torch to numpy

import torch

set seed

torch.manual_seed(7) 

generate one row, 5 col

torch.randn((1, 5))

numpy to tensor

import numpy as np
a = np.random.rand(4,3)
torch.from_numpy(a)

torch to numpy

t = torch.randn((1, 5))
t.numpy()

Building a Fully Connected Network

from torchvision import datasets, transforms

# Define a transform to normalize the data
transform = transforms.Compose([transforms.ToTensor(),
                              transforms.Normalize((0.5,), (0.5,)),
                              ])

# Download and load the training data
trainset = datasets.MNIST('~/.pytorch/MNIST_data/', download=True, train=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64, shuffle=True)

from collections import OrderedDict
model = nn.Sequential(OrderedDict([
                      ('fc1', nn.Linear(input_size, hidden_sizes[0])),
                      ('relu1', nn.ReLU()),
                      ('fc2', nn.Linear(hidden_sizes[0], hidden_sizes[1])),
                      ('relu2', nn.ReLU()),
                      ('output', nn.Linear(hidden_sizes[1], output_size)),
                      ('softmax', nn.LogSoftmax(dim=1))]))
criterion = nn.NLLLoss()
optimizer = optim.SGD(model.parameters(), lr=0.003)

epochs = 5
for e in range(epochs):
    running_loss = 0
    for images, labels in trainloader:
        # Flatten MNIST images into a 784 long vector
        images = images.view(./images.shape[0], -1)
    
        # TODO: Training pass
        optimizer.zero_grad()
        
        output = model(./images)
        loss = criterion(output, labels)
        loss.backward()
        optimizer.step()
        
        running_loss += loss.item()
    else:
        print(f"Training loss: {running_loss/len(trainloader)}")

img = images[0].view(1, 784)
# Turn off gradients to speed up this part
with torch.no_grad():
    logps = model(img)

# Output of the network are log-probabilities, need to take exponential for probabilities
ps = torch.exp(logps)