Created
September 16, 2018 19:19
-
-
Save carlosgmartin/8f5dca0795047e21f4ba7971a416d4b0 to your computer and use it in GitHub Desktop.
Pure-numpy neural network on CIFAR10 dataset
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy | |
import torch | |
import torchvision | |
import matplotlib.pyplot as plt | |
def relu(x): | |
return numpy.maximum(0, x) | |
def relu_derivative(x): | |
return (x > 0).astype(float) | |
def softmax(x): | |
y = numpy.exp(x - x.max(-1, keepdims=True)) | |
return y / y.sum(-1, keepdims=True) | |
class NeuralNetwork: | |
def __init__(self, dimensions): | |
self.L = len(dimensions) - 1 | |
self.w = [ | |
numpy.random.randn(i, j) * numpy.sqrt(2 / i) | |
for i, j in zip(dimensions, dimensions[1:]) | |
] | |
self.b = [ | |
numpy.zeros(j) | |
for j in dimensions[1:] | |
] | |
self.a = {} | |
self.dw = {} | |
self.db = {} | |
def forward(self, x): | |
self.a[0] = x.reshape(len(x), -1) | |
for l in range(self.L): | |
self.a[l + 1] = (relu if l + 1 < self.L else softmax)(self.a[l] @ self.w[l] + self.b[l]) | |
def backward(self, y): | |
delta = {} | |
for l in reversed(range(self.L)): | |
if l + 1 == self.L: | |
delta[l] = self.a[l + 1] - numpy.eye(len(self.b[-1]))[y] | |
else: | |
delta[l] = delta[l + 1] @ self.w[l + 1].T * relu_derivative(self.a[l + 1]) | |
self.dw[l] = self.a[l].T @ delta[l] | |
self.db[l] = delta[l].sum(0) | |
def step(self, learning_rate): | |
for l in range(self.L): | |
self.w[l] -= learning_rate * self.dw[l] | |
self.b[l] -= learning_rate * self.db[l] | |
def predict(self): | |
return self.a[self.L].argmax(-1) | |
def loss(self, y): | |
return -numpy.log(self.a[self.L][:, y]).mean() | |
def accuracy(self, y): | |
return (y == self.predict()).mean() | |
def train(self, x_train, x_val, y_train, y_val, epochs, learning_rate, batch_size): | |
for epoch in range(epochs): | |
print('epoch {}'.format(epoch)) | |
p = numpy.random.permutation(len(x_train)) | |
for i in range(0, len(x_train), batch_size): | |
x = x_train[p[i:i + batch_size]] | |
y = y_train[p[i:i + batch_size]] | |
self.forward(x) | |
self.backward(y) | |
self.step(learning_rate) | |
self.forward(x_train) | |
print(' train accuracy: {:.3f}'.format(self.accuracy(y_train))) | |
self.forward(x_val) | |
print(' validation accuracy: {:.3f}'.format(self.accuracy(y_val))) | |
transform = torchvision.transforms.Compose([ | |
torchvision.transforms.ToTensor(), | |
torchvision.transforms.Normalize((.5, .5, .5), (.5, .5, .5)), | |
torchvision.transforms.Lambda(lambda x: x.numpy()) | |
]) | |
x_train, y_train = map(numpy.array, zip(*torchvision.datasets.CIFAR10( | |
root='data', | |
train=True, | |
transform=transform, | |
download=True | |
))) | |
x_test, y_test = map(numpy.array, zip(*torchvision.datasets.CIFAR10( | |
root='data', | |
train=False, | |
transform=transform, | |
download=True | |
))) | |
shuffle = numpy.random.permutation(len(x_train)) | |
split = [int(len(x_train) * .1)] | |
x_val, x_train = numpy.split(x_train[shuffle], split) | |
y_val, y_train = numpy.split(y_train[shuffle], split) | |
net = NeuralNetwork([ | |
numpy.prod(x_train.shape[1:]), | |
100, | |
y_train.max() + 1 | |
]) | |
net.train( | |
x_train, | |
x_val, | |
y_train, | |
y_val, | |
epochs=20, | |
learning_rate=1e-4, | |
batch_size=10 | |
) | |
net.forward(x_train) | |
print('train loss: {:.3f}'.format(net.loss(y_train))) | |
print('train accuracy: {:.3f}'.format(net.accuracy(y_train))) | |
net.forward(x_test) | |
print('test accuracy: {:.3f}'.format(net.accuracy(y_test))) | |
rows, cols = 3, 5 | |
samples = numpy.random.choice(len(x_test), size=rows * cols, replace=False) | |
images = numpy.transpose(x_test[samples], (0, 2, 3, 1)) / 2 + .5 | |
classes = numpy.array(['plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']) | |
labels = classes[y_test[samples]] | |
net.forward(x_test[samples]) | |
predictions = classes[net.predict()] | |
fig, axes = plt.subplots(rows, cols) | |
for i in range(rows): | |
for j in range(cols): | |
axes[i, j].imshow(images[i * cols + j]) | |
axes[i, j].set_xlabel(predictions[i * 5 + j]) | |
plt.tight_layout() | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment