general.py 文件源码

def fully_connected(in_tensor, layer_name, out_chan, trainable=True):
        with tf.variable_scope(layer_name):
            in_size = in_tensor.get_shape().as_list()
            assert len(in_size) == 2, 'Input to a fully connected layer must be a vector.'
            weights_shape = [in_size[1], out_chan]

            # weight matrix
            weights = tf.get_variable('weights', weights_shape, tf.float32,
                                     tf.contrib.layers.xavier_initializer(), trainable=trainable)
            weights = tf.check_numerics(weights, 'weights: %s' % layer_name)

            # bias
            biases = tf.get_variable('biases', [out_chan], tf.float32,
                                     tf.constant_initializer(0.0001), trainable=trainable)
            biases = tf.check_numerics(biases, 'biases: %s' % layer_name)

            out_tensor = tf.matmul(in_tensor, weights) + biases
            return out_tensor