def test_net(test_loader=None, path='model.pt', batch_size=128, fname=None):
n_batches = len(test_loader)
model = torch.load(path)
net = model['model']
net.load_state_dict(model['state_dict'])
for par in net.parameters():
par.requires_grad = False
net.eval()
net = net.float()
net = net.to('cuda')
#writing results to spreadsheet
if fname is None:
fname = 'test_pred.csv'
f_out = open(fname, "w")
wrt = csv.writer(f_out)
#testing metrics
corr_cnt = 0
total_iter = 0
for data in test_loader:
[inputs, labels, snr] = data
inputs, labels = Variable(inputs).to('cuda'), Variable(labels)
pred = net(inputs.float())
snr = snr.numpy()
pred = np.argmax(pred.cpu(), axis=1).numpy()
labels = np.argmax(labels.numpy(), axis=1)
for s, p, l in zip(snr, pred, labels):
#wrt.writerow([s,p,l])
if (p == l):
corr_cnt += 1
total_iter += 1
print("Test done, accr = :" + str(corr_cnt / total_iter))
f_out.close()
def train_net(train_loader=None,
net=None,
batch_size=128,
n_epochs=5,
learning_rate=0.001,
saved_model=None,
fname=None):
#Print all of the hyperparameters of the training iteration:
print("===== HYPERPARAMETERS =====")
print("batch_size=", batch_size)
print("epochs=", n_epochs)
print("learning_rate=", learning_rate)
print("=" * 30)
#Get training and test data
n_batches = len(train_loader)
#Create our loss and optimizer functions
loss, optimizer = get_loss_optimizer(net, learning_rate)
#Time for printing
training_start_time = time.time()
f_out = open(fname, "w")
wrt = csv.writer(f_out)
total_train_loss = 0
scheduler = StepLR(optimizer, step_size=250, gamma=0.1)
net = net.float()
net = net.to('cuda')
#Loop for n_epochs
for epoch in range(n_epochs):
running_loss = 0.0
print_every = n_batches // 10
start_time = time.time()
wrt.writerow([epoch, total_train_loss])
total_train_loss = 0
if (((epoch + 1) % 250) == 0):
checkpoint = {
'model': net,
'state_dict': net.state_dict(),
'optimizer': optimizer.state_dict()
}
file_name = 'checkpoint.pt'
torch.save(checkpoint, file_name)
i = 0
for data in train_loader:
[inputs, labels, snr] = data
#print(inputs.shape)
#Wrap them in a Variable object
inputs, labels, snr = Variable(inputs).to('cuda'), Variable(
labels).to('cuda'), Variable(snr).to('cuda')
#inputs,labels,snr = Variable(inputs), Variable(labels), Variable(snr)
#Set the parameter gradients to zero
optimizer.zero_grad()
#Forward pass, backward pass, optimize
outputs = net(inputs.float())
labels = labels.squeeze_().cpu()
loss_size = loss(outputs.cpu(), np.argmax(labels, axis=1))
#loss_size = loss(outputs, np.argmax(labels,axis=1))
loss_size.backward()
optimizer.step()
#Print statistics
running_loss += loss_size.data
total_train_loss += loss_size.data
#Print loss from every 10% (then resets to 0) of a batch of an epoch
if (i + 1) % (print_every + 1) == 0:
print("Epoch {}, {:d}% \t train_loss: {:.4f} took: {:.2f}s".
format(epoch + 1, int(100 * (i + 1) / n_batches),
total_train_loss / print_every,
time.time() - start_time))
#Reset running loss and time
running_loss = 0.0
start_time = time.time()
i += 1
scheduler.step()
print("Training finished, took {:.2f}s".format(time.time() -
training_start_time))
final = {
'model': net,
'state_dict': net.state_dict(),
'optimizer': optimizer.state_dict()
}
torch.save(final, saved_model)
f_out.close()
def test_net(test_loader=None,
path='model.pt',
batch_size=128,
fname=None,
a=8,
b=12,
c=20):
n_batches = len(test_loader)
model = torch.load(path)
net = model['model']
net.load_state_dict(model['state_dict'])
for par in net.parameters():
par.requires_grad = False
net.eval()
net = net.float()
net = net.to('cuda')
#writing results to spreadsheet
if fname is None:
fname = 'test_pred.csv'
f_out = open(fname, "w")
wrt = csv.writer(f_out)
#testing metrics
corr_cnt = 0
total_iter = 0
run_max = 0
for i in range(20, 30):
for j in range(40, 60):
for k in range(70, 80):
for data in test_loader:
[inputs, labels, snr] = data
inputs, labels = Variable(inputs).to('cuda'), Variable(
labels)
pred = net(inputs.float())
snr = snr.numpy()
pred = pred.cpu().numpy()
labels = np.argmax(labels.numpy(), axis=1)
for s, p, l in zip(snr, pred, labels):
#wrt.writerow([s,p,l])
#wrt.writerow([p,l])
#p = bisect.bisect_left([0.25,0.5,0.75],p)
p = bisect.bisect_left(
[float(i / 100),
float(j / 100),
float(k / 100)], p)
if (p == l):
corr_cnt += 1
total_iter += 1
acc = corr_cnt / total_iter
if (run_max < acc):
run_max = acc
print("Test done, accr = :" + str(acc))
#print("i" + str(float(i/100)))
#print("j" + str(float(j/100)))
#print("k" + str(float(k/100)))
wrt.writerow([i, j, k, acc])
print(run_max)
f_out.close()
import pandas as pd
import numpy as np
from sklearn.preprocessing import MinMaxScaler
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
#Load the data
data = pd.read_csv('../data/data.csv')
relevent_data = data.drop('code_size', axis=1)
test_app = 'consumer_tiffmedian'
from net import net
losses = []
net = net.to(device)
net.train()
def train_test_split(test_app):
train_data = relevent_data[relevent_data['APP_NAME'] != test_app]
test_data = relevent_data[relevent_data['APP_NAME'] == test_app]
scaler = MinMaxScaler(feature_range=(0, 1)).fit(
relevent_data[relevent_data['APP_NAME'] != test_app].iloc[:, 1:-5])
scaled_train_predictors = scaler.transform(
relevent_data[relevent_data['APP_NAME'] != test_app].iloc[:, 1:-5])
train_targets = relevent_data[
relevent_data['APP_NAME'] != test_app].iloc[:, -5:]
scaled_train_targets = []
for app in range(0, train_targets.shape[0], 128):
scaled_train_targets.append(
