def run():
global model
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
# Create dataset
template_dataset = TemplateDataset(config)
training_loader, validation_loader, test_loader = template_dataset.get_loaders(
)
# Create the neural network
model = NN(net, optimizer, loss_function, lr_scheduler, metric, device,
config).to(device)
# Create the data handler
data_handler = DataHandler(training_loader, validation_loader, test_loader)
for epoch in range(config['epochs']):
# Training
model.train()
for i, data in enumerate(training_loader, 0):
x, y = data
x, y = x.to(device), y.to(device)
y_hat = model(x)
loss = model.backpropagate(y_hat, y)
result = model.evaluate(y_hat, y)
data_handler.train_loss.append(loss)
data_handler.train_metric.append(result)
with torch.no_grad():
model.eval()
# Validating
if validation_loader is not None:
for i, data in enumerate(validation_loader, 0):
x, y = data
x, y = x.to(device), y.to(device)
y_hat = model(x)
_, loss = model.calculate_loss(y_hat, y)
result = model.evaluate(y_hat, y)
data_handler.valid_loss.append(loss)
data_handler.valid_metric.append(result)
# Testing
if test_loader is not None:
for i, data in enumerate(test_loader, 0):
x, y = data
x, y = x.to(device), y.to(device)
y_hat = model(x)
_, loss = model.calculate_loss(y_hat, y)
result = model.evaluate(y_hat, y)
data_handler.test_loss.append(loss)
data_handler.test_metric.append(result)
model.lr_scheduler_step()
data_handler.epoch_end(epoch, model.get_lr())
data_handler.plot(loss=config['plot']['loss'],
metric=config['plot']['metric'])
float(string[1]) / 10.0,
float(string[2]) / 10.0,
float(string[3]) / 10.0
]]
if string[4].rstrip() == "Iris-setosa":
x += [[1]]
else:
x += [[0]]
testSet += [x]
trainingFile.close()
testFile.close()
#TRAINING
nn.backPropagation(trainingSet, n, 4, nhidden, 1)
#TESTING
p = 0
for x, t in testSet:
O = nn.evaluate(x)
if ((1 - O[0]) < 0.1):
if (t[0] == 1):
p += 1
else:
if (t[0] == 0):
p += 1
print(str(p) + " out of " + str(len(testSet)) + " tests")
nn.saveWeights(sys.argv[5])
else:
print("Usage:\n python Area.py training_file learning_rate number_hidden_neurons test_file \n python Area.py weight_file test_file")
quit()
#TESTING
p = 0
xr = []
yr = []
xc = []
yc = []
for x,t in testSet:
O = nn.evaluate(x)
if O[0] > 0.5:
if t[0] == 1: ##THRESHOLD 0.5
p += 1
xr += [x[0]]
yr += [x[1]]
elif O[0] <= 0.5 :
if t[0] == 0:
p += 1
xc += [x[0]]
yc += [x[1]]
print(p)
#PLOT
# f1, p2 = plt.subplots()
from nn import NN
nn = NN()
train = [[[0, 0], [0]], [[0, 1], [1]], [[1, 0], [1]], [[1, 1], [0]]]
for x in train:
print(x)
nn.backPropagation(train, 0.5, 2, 3, 1)
print(nn.evaluate([0, 0]))
print(nn.evaluate([0, 1]))
print(nn.evaluate([1, 0]))
print(nn.evaluate([1, 1]))
from nn import NN
nn = NN()
train = [[[0, 0], [0]], [[0, 1], [1]], [[1, 0], [1]], [[1, 1], [0]]]
for x in train:
print(x)
nn.backPropagation(train, 0.5, 2, 3, 1)
print(nn.evaluate([0, 0]))
print(nn.evaluate([0, 1]))
print(nn.evaluate([1, 0]))
print(nn.evaluate([1, 1]))
