Deep Learning Models -- A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks.
%load_ext watermark
%watermark -a 'Sebastian Raschka' -v -p torch
Sebastian Raschka CPython 3.6.8 IPython 7.2.0 torch 1.0.0
import time
import numpy as np
from torchvision import datasets
from torchvision import transforms
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch
if torch.cuda.is_available():
torch.backends.cudnn.deterministic = True
##########################
### SETTINGS
##########################
# Device
device = torch.device("cuda:3" if torch.cuda.is_available() else "cpu")
# Hyperparameters
random_seed = 1
learning_rate = 0.1
num_epochs = 10
batch_size = 64
# Architecture
num_features = 784
num_hidden_1 = 128
num_hidden_2 = 256
num_classes = 10
##########################
### MNIST DATASET
##########################
# Note transforms.ToTensor() scales input images
# to 0-1 range
train_dataset = datasets.MNIST(root='data',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = datasets.MNIST(root='data',
train=False,
transform=transforms.ToTensor())
train_loader = DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
# Checking the dataset
for images, labels in train_loader:
print('Image batch dimensions:', images.shape)
print('Image label dimensions:', labels.shape)
break
Image batch dimensions: torch.Size([64, 1, 28, 28]) Image label dimensions: torch.Size([64])
##########################
### MODEL
##########################
class MultilayerPerceptron(torch.nn.Module):
def __init__(self, num_features, num_classes):
super(MultilayerPerceptron, self).__init__()
### 1st hidden layer
self.linear_1 = torch.nn.Linear(num_features, num_hidden_1)
# The following two lines are not necessary,
# but used here to demonstrate how to access the weights
# and use a different weight initialization.
# By default, PyTorch uses Xavier/Glorot initialization, which
# should usually be preferred.
self.linear_1.weight.detach().normal_(0.0, 0.1)
self.linear_1.bias.detach().zero_()
### 2nd hidden layer
self.linear_2 = torch.nn.Linear(num_hidden_1, num_hidden_2)
self.linear_2.weight.detach().normal_(0.0, 0.1)
self.linear_2.bias.detach().zero_()
### Output layer
self.linear_out = torch.nn.Linear(num_hidden_2, num_classes)
self.linear_out.weight.detach().normal_(0.0, 0.1)
self.linear_out.bias.detach().zero_()
def forward(self, x):
out = self.linear_1(x)
out = F.relu(out)
out = self.linear_2(out)
out = F.relu(out)
logits = self.linear_out(out)
probas = F.log_softmax(logits, dim=1)
return logits, probas
torch.manual_seed(random_seed)
model = MultilayerPerceptron(num_features=num_features,
num_classes=num_classes)
model = model.to(device)
optimizer = torch.optim.SGD(model.parameters(), lr=learning_rate)
