train_net.py

import h5py
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torch.utils.data as data
import sys

class H5Dataset(data.Dataset):
    def __init__(self, file_path):
        super(H5Dataset, self).__init__()
        h5_file = h5py.File(file_path)
        self.data = h5_file.get('images')
        self.target = h5_file.get('labels')

    def __getitem__(self, index):
        data = self.data[index,:,:].astype('float32')
        # ptorch uses NCHW format
        data = data.reshape((data.shape[2], data.shape[0], data.shape[1]))
        target = self.target[index,:].astype('int32')[0]
        return (data, target)

    def __len__(self):
        return self.data.shape[0]

class Net(nn.Module):
    def __init__(self, input_channels):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(input_channels, 20, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(20, 50, 5)
        self.fc1 = nn.Linear(50 * 12 * 12, 500)
        self.fc2 = nn.Linear(500, 2)
        # self.fc2 = nn.Linear(120, 84)
        # self.fc3 = nn.Linear(84, 2)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 50 * x.shape[2] * x.shape[3])
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        # x = F.relu(self.fc2(x))
        # x = self.fc3(x)
        return x

# Load the training data.
dset = H5Dataset(sys.argv[1])
train_loader = data.DataLoader(dset, batch_size=64, shuffle=True)

# Create the network.
input_channels = int(sys.argv[3])
net = Net(input_channels)
print net

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(device)
net.to(device)

# Define the loss function and optimizer.
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.00001, momentum=0.9)

num_epochs = 1

for epoch in range(num_epochs):  # loop over the dataset multiple times
    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):
        # get the inputs
        inputs, labels = data
        inputs, labels = inputs.to(device), labels.to(device)

        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels.long())
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 10 == 9: # print every 10 mini-batches
            print('[%d, %5d] loss: %.5f' %
                  (epoch + 1, i + 1, running_loss / 10))
            running_loss = 0.0

print('Finished Training')

# Test the network on the test data.
test_set = H5Dataset(sys.argv[2])
test_loader = data.DataLoader(test_set, batch_size=64, shuffle=True)
correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (
    100 * correct / total))