In [1]:

    

HOST = "app.verta.ai"

PROJECT_NAME = "MNIST Multiclassification"
EXPERIMENT_NAME = "ConvNet"


    

In [2]:

    

# import os
# os.environ['VERTA_EMAIL'] = 
# os.environ['VERTA_DEV_KEY'] =


    

In [3]:

    

from verta import Client

client = Client(HOST)
proj = client.set_project(PROJECT_NAME)
expt = client.set_experiment(EXPERIMENT_NAME)


    

In [4]:

    

from __future__ import print_function

import itertools

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.optim.lr_scheduler import StepLR


    

In [5]:

    

# Training settings
batch_size = 256
test_batch_size = 1000
epochs = 1
lr = 1.0
gamma = 0.7
seed = 1
save_model = False
use_cuda = torch.cuda.is_available()


    

In [6]:

    

torch.manual_seed(seed)

device = torch.device("cuda" if use_cuda else "cpu")

kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=True, download=True,
                   transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))
                   ])),
    batch_size=batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('../data', train=False, transform=transforms.Compose([
                       transforms.ToTensor(),
                       transforms.Normalize((0.1307,), (0.3081,))
                   ])),
    batch_size=test_batch_size, shuffle=True, **kwargs)


    

In [7]:

    

class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout2d(0.25)
        self.dropout2 = nn.Dropout2d(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output

model = Net().to(device)


    

In [8]:

    

def train(model, device, train_loader, optimizer, 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 % 10 == 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()))


    

In [9]:

    

def test(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, reduction='sum').item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)

    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


    

In [10]:

    

from verta.integrations.torch import verta_hook


run = client.set_experiment_run()
model.register_forward_hook(verta_hook(run))


    

In [11]:

    

optimizer = optim.Adadelta(model.parameters(), lr=lr)

scheduler = StepLR(optimizer, step_size=1, gamma=gamma)
for epoch in range(1, epochs + 1):
    train(model, device, train_loader, optimizer, epoch)
    test(model, device, test_loader)
    scheduler.step()

if save_model:
    torch.save(model.state_dict(), "mnist_cnn.pt")


    

In [12]:

    

run