def compute_accuracy(net, data_loader):
net.eval()
correct_pred, num_examples = 0, 0
with torch.no_grad():
for features, targets in data_loader:
features = features.view(-1, 28*28).to(device)
targets = targets.to(device)
logits, probas = net(features)
_, predicted_labels = torch.max(probas, 1)
num_examples += targets.size(0)
correct_pred += (predicted_labels == targets).sum()
return correct_pred.float()/num_examples * 100
start_time = time.time()
for epoch in range(num_epochs):
model.train()
for batch_idx, (features, targets) in enumerate(train_loader):
features = features.view(-1, 28*28).to(device)
targets = targets.to(device)
### FORWARD AND BACK PROP
logits, probas = model(features)
cost = F.cross_entropy(logits, targets)
optimizer.zero_grad()
cost.backward()
### UPDATE MODEL PARAMETERS
optimizer.step()
### LOGGING
if not batch_idx % 50:
print ('Epoch: %03d/%03d | Batch %03d/%03d | Cost: %.4f'
%(epoch+1, num_epochs, batch_idx,
len(train_loader), cost))
with torch.set_grad_enabled(False):
print('Epoch: %03d/%03d training accuracy: %.2f%%' % (
epoch+1, num_epochs,
compute_accuracy(model, train_loader)))
print('Time elapsed: %.2f min' % ((time.time() - start_time)/60))
print('Total Training Time: %.2f min' % ((time.time() - start_time)/60))
Epoch: 001/010 | Batch 000/938 | Cost: 2.4231 Epoch: 001/010 | Batch 050/938 | Cost: 0.7213 Epoch: 001/010 | Batch 100/938 | Cost: 0.3137 Epoch: 001/010 | Batch 150/938 | Cost: 0.4774 Epoch: 001/010 | Batch 200/938 | Cost: 0.3311 Epoch: 001/010 | Batch 250/938 | Cost: 0.3082 Epoch: 001/010 | Batch 300/938 | Cost: 0.3940 Epoch: 001/010 | Batch 350/938 | Cost: 0.2292 Epoch: 001/010 | Batch 400/938 | Cost: 0.0837 Epoch: 001/010 | Batch 450/938 | Cost: 0.2238 Epoch: 001/010 | Batch 500/938 | Cost: 0.2501 Epoch: 001/010 | Batch 550/938 | Cost: 0.1543 Epoch: 001/010 | Batch 600/938 | Cost: 0.2353 Epoch: 001/010 | Batch 650/938 | Cost: 0.4138 Epoch: 001/010 | Batch 700/938 | Cost: 0.2955 Epoch: 001/010 | Batch 750/938 | Cost: 0.3486 Epoch: 001/010 | Batch 800/938 | Cost: 0.1391 Epoch: 001/010 | Batch 850/938 | Cost: 0.0675 Epoch: 001/010 | Batch 900/938 | Cost: 0.2827 Epoch: 001/010 training accuracy: 94.90% Time elapsed: 0.22 min Epoch: 002/010 | Batch 000/938 | Cost: 0.3237 Epoch: 002/010 | Batch 050/938 | Cost: 0.2792 Epoch: 002/010 | Batch 100/938 | Cost: 0.0915 Epoch: 002/010 | Batch 150/938 | Cost: 0.2269 Epoch: 002/010 | Batch 200/938 | Cost: 0.2248 Epoch: 002/010 | Batch 250/938 | Cost: 0.1607 Epoch: 002/010 | Batch 300/938 | Cost: 0.0551 Epoch: 002/010 | Batch 350/938 | Cost: 0.2369 Epoch: 002/010 | Batch 400/938 | Cost: 0.0538 Epoch: 002/010 | Batch 450/938 | Cost: 0.0951 Epoch: 002/010 | Batch 500/938 | Cost: 0.2423 Epoch: 002/010 | Batch 550/938 | Cost: 0.2082 Epoch: 002/010 | Batch 600/938 | Cost: 0.1623 Epoch: 002/010 | Batch 650/938 | Cost: 0.1743 Epoch: 002/010 | Batch 700/938 | Cost: 0.1987 Epoch: 002/010 | Batch 750/938 | Cost: 0.0871 Epoch: 002/010 | Batch 800/938 | Cost: 0.1662 Epoch: 002/010 | Batch 850/938 | Cost: 0.1087 Epoch: 002/010 | Batch 900/938 | Cost: 0.1574 Epoch: 002/010 training accuracy: 96.62% Time elapsed: 0.45 min Epoch: 003/010 | Batch 000/938 | Cost: 0.1088 Epoch: 003/010 | Batch 050/938 | Cost: 0.0994 Epoch: 003/010 | Batch 100/938 | Cost: 0.0771 Epoch: 003/010 | Batch 150/938 | Cost: 0.1926 Epoch: 003/010 | Batch 200/938 | Cost: 0.1231 Epoch: 003/010 | Batch 250/938 | Cost: 0.2532 Epoch: 003/010 | Batch 300/938 | Cost: 0.0637 Epoch: 003/010 | Batch 350/938 | Cost: 0.1193 Epoch: 003/010 | Batch 400/938 | Cost: 0.0839 Epoch: 003/010 | Batch 450/938 | Cost: 0.0830 Epoch: 003/010 | Batch 500/938 | Cost: 0.0689 Epoch: 003/010 | Batch 550/938 | Cost: 0.0504 Epoch: 003/010 | Batch 600/938 | Cost: 0.1999 Epoch: 003/010 | Batch 650/938 | Cost: 0.1190 Epoch: 003/010 | Batch 700/938 | Cost: 0.2022 Epoch: 003/010 | Batch 750/938 | Cost: 0.0598 Epoch: 003/010 | Batch 800/938 | Cost: 0.0216 Epoch: 003/010 | Batch 850/938 | Cost: 0.0174 Epoch: 003/010 | Batch 900/938 | Cost: 0.0660 Epoch: 003/010 training accuracy: 97.70% Time elapsed: 0.67 min Epoch: 004/010 | Batch 000/938 | Cost: 0.0067 Epoch: 004/010 | Batch 050/938 | Cost: 0.0344 Epoch: 004/010 | Batch 100/938 | Cost: 0.1624 Epoch: 004/010 | Batch 150/938 | Cost: 0.0572 Epoch: 004/010 | Batch 200/938 | Cost: 0.0306 Epoch: 004/010 | Batch 250/938 | Cost: 0.1564 Epoch: 004/010 | Batch 300/938 | Cost: 0.2233 Epoch: 004/010 | Batch 350/938 | Cost: 0.0229 Epoch: 004/010 | Batch 400/938 | Cost: 0.1174 Epoch: 004/010 | Batch 450/938 | Cost: 0.1853 Epoch: 004/010 | Batch 500/938 | Cost: 0.1418 Epoch: 004/010 | Batch 550/938 | Cost: 0.1071 Epoch: 004/010 | Batch 600/938 | Cost: 0.0354 Epoch: 004/010 | Batch 650/938 | Cost: 0.0487 Epoch: 004/010 | Batch 700/938 | Cost: 0.1886 Epoch: 004/010 | Batch 750/938 | Cost: 0.1568 Epoch: 004/010 | Batch 800/938 | Cost: 0.0702 Epoch: 004/010 | Batch 850/938 | Cost: 0.0533 Epoch: 004/010 | Batch 900/938 | Cost: 0.1500 Epoch: 004/010 training accuracy: 98.01% Time elapsed: 0.89 min Epoch: 005/010 | Batch 000/938 | Cost: 0.0225 Epoch: 005/010 | Batch 050/938 | Cost: 0.0168 Epoch: 005/010 | Batch 100/938 | Cost: 0.1133 Epoch: 005/010 | Batch 150/938 | Cost: 0.0691 Epoch: 005/010 | Batch 200/938 | Cost: 0.0413 Epoch: 005/010 | Batch 250/938 | Cost: 0.0840 Epoch: 005/010 | Batch 300/938 | Cost: 0.0697 Epoch: 005/010 | Batch 350/938 | Cost: 0.0901 Epoch: 005/010 | Batch 400/938 | Cost: 0.0370 Epoch: 005/010 | Batch 450/938 | Cost: 0.0514 Epoch: 005/010 | Batch 500/938 | Cost: 0.1403 Epoch: 005/010 | Batch 550/938 | Cost: 0.1164 Epoch: 005/010 | Batch 600/938 | Cost: 0.0624 Epoch: 005/010 | Batch 650/938 | Cost: 0.0280 Epoch: 005/010 | Batch 700/938 | Cost: 0.0555 Epoch: 005/010 | Batch 750/938 | Cost: 0.0432 Epoch: 005/010 | Batch 800/938 | Cost: 0.0434 Epoch: 005/010 | Batch 850/938 | Cost: 0.1074 Epoch: 005/010 | Batch 900/938 | Cost: 0.0353 Epoch: 005/010 training accuracy: 98.56% Time elapsed: 1.12 min Epoch: 006/010 | Batch 000/938 | Cost: 0.1073 Epoch: 006/010 | Batch 050/938 | Cost: 0.0901 Epoch: 006/010 | Batch 100/938 | Cost: 0.0736 Epoch: 006/010 | Batch 150/938 | Cost: 0.0290 Epoch: 006/010 | Batch 200/938 | Cost: 0.0399 Epoch: 006/010 | Batch 250/938 | Cost: 0.0720 Epoch: 006/010 | Batch 300/938 | Cost: 0.0863 Epoch: 006/010 | Batch 350/938 | Cost: 0.0629 Epoch: 006/010 | Batch 400/938 | Cost: 0.1095 Epoch: 006/010 | Batch 450/938 | Cost: 0.0531 Epoch: 006/010 | Batch 500/938 | Cost: 0.0680 Epoch: 006/010 | Batch 550/938 | Cost: 0.1777 Epoch: 006/010 | Batch 600/938 | Cost: 0.0525 Epoch: 006/010 | Batch 650/938 | Cost: 0.0364 Epoch: 006/010 | Batch 700/938 | Cost: 0.0836 Epoch: 006/010 | Batch 750/938 | Cost: 0.1251 Epoch: 006/010 | Batch 800/938 | Cost: 0.0638 Epoch: 006/010 | Batch 850/938 | Cost: 0.0725 Epoch: 006/010 | Batch 900/938 | Cost: 0.1785 Epoch: 006/010 training accuracy: 98.88% Time elapsed: 1.34 min Epoch: 007/010 | Batch 000/938 | Cost: 0.0043 Epoch: 007/010 | Batch 050/938 | Cost: 0.0928 Epoch: 007/010 | Batch 100/938 | Cost: 0.0375 Epoch: 007/010 | Batch 150/938 | Cost: 0.1094 Epoch: 007/010 | Batch 200/938 | Cost: 0.0237 Epoch: 007/010 | Batch 250/938 | Cost: 0.0398 Epoch: 007/010 | Batch 300/938 | Cost: 0.0592 Epoch: 007/010 | Batch 350/938 | Cost: 0.0340 Epoch: 007/010 | Batch 400/938 | Cost: 0.0255 Epoch: 007/010 | Batch 450/938 | Cost: 0.0472 Epoch: 007/010 | Batch 500/938 | Cost: 0.0172 Epoch: 007/010 | Batch 550/938 | Cost: 0.0860 Epoch: 007/010 | Batch 600/938 | Cost: 0.1124 Epoch: 007/010 | Batch 650/938 | Cost: 0.0783 Epoch: 007/010 | Batch 700/938 | Cost: 0.0307 Epoch: 007/010 | Batch 750/938 | Cost: 0.0686 Epoch: 007/010 | Batch 800/938 | Cost: 0.0128 Epoch: 007/010 | Batch 850/938 | Cost: 0.0684 Epoch: 007/010 | Batch 900/938 | Cost: 0.0541 Epoch: 007/010 training accuracy: 98.98% Time elapsed: 1.56 min Epoch: 008/010 | Batch 000/938 | Cost: 0.0237 Epoch: 008/010 | Batch 050/938 | Cost: 0.0167 Epoch: 008/010 | Batch 100/938 | Cost: 0.0446 Epoch: 008/010 | Batch 150/938 | Cost: 0.0324 Epoch: 008/010 | Batch 200/938 | Cost: 0.0068 Epoch: 008/010 | Batch 250/938 | Cost: 