-
Notifications
You must be signed in to change notification settings - Fork 0
/
main.py
87 lines (76 loc) · 3.8 KB
/
main.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# Training settings
parser = argparse.ArgumentParser(description='PyTorch GTSRB example')
parser.add_argument('--data', type=str, default='data', metavar='D',
help="folder where data is located. train_data.zip and test_data.zip need to be found in the folder")
parser.add_argument('--batch-size', type=int, default=64, metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument('--epochs', type=int, default=10, metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
help='learning rate (default: 0.001)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
help='SGD momentum (default: 0.5)')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
help='how many batches to wait before logging training status')
args = parser.parse_args()
torch.manual_seed(args.seed)
### Data Initialization and Loading
from data import initialize_data, data_transforms # data.py in the same folder
initialize_data(args.data) # extracts the zip files, makes a validation set
train_loader = torch.utils.data.DataLoader(
datasets.ImageFolder(args.data + '/train_images',
transform=data_transforms),
batch_size=args.batch_size, shuffle=True, num_workers=1)
val_loader = torch.utils.data.DataLoader(
datasets.ImageFolder(args.data + '/val_images',
transform=data_transforms),
batch_size=args.batch_size, shuffle=False, num_workers=1)
### Neural Network and Optimizer
# We define neural net in model.py so that it can be reused by the evaluate.py script
from model import model, optimizer
model.to(device)
def train(epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
def validation():
model.eval()
validation_loss = 0
correct = 0
with torch.no_grad():
for data, target in val_loader:
data, target = data.to(device), target.to(device)
output = model(data)
validation_loss += F.nll_loss(output, target, reduction='sum').item() # sum up batch loss
pred = output.data.max(1, keepdim=True)[1] # get the index of the max log-probability
correct += pred.eq(target.data.view_as(pred)).to(device).sum()
validation_loss /= len(val_loader.dataset)
print('\nValidation set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
validation_loss, correct, len(val_loader.dataset),
100. * correct / len(val_loader.dataset)))
for epoch in range(1, args.epochs + 1):
train(epoch)
validation()
model_file = 'model_' + str(epoch) + '.pth'
torch.save(model.state_dict(), model_file)
print('\nSaved model to ' + model_file + '. You can run `python evaluate.py --model ' + model_file + '` to generate the Kaggle formatted csv file')