CODEWITHSUNDEEP
neural-networkdeep-learningcomputer-visionconv-neural-networkpytorch
blue-sky
blue-sky

Reputation: 53796

Making a prediction from a trained convolution network

Here is my convolution net that creates training data , then trains on this data using a single convolution with relu activation : 

train_dataset = []
mu, sigma = 0, 0.1 # mean and standard deviation
num_instances = 10

for i in range(num_instances) :
    image = []
    image_x = np.random.normal(mu, sigma, 1000).reshape((1 , 100, 10))
    train_dataset.append(image_x)

mu, sigma = 100, 0.80 # mean and standard deviation
for i in range(num_instances) :
    image = []
    image_x = np.random.normal(mu, sigma, 1000).reshape((1 , 100, 10))
    train_dataset.append(image_x)

labels_1 = [1 for i in range(num_instances)]
labels_0 = [0 for i in range(num_instances)]

labels = labels_1 + labels_0

print(labels)

x2 = torch.tensor(train_dataset).float()
y2 = torch.tensor(labels).long()

my_train2 = data_utils.TensorDataset(x2, y2)
train_loader2 = data_utils.DataLoader(my_train2, batch_size=batch_size_value, shuffle=False)


import torch 
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms


# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# device = 'cpu'

# Hyper parameters
num_epochs = 50
num_classes = 2
batch_size = 5
learning_rate = 0.001

# Convolutional neural network (two convolutional layers)
class ConvNet(nn.Module):
    def __init__(self, num_classes=1):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(32*25*2, num_classes)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

model = ConvNet(num_classes).to(device)

# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)

# Train the model
total_step = len(train_loader2)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader2):
        images = images.to(device)
        labels = labels.to(device)

        # Forward pass
        outputs = model(images)
        loss = criterion(outputs, labels)

        # Backward and optimize
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if (i % 10) == 0:
            print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}' 
                   .format(epoch+1, num_epochs, i+1, total_step, loss.item()))

To make a single prediction I use :

model(x2[10].unsqueeze_(0).cuda())

Which outputs : 

tensor([[ 4.4880, -4.3128]], device='cuda:0')

Should this not return an image tensor of shape (100,10) of the prediction ?

Update : In order to perform a prediction I use :

torch.argmax(model(x2[2].unsqueeze_(0).cuda()), dim=1)

src : https://discuss.pytorch.org/t/argmax-with-pytorch/1528/11

torch.argmax in this context returns the position of the value that maximises the prediction.

Upvotes: 1

Views: 169

Answers (1)

Shai
Shai

Reputation: 114786

As noted by Koustav your net is not "fully convolutional": although you have two nn.Conv2d layers, you still have a "fully-connected" (aka nn.Linear) layer on top, which outputs only 2 dimensional (num_classes) output tensor.

More specifically, your net expects a 1x100x10 input (single channel, 100 by 10 pixels image).
After self.layer1 you have a 16x50x5 tensor (16 channels from the convolution, spatial dimensions reduced by max pooling layer).
After self.layer2 you have a 32x25x2 tensor (32 channels from the convolution, spatial dimensions reduced by another max pooling layer).
Finally, your fully connected self.fc nn.Linear layer takes the entire 32*25*2 dimensional input tensor and produces a num_classes output from the entire input.

Upvotes: 1

Related Questions