public void Run()
{
// Parameters
double learning_rate = 0.01;
int training_epochs = 1000;
int display_step = 50;
// Training Data
var train_X = np.array(3.3, 4.4, 5.5, 6.71, 6.93, 4.168, 9.779, 6.182, 7.59, 2.167,
7.042, 10.791, 5.313, 7.997, 5.654, 9.27, 3.1);
var train_Y = np.array(1.7, 2.76, 2.09, 3.19, 1.694, 1.573, 3.366, 2.596, 2.53, 1.221,
2.827, 3.465, 1.65, 2.904, 2.42, 2.94, 1.3);
var n_samples = train_X.shape[0];
// tf Graph Input
var X = tf.placeholder(tf.float64);
var Y = tf.placeholder(tf.float64);
// Set model weights
var W = tf.Variable(rng.randn <double>(), name: "weight");
var b = tf.Variable(rng.randn <double>(), name: "bias");
var part1 = tf.multiply(X, W);
var pred = tf.add(part1, b);
// Mean squared error
var sub = pred - Y;
var pow = tf.pow(sub, 2);
var reduce = tf.reduce_sum(pow);
var cost = reduce / (2d * n_samples);
// radient descent
// Note, minimize() knows to modify W and b because Variable objects are trainable=True by default
var optimizer = tf.train.GradientDescentOptimizer(learning_rate);
optimizer.minimize(cost);
// Initialize the variables (i.e. assign their default value)
var init = tf.global_variables_initializer();
// Start training
Python.with <Session>(tf.Session(), sess =>
{
// Run the initializer
sess.run(init);
// Fit all training data
for (int i = 0; i < training_epochs; i++)
{
for (int index = 0; index < train_X.size; index++)
{
(double x, double y) = Python.zip <double>(train_X, train_Y, index);
var feed_dict = new Dictionary <Tensor, NDArray>();
// sess.run(optimizer, feed_dict);
}
}
});
}
public void Run()
{
// Parameters
double learning_rate = 0.01;
int training_epochs = 1000;
int display_step = 50;
// Training Data
var train_X = np.array(3.3, 4.4, 5.5, 6.71, 6.93, 4.168, 9.779, 6.182, 7.59, 2.167,
7.042, 10.791, 5.313, 7.997, 5.654, 9.27, 3.1);
var train_Y = np.array(1.7, 2.76, 2.09, 3.19, 1.694, 1.573, 3.366, 2.596, 2.53, 1.221,
2.827, 3.465, 1.65, 2.904, 2.42, 2.94, 1.3);
var n_samples = train_X.shape[0];
// tf Graph Input
var X = tf.placeholder(tf.float64);
var Y = tf.placeholder(tf.float64);
// Set model weights
var W = tf.Variable(rng.randn <double>(), name: "weight");
var b = tf.Variable(rng.randn <double>(), name: "bias");
var part1 = tf.multiply(X, W);
var pred = tf.add(part1, b);
// Mean squared error
var sub = pred - Y;
var pow = tf.pow(sub, 2);
var reduce = tf.reduce_sum(pow);
var cost = reduce / (2d * n_samples);
// radient descent
// Note, minimize() knows to modify W and b because Variable objects are trainable=True by default
// var optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost);
}
/// <summary>
/// 神经网络
/// </summary>
/// <param name="neuronsCounts">神经网络每一层神经元数量</param>
public Network(int[] neuronsCounts)
{
this.LayersCount = neuronsCounts.Length;
this.NeuronsCounts = neuronsCounts;
// 高斯(正态)分布 随机数发生器
var pyRandom = new NumPyRandom();
this.Biases = neuronsCounts.Skip(1).Select(count => pyRandom.randn(count, 1)).ToArray();
this.Weights = neuronsCounts.Skip(1).Zip(neuronsCounts.SkipLast(1)).Select(counts => pyRandom.randn(counts.First, counts.Second)).ToArray();
}
/// <summary>
/// 初始化神经网络
/// </summary>
/// <param name="neuronCounts">神经网络每层神经元个数的集合</param>
public Network(IEnumerable <int> neuronCounts)
{
// 初始化神经网络神经元集合
this.NeuronPool = new List <List <TNeuron> >(
neuronCounts.Select(
count =>
Enumerable.Range(0, count).
Select(index => Activator.CreateInstance <TNeuron>())
.ToList())
);
// 高斯(正态)分布 随机数发生器
var pyRandom = new NumPyRandom();
// 为非输入层初始化偏置
_ = this.NeuronPool.Skip(1).All(neurons =>
{
foreach (var(neuron, bias) in neurons.Zip(pyRandom.randn(new[] { neurons.Count, 1 }).Array as double[]))
{
neuron.Bias = bias;
}
return(true);
});
// 为非输入层初始化对前一层神经元输入的权重
_ = this.NeuronPool.SkipLast(1).Zip(this.NeuronPool.Skip(1)).All(neurons =>
{
var weights = pyRandom.randn(new int[] { neurons.Second.Count, neurons.First.Count });
for (int index = 0; index < neurons.Second.Count; index++)
{
neurons.Second[index].Weight = weights[index].Array as double[];
}
return(true);
});
}
public void Run()
{
// Parameters
double learning_rate = 0.01;
int training_epochs = 1000;
int display_step = 50;
// Training Data
var train_X = np.array(3.3, 4.4, 5.5, 6.71, 6.93, 4.168, 9.779, 6.182, 7.59, 2.167,
7.042, 10.791, 5.313, 7.997, 5.654, 9.27, 3.1);
var train_Y = np.array(1.7, 2.76, 2.09, 3.19, 1.694, 1.573, 3.366, 2.596, 2.53, 1.221,
2.827, 3.465, 1.65, 2.904, 2.42, 2.94, 1.3);
var n_samples = train_X.shape[0];
// tf Graph Input
var X = tf.placeholder(tf.float64);
var Y = tf.placeholder(tf.float64);
// Set model weights
var W = tf.Variable(rng.randn <double>(), name: "weight");
var b = tf.Variable(rng.randn <double>(), name: "bias");
var mul = tf.multiply(X, W);
var pred = tf.add(mul, b);
// Mean squared error
var sub = pred - Y;
var pow = tf.pow(sub, 2);
var reduce = tf.reduce_sum(pow);
var cost = reduce / (2d * n_samples);
// radient descent
// Note, minimize() knows to modify W and b because Variable objects are trainable=True by default
var grad = tf.train.GradientDescentOptimizer(learning_rate);
var optimizer = grad.minimize(cost);
// Initialize the variables (i.e. assign their default value)
var init = tf.global_variables_initializer();
// Start training
Python.with <Session>(tf.Session(), sess =>
{
// Run the initializer
sess.run(init);
// Fit all training data
for (int epoch = 0; epoch < training_epochs; epoch++)
{
foreach (var(x, y) in Python.zip <double>(train_X, train_Y))
{
sess.run(optimizer, feed_dict: new FeedItem[]
{
new FeedItem(X, x),
new FeedItem(Y, y)
});
}
// Display logs per epoch step
if ((epoch + 1) % display_step == 0)
{
var c = sess.run(cost, feed_dict: new FeedItem[]
{
new FeedItem(X, train_X),
new FeedItem(Y, train_Y)
});
var rW = sess.run(W);
Console.WriteLine($"Epoch: {epoch + 1} cost={c} " +
$"W={rW} b={sess.run(b)}");
}
}
