def train(net, train_set, NUM_EPOCHS):
print("Started training")
net = Autoencoder()
criterion = nn.MSELoss()
train_loss = []
optimizer = optim.Adam(net.parameters(), lr=LEARNING_RATE)
if torch.cuda.is_available():
net = net.cuda()
criterion = criterion.cuda()
for epoch in range(NUM_EPOCHS):
running_loss = 0.0
for i, data in enumerate(train_set, 0):
img = data.get("image")
img = img.cuda()
img = img.view(img.size(0), -1)
optimizer.zero_grad()
outputs = net(img)
loss = criterion(outputs, img)
loss.backward()
optimizer.step()
running_loss += loss.item()
loss = running_loss / len(train_set)
train_loss.append(loss)
train_loss.append(loss)
print('Epoch {} of {}, Train Loss: {:.3f}'.format(
epoch + 1, NUM_EPOCHS, loss))
#if epoch % 5 == 0:
#save_decoded_image(outputs.cpu().data, epoch)
print("Finished training")
return train_loss
import matplotlib.pyplot as plt
import torch.nn.functional as F
from torchvision import datasets
from torch.utils.data import DataLoader
from torchvision.utils import save_image
from autoencoder import Autoencoder
from VRUDataset import VRUDataset
NUM_EPOCHS = 3
LEARNING_RATE = 1e-3
BATCH_SIZE = 32
net = Autoencoder()
if torch.cuda.is_available():
net = net.cuda()
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, ), (0.5, ))])
train_set = VRUDataset(
transform=transform,
json_path=
"C:\\Users\\shubh\\OneDrive\\Desktop\\ENTR 390\\Code\\project-pineapple\\train.json",
data_path="C:\\Users\\shubh\\OneDrive\\Desktop\\ENTR 390\\Dataset\\Train")
val_set = VRUDataset(
transform=transform,
json_path=
"C:\\Users\\shubh\\OneDrive\\Desktop\\ENTR 390\\Code\\project-pineapple\\val.json",
data_path="C:\\Users\\shubh\\OneDrive\\Desktop\\ENTR 390\\Dataset\\Val")
train_set = DataLoader(train_set, shuffle=True, batch_size=BATCH_SIZE)
val_set = DataLoader(val_set, shuffle=True, batch_size=BATCH_SIZE)
class Net(BaseNet):
def __init__(self,
name,
input_dim,
output_dim,
n_hid,
n_bottleneck=None,
lr=1e-4,
weight_decay=0,
cuda=True):
super(Net, self).__init__()
cprint('c', '\nNet:')
self.name = name
self.input_dim = input_dim
self.output_dim = output_dim
self.n_bottleneck = n_bottleneck
self.n_hid = n_hid
self.cuda = cuda
self.create_net()
self.create_opt(lr, weight_decay)
def create_net(self):
if self.name == 'feed_forward':
self.model = feed_forward(self.input_dim, self.output_dim,
self.n_hid)
self.J = nn.MSELoss(size_average=True, reduce=True)
elif self.name == 'autoencoder':
self.model = Autoencoder(self.input_dim, self.output_dim,
self.n_hid, self.n_bottleneck)
self.J = nn.MSELoss(size_average=True, reduce=True)
elif self.name == 'ff_mlpg':
self.model = ff_mlpg(self.input_dim, self.output_dim, self.n_hid)
self.J = Nloss_GD(self.input_dim)
else:
pass
if self.cuda:
self.model = self.model.cuda()
self.J = self.J.cuda()
print(' Total params: %.2fM' %
(sum(p.numel() for p in self.model.parameters()) / 1000000.0))
def create_opt(self, lr=1e-4, weight_decay=0):
self.lr = lr
self.weight_decay = weight_decay
self.optimizer = torch.optim.Adam(self.model.parameters(),
lr=self.lr,
weight_decay=self.weight_decay)
self.schedule = None # [-1] #[50,200,400,600]
def fit(self, x, y):
x, y = to_variable(var=(x, y), volatile=False, cuda=self.cuda)
self.optimizer.zero_grad()
if self.name == 'ff_mlpg':
out, sq_Beta = self.model(x)
loss = self.J(out, y, sq_Beta)
loss.backward()
self.optimizer.step()
return loss.data[0], sq_Beta.abs().mean().data
elif self.name == 'feed_forward':
out = self.model(x)
loss = self.J(out, y)
else:
out = self.model(x)
loss = self.J(out, y)
loss.backward()
self.optimizer.step()
return loss.data[0]
def eval(self, x, y, train=False):
with torch.no_grad():
x, y = to_variable(var=(x, y), volatile=True, cuda=self.cuda)
if self.name == 'ff_mlpg':
out, sq_Beta = self.model(x)
loss = self.J(out, y, sq_Beta)
return loss.data[0], sq_Beta.abs().mean().data
elif self.name == 'feed_forward':
out = self.model(x)
loss = self.J(out, y)
else:
out = self.model(x)
loss = self.J(out, y)
return loss.data[0]
def predict(self, x, train=False):
with torch.no_grad():
x, = to_variable(var=(x, ), volatile=False, cuda=self.cuda)
if self.name == 'ff_mlpg':
out, sq_Beta = self.model(x)
return out.data, sq_Beta.abs().data
else:
out = self.model(x)
return out.data