdm(total=args.epoch) as pbar:
for t in range(args.epoch):
pbar.update(1)
pbar.set_description("Epoch {}".format(t))
# print(DIEZ + "Epoch Number: {}".format(t) + DIEZ)
train_loss, train_acc = train(model, train_loader, f_loss,
optimizer, device, LogManager)
progress(train_loss, train_acc)
# time.sleep(0.5)
val_loss, val_acc = test(model,
test_loader,
f_loss,
device,
log_manager=LogManager)
print(" Validation : Loss : {:.4f}, Acc : {:.4f}".format(
val_loss, val_acc))
model_checkpoint.update(val_loss)
# lw.write_log(log_file_path, val_acc, val_loss, train_acc, train_loss)
if args.log:
tensorboard_writer.add_scalars("Loss/", {
'train_loss': train_loss,
'val_loss': val_loss
}, t)
# tensorboard_writer.add_scalar(METRICS + 'train_loss', train_loss, t)
# tensorboard_writer.add_scalar(METRICS + 'train_acc', train_acc, t)
# tensorboard_writer.add_scalar(METRICS + 'val_loss', val_loss, t)
# tensorboard_writer.add_scalar(METRICS + 'val_acc', val_acc, t)
LogManager.write_log(log_file_path, val_acc, val_loss, train_acc,
train_loss)
model.load_state_dict(torch.load(path_model_check_point + BEST_MODELE))
print(DIEZ + " Final Test " + DIEZ)
_, _ = test(model,
train_loader,
f_loss,
device,
final_test=True,
log_manager=LogManager,
txt="training")
test_loss, test_acc = test(model,
test_loader,
f_loss,
device,
log_manager=LogManager,
final_test=True)
print(" Test : Loss : {:.4f}, Acc : {:.4f}".format(
test_loss, test_acc))
# Build matrix
keep_data = []
for row in data:
keep_row = {}
for j in keep_header_js:
h = headers[j]
if j < len(row) and row[j] == '' and args.zero:
keep_row[h] = 0.0
elif j < len(row) and row[j]:
keep_row[h] = float(row[j])
if keep_row:
keep_data.append(keep_row)
keep_headers = [headers[j] for j in keep_header_js]
# Compress json output
json.encoder.FLOAT_REPR = lambda f: ("%.4f" % f)
json.encoder.c_make_encoder = None
print 'training'
for model in autoencoder.train(keep_headers,
keep_data,
bins=args.bins,
n_hidden_units=args.n_hidden_units,
n_hidden_layers=args.n_hidden_layers):
js = 'var data = %s;' % json.dumps(model)
f = open(args.output, 'w')
f.write(js)
f.close()
# Build matrix
keep_data = []
for row in data:
keep_row = {}
for j in keep_header_js:
h = headers[j]
if j < len(row) and row[j] == '' and args.zero:
keep_row[h] = 0.0
elif j < len(row) and row[j]:
keep_row[h] = float(row[j])
if keep_row:
keep_data.append(keep_row)
keep_headers = [headers[j] for j in keep_header_js]
# Compress json output
json.encoder.FLOAT_REPR = lambda f: ("%.4f" % f)
json.encoder.c_make_encoder = None
print 'training'
for model in autoencoder.train(keep_headers, keep_data,
bins=args.bins,
n_hidden_units=args.n_hidden_units,
n_hidden_layers=args.n_hidden_layers):
js = 'var data = %s;' % json.dumps(model)
f = open(args.output, 'w')
f.write(js)
f.close()
weight_lambda = 1e-5
training_dataset = tf.data.Dataset.from_tensor_slices(bops).batch(batch_size)
autoencoder = ae.Autoencoder(original_dim=original_dim,
code_dim=code_dim,
hidden_dim=hidden_dim,
weight_lambda=weight_lambda)
#opt = tf.optimizers.SGD(learning_rate=learning_rate, momentum=momentum)
opt = tf.optimizers.Adam(learning_rate=learning_rate)
with open("loss_%s" % input_filename, "w") as loss_file:
real_step = 0
for epoch in range(epochs):
for step, batch_features in enumerate(training_dataset):
ae.train(ae.loss, autoencoder, opt, batch_features)
loss_value = ae.loss(autoencoder, batch_features)
real_step += 1
print("%d %f" % (real_step, loss_value), file=loss_file)
encoded_bops = autoencoder.encoder(tf.constant(bops))
# FIND THE GAUSSIAN MIXTURE MODEL THAT BEST APPROXIMATES THE DATA THROUGH A BIC CRITERIUM
from sklearn import mixture
import itertools
lowest_bic = np.infty
bic = []
n_components_range = range(1, 10)
for n_components in n_components_range:
training_data, validation_data, test_data = mnist_loader.load_data_wrapper()
# only get x inputs
training_data, test_data = np.array(list(training_data))[:, 0], np.array(
list(test_data))[:, 0]
training_data, test_data = np.array(
list(map(lambda x: np.squeeze(x), training_data))), np.array(
list(map(lambda x: np.squeeze(x), test_data)))
print("processed data")
# [ 784, 400, L50, 400, 784]
autoencoder = autoencoder.Autoencoder([784, 400], [400, 784], 50)
print("finished building autoencoder")
autoencoder.train(training_data, test_data)
print("finished training!")
'''=
# Creates filename and prepares network properties(performance and parameters) for saving
# name follows naming scheme: inputsize_layer1size_layer2size_...outputsize
file_name = str(net.sizes).replace("[","").replace("]","").replace(" ","").replace(",","_")+'.pkl'
new_net_properties = [net.performance, net.weights, net.biases, ]
Saves network properties (learned parameters and performance).
If the shape had been previously trained, it will override previous saved file if
new performance is better. If it is a new shape, it will save to a new file
try:
with open('best_networks/{0}'.format(file_name), 'rb') as f:
old_net_properties = pickle.load(f)
import image_preprocessing as img import numpy as np import matplotlib.pyplot as plt import autoencoder as A X = img.blur_images(100) Y = img.pre_process(100) X = X / X.max() Y = Y / Y.max() ip = np.prod(np.array(X[0].shape)) print(X.shape) print(Y.shape) model = A.train(X, Y, ip, 1) predictions = model.predict(X) plt.imshow(predictions[0].reshape(100, 100), cmap='gray') plt.show()