0.0529 Epoch: 008/010 | Batch 300/938 | Cost: 0.0278 Epoch: 008/010 | Batch 350/938 | Cost: 0.0289 Epoch: 008/010 | Batch 400/938 | Cost: 0.0099 Epoch: 008/010 | Batch 450/938 | Cost: 0.0052 Epoch: 008/010 | Batch 500/938 | Cost: 0.0116 Epoch: 008/010 | Batch 550/938 | Cost: 0.0049 Epoch: 008/010 | Batch 600/938 | Cost: 0.0214 Epoch: 008/010 | Batch 650/938 | Cost: 0.0397 Epoch: 008/010 | Batch 700/938 | Cost: 0.0494 Epoch: 008/010 | Batch 750/938 | Cost: 0.0166 Epoch: 008/010 | Batch 800/938 | Cost: 0.0482 Epoch: 008/010 | Batch 850/938 | Cost: 0.0049 Epoch: 008/010 | Batch 900/938 | Cost: 0.0482 Epoch: 008/010 training accuracy: 99.25% Time elapsed: 1.78 min Epoch: 009/010 | Batch 000/938 | Cost: 0.0367 Epoch: 009/010 | Batch 050/938 | Cost: 0.0624 Epoch: 009/010 | Batch 100/938 | Cost: 0.0095 Epoch: 009/010 | Batch 150/938 | Cost: 0.0166 Epoch: 009/010 | Batch 200/938 | Cost: 0.0764 Epoch: 009/010 | Batch 250/938 | Cost: 0.0056 Epoch: 009/010 | Batch 300/938 | Cost: 0.0066 Epoch: 009/010 | Batch 350/938 | Cost: 0.0060 Epoch: 009/010 | Batch 400/938 | Cost: 0.0583 Epoch: 009/010 | Batch 450/938 | Cost: 0.0170 Epoch: 009/010 | Batch 500/938 | Cost: 0.0252 Epoch: 009/010 | Batch 550/938 | Cost: 0.0140 Epoch: 009/010 | Batch 600/938 | Cost: 0.0911 Epoch: 009/010 | Batch 650/938 | Cost: 0.0469 Epoch: 009/010 | Batch 700/938 | Cost: 0.0146 Epoch: 009/010 | Batch 750/938 | Cost: 0.0573 Epoch: 009/010 | Batch 800/938 | Cost: 0.0067 Epoch: 009/010 | Batch 850/938 | Cost: 0.1513 Epoch: 009/010 | Batch 900/938 | Cost: 0.0029 Epoch: 009/010 training accuracy: 99.30% Time elapsed: 2.01 min Epoch: 010/010 | Batch 000/938 | Cost: 0.0207 Epoch: 010/010 | Batch 050/938 | Cost: 0.0154 Epoch: 010/010 | Batch 100/938 | Cost: 0.0135 Epoch: 010/010 | Batch 150/938 | Cost: 0.0122 Epoch: 010/010 | Batch 200/938 | Cost: 0.0354 Epoch: 010/010 | Batch 250/938 | Cost: 0.0217 Epoch: 010/010 | Batch 300/938 | Cost: 0.0102 Epoch: 010/010 | Batch 350/938 | Cost: 0.0189 Epoch: 010/010 | Batch 400/938 | Cost: 0.0015 Epoch: 010/010 | Batch 450/938 | Cost: 0.0101 Epoch: 010/010 | Batch 500/938 | Cost: 0.0950 Epoch: 010/010 | Batch 550/938 | Cost: 0.0130 Epoch: 010/010 | Batch 600/938 | Cost: 0.0328 Epoch: 010/010 | Batch 650/938 | Cost: 0.0506 Epoch: 010/010 | Batch 700/938 | Cost: 0.0182 Epoch: 010/010 | Batch 750/938 | Cost: 0.0091 Epoch: 010/010 | Batch 800/938 | Cost: 0.0075 Epoch: 010/010 | Batch 850/938 | Cost: 0.0092 Epoch: 010/010 | Batch 900/938 | Cost: 0.0413 Epoch: 010/010 training accuracy: 99.00% Time elapsed: 2.23 min Total Training Time: 2.23 min
print('Test accuracy: %.2f%%' % (compute_accuracy(model, test_loader)))
Test accuracy: 97.54%
%watermark -iv
numpy 1.15.4 torch 1.0.0