计算图构建
构建CNN静态计算图，其中学习率每n轮Epoch进行1次递减。
#region BuildGraph
public Graph BuildGraph()
{
var graph = new Graph().as_default();
tf_with(tf.name_scope("Input"), delegate
{
x = tf.placeholder(tf.float32, shape: (-1, img_h, img_w, n_channels), name: "X");
y = tf.placeholder(tf.float32, shape: (-1, n_classes), name: "Y");
});
var conv1 = conv_layer(x, filter_size1, num_filters1, stride1, name: "conv1");
var pool1 = max_pool(conv1, ksize: 2, stride: 2, name: "pool1");
var conv2 = conv_layer(pool1, filter_size2, num_filters2, stride2, name: "conv2");
var pool2 = max_pool(conv2, ksize: 2, stride: 2, name: "pool2");
var layer_flat = flatten_layer(pool2);
var fc1 = fc_layer(layer_flat, h1, "FC1", use_relu: true);
var output_logits = fc_layer(fc1, n_classes, "OUT", use_relu: false);
//Some important parameter saved with graph , easy to load later
var img_h_t = tf.constant(img_h, name: "img_h");
var img_w_t = tf.constant(img_w, name: "img_w");
var img_mean_t = tf.constant(img_mean, name: "img_mean");
var img_std_t = tf.constant(img_std, name: "img_std");
var channels_t = tf.constant(n_channels, name: "img_channels");
//learning rate decay
gloabl_steps = tf.Variable(0, trainable: false);
learning_rate = tf.Variable(learning_rate_base);
//create train images graph
tf_with(tf.variable_scope("LoadImage"), delegate
{
decodeJpeg = tf.placeholder(tf.@byte, name: "DecodeJpeg");
var cast = tf.cast(decodeJpeg, tf.float32);
var dims_expander = tf.expand_dims(cast, 0);
var resize = tf.constant(new int[] { img_h, img_w });
var bilinear = tf.image.resize_bilinear(dims_expander, resize);
var sub = tf.subtract(bilinear, new float[] { img_mean });
normalized = tf.divide(sub, new float[] { img_std }, name: "normalized");
});
tf_with(tf.variable_scope("Train"), delegate
{
tf_with(tf.variable_scope("Loss"), delegate
{
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels: y, logits: output_logits), name: "loss");
});
tf_with(tf.variable_scope("Optimizer"), delegate
{
optimizer = tf.train.AdamOptimizer(learning_rate: learning_rate, name: "Adam-op").minimize(loss, global_step: gloabl_steps);
});
tf_with(tf.variable_scope("Accuracy"), delegate
{
var correct_prediction = tf.equal(tf.argmax(output_logits, 1), tf.argmax(y, 1), name: "correct_pred");
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name: "accuracy");
});
tf_with(tf.variable_scope("Prediction"), delegate
{
cls_prediction = tf.argmax(output_logits, axis: 1, name: "predictions");
prob = tf.nn.softmax(output_logits, axis: 1, name: "prob");
});
});
return graph;
}
/// <summary>
/// Create a 2D convolution layer
/// </summary>
/// <param name="x">input from previous layer</param>
/// <param name="filter_size">size of each filter</param>
/// <param name="num_filters">number of filters(or output feature maps)</param>
/// <param name="stride">filter stride</param>
/// <param name="name">layer name</param>
/// <returns>The output array</returns>
private Tensor conv_layer(Tensor x, int filter_size, int num_filters, int stride, string name)
{
return tf_with(tf.variable_scope(name), delegate
{
var num_in_channel = x.shape[x.NDims - 1];
var shape = new[] { filter_size, filter_size, num_in_channel, num_filters };
var W = weight_variable("W", shape);
// var tf.summary.histogram("weight", W);
var b = bias_variable("b", new[] { num_filters });
// tf.summary.histogram("bias", b);
var layer = tf.nn.conv2d(x, W,
strides: new[] { 1, stride, stride, 1 },
padding: "SAME");
layer += b;
return tf.nn.relu(layer);
});
}
/// <summary>
/// Create a max pooling layer
/// </summary>
/// <param name="x">input to max-pooling layer</param>
/// <param name="ksize">size of the max-pooling filter</param>
/// <param name="stride">stride of the max-pooling filter</param>
/// <param name="name">layer name</param>
/// <returns>The output array</returns>
private Tensor max_pool(Tensor x, int ksize, int stride, string name)
{
return tf.nn.max_pool(x,
ksize: new[] { 1, ksize, ksize, 1 },
strides: new[] { 1, stride, stride, 1 },
padding: "SAME",
name: name);
}
/// <summary>
/// Flattens the output of the convolutional layer to be fed into fully-connected layer
/// </summary>
/// <param name="layer">input array</param>
/// <returns>flattened array</returns>
private Tensor flatten_layer(Tensor layer)
{
return tf_with(tf.variable_scope("Flatten_layer"), delegate
{
var layer_shape = layer.TensorShape;
var num_features = layer_shape[new Slice(1, 4)].size;
var layer_flat = tf.reshape(layer, new[] { -1, num_features });
return layer_flat;
});
}
/// <summary>
/// Create a weight variable with appropriate initialization
/// </summary>
/// <param name="name"></param>
/// <param name="shape"></param>
/// <returns></returns>
private RefVariable weight_variable(string name, int[] shape)
{
var initer = tf.truncated_normal_initializer(stddev: 0.01f);
return tf.get_variable(name,
dtype: tf.float32,
shape: shape,
initializer: initer);
}
/// <summary>
/// Create a bias variable with appropriate initialization
/// </summary>
/// <param name="name"></param>
/// <param name="shape"></param>
/// <returns></returns>
private RefVariable bias_variable(string name, int[] shape)
{
var initial = tf.constant(0f, shape: shape, dtype: tf.float32);
return tf.get_variable(name,
dtype: tf.float32,
initializer: initial);
}
/// <summary>
/// Create a fully-connected layer
/// </summary>
/// <param name="x">input from previous layer</param>
/// <param name="num_units">number of hidden units in the fully-connected layer</param>
/// <param name="name">layer name</param>
/// <param name="use_relu">boolean to add ReLU non-linearity (or not)</param>
/// <returns>The output array</returns>
private Tensor fc_layer(Tensor x, int num_units, string name, bool use_relu = true)
{
return tf_with(tf.variable_scope(name), delegate
{
var in_dim = x.shape[1];
var W = weight_variable("W_" + name, shape: new[] { in_dim, num_units });
var b = bias_variable("b_" + name, new[] { num_units });
var layer = tf.matmul(x, W) + b;
if (use_relu)
layer = tf.nn.relu(layer);
return layer;
});
}
#endregion
