Hello everyone! This is my first post. What brought me here was my curiosity with experimenting with neural networks, but all other modules are very limiting (keras, theano, etc).
I came across pytorch and noticed that it’s good for experiments. I wanted to know how I could make a custom Dropout function that, when given the weights of a layer, It produces a vector of masks and it then applies the mask during forward propagation. I have some code with me, I really hope any of y’all could help me! THANKS
import torch
import torch.nn as nn
import torchvision.datasets as dsets
import torchvision.transforms as transforms
from torch.autograd import Variable
import torch.nn.functional as F
# Hyper Parameters
input_size = 784
hidden_size = 500
num_classes = 10
num_epochs = 5
batch_size = 100
learning_rate = 0.001
# MNIST Dataset
train_dataset = dsets.MNIST(root='./data',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = dsets.MNIST(root='./data',
train=False,
transform=transforms.ToTensor())
# Data Loader (Input Pipeline)
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
class Dropout(nn.Module):
def __init__(self, p=0.5, inplace=False):
super(Dropout, self).__init__()
if p < 0 or p > 1:
raise ValueError("dropout probability has to be between 0 and 1, "
"but got {}".format(p))
self.p = p
self.inplace = inplace
def forward(self, input):
return F.dropout(input, self.p, self.training, self.inplace)
def __repr__(self):
inplace_str = ', inplace' if self.inplace else ''
return self.__class__.__name__ + '(' \
+ 'p=' + str(self.p) \
+ inplace_str + ')'
# Neural Network Model (1 hidden layer)
class Net(nn.Module):
def __init__(self, input_size, hidden_size, num_classes):
super(Net, self).__init__()
self.fc1 = nn.Linear(input_size, hidden_size)
self.relu = nn.ReLU()
self.dropout = Dropout(0.2)
self.fc2 = nn.Linear(hidden_size, num_classes)
def forward(self, x):
out = self.fc1(x)
out = self.relu(out)
out = self.dropout(out)
out = self.fc2(out)
return out
net = Net(input_size, hidden_size, num_classes)
# Loss and Optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(net.parameters(), lr=learning_rate)
# Train the Model
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
# Convert torch tensor to Variable
images = Variable(images.view(-1, 28*28))
labels = Variable(labels)
# Forward + Backward + Optimize
optimizer.zero_grad() # zero the gradient buffer
outputs = net(images)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print ('Epoch [%d/%d], Step [%d/%d], Loss: %.4f'
%(epoch+1, num_epochs, i+1, len(train_dataset)//batch_size, loss.data[0]))
# Test the Model
correct = 0
total = 0
for images, labels in test_loader:
images = Variable(images.view(-1, 28*28))
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum()
print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))
# Save the Model
torch.save(net.state_dict(), 'model.pkl')