コード例 #1
0
 def _build_net(self):
     w2 = helpers.weight_variable([ENCODED_FEATURES, HIDDEN_UNITS_2])
     b2 = helpers.bias_variable([HIDDEN_UNITS_2])
     l2 = tf.nn.relu6(tf.matmul(self.x_placeholder, w2) + b2)
     l2_drop = tf.nn.dropout(l2, self.keep_prob)
     # Output layer
     w5 = helpers.weight_variable([HIDDEN_UNITS_2, OUTPUT_CLASSES])
     b5 = helpers.bias_variable([OUTPUT_CLASSES])
     l5 = tf.nn.relu6(tf.matmul(l2_drop, w5) + b5)
     return tf.nn.softmax(l5)
コード例 #2
0
 def _build(self):
     # First hidden layer
     w2 = helpers.weight_variable([INPUT_UNITS, HIDDEN_UNITS_1])
     b2 = helpers.bias_variable([HIDDEN_UNITS_1])
     l2 = tf.nn.relu(tf.matmul(self.x_placeholder, w2) + b2)
     l2_drop = tf.nn.dropout(l2, self.keep_prob)
     # Second hidden layer
     w3 = helpers.weight_variable([HIDDEN_UNITS_1, HIDDEN_UNITS_2])
     b3 = helpers.bias_variable([HIDDEN_UNITS_2])
     l3 = tf.nn.relu(tf.matmul(l2_drop, w3) + b3)
     l3_drop = tf.nn.dropout(l3, self.keep_prob)
     # Output layer
     w5 = helpers.weight_variable([HIDDEN_UNITS_2, OUTPUT_CLASSES])
     b5 = helpers.bias_variable([OUTPUT_CLASSES])
     return tf.nn.softmax(tf.matmul(l3_drop, w5) + b5)
コード例 #3
0
ファイル: deep_network.py プロジェクト: klangner/telstra
 def _build(self):
     # First hidden layer
     w2 = helpers.weight_variable([INPUT_UNITS, HIDDEN_UNITS_1])
     b2 = helpers.bias_variable([HIDDEN_UNITS_1])
     l2 = tf.nn.relu(tf.matmul(self.x_placeholder, w2) + b2)
     l2_drop = tf.nn.dropout(l2, self.keep_prob)
     # Second hidden layer
     w3 = helpers.weight_variable([HIDDEN_UNITS_1, HIDDEN_UNITS_2])
     b3 = helpers.bias_variable([HIDDEN_UNITS_2])
     l3 = tf.nn.relu(tf.matmul(l2_drop, w3) + b3)
     l3_drop = tf.nn.dropout(l3, self.keep_prob)
     # Output layer
     w5 = helpers.weight_variable([HIDDEN_UNITS_2, OUTPUT_CLASSES])
     b5 = helpers.bias_variable([OUTPUT_CLASSES])
     return tf.nn.softmax(tf.matmul(l3_drop, w5) + b5)
コード例 #4
0
 def _build_decoder(self, encoder):
     weights = helpers.weight_variable([ENCODED_FEATURES, INPUT_UNITS])
     biases = helpers.bias_variable([INPUT_UNITS])
     l3 = tf.nn.relu(tf.matmul(encoder, weights) + biases)
     return tf.nn.softmax(l3)
コード例 #5
0
 def _build_encoder(self):
     weights = helpers.weight_variable([INPUT_UNITS, ENCODED_FEATURES])
     biases = helpers.bias_variable([ENCODED_FEATURES])
     return tf.nn.relu(tf.matmul(self.x_placeholder, weights) + biases)
コード例 #6
0
def inference():
    x = tf.placeholder(tf.float32, shape=[None, 784], name='input')
    image = tf.reshape(x, [-1, 28, 28, 1])

    with tf.name_scope('conv_layer_1'):
        W_conv1 = helpers.weight_variable([5, 5, 1, 32], 'W_conv1')
        b_conv1 = helpers.bias_variable([32], 'bias_conv1')
        alphas_conv1 = helpers.bias_variable([32], 'alpha_conv1')
        layer_conv_1 = helpers.prelu(
            helpers.conv2d(image, W_conv1) + b_conv1, alphas_conv1)

        W_conv1_b = helpers.weight_variable([5, 5, 32, 32], 'W_conv1_b')
        b_conv1_b = helpers.bias_variable([32], 'bias_conv1_b')
        alphas_conv1_b = helpers.bias_variable([32], 'alpha_conv1_b')

        layer_conv_1_b = helpers.prelu(
            helpers.conv2d(layer_conv_1, W_conv1_b) + b_conv1_b,
            alphas_conv1_b)

        stage_1_pool = helpers.max_pool_2x2(layer_conv_1_b)

    with tf.name_scope('conv_layer_2'):
        W_conv2 = helpers.weight_variable([5, 5, 32, 64], "W_conv2")
        b_conv2 = helpers.bias_variable([64], 'bias_conv2')
        alphas_conv2 = helpers.bias_variable([64], 'alpha_conv2')
        layer_conv_2 = helpers.prelu(
            helpers.conv2d(stage_1_pool, W_conv2) + b_conv2, alphas_conv2)

        W_conv2_b = helpers.weight_variable([5, 5, 64, 64], "W_conv2_b")
        b_conv2_b = helpers.bias_variable([64], 'bias_conv2_b')
        alphas_conv2_b = helpers.bias_variable([64], 'alpha_conv2_b')
        layer_conv_2_b = helpers.prelu(
            helpers.conv2d(layer_conv_2, W_conv2_b) + b_conv2_b,
            alphas_conv2_b)

        stage_2_pool = helpers.max_pool_2x2(layer_conv_2_b)
        # stage_2_pool_flat = tf.reshape(stage_2_pool, [-1, 7 * 7 * 64])

    with tf.name_scope('conv_layer_3'):
        W_conv3 = helpers.weight_variable([5, 5, 64, 128], "W_conv3")
        b_conv3 = helpers.bias_variable([128], 'bias_conv3')
        alphas_conv3 = helpers.bias_variable([128], 'alpha_conv3')
        layer_conv_3 = helpers.prelu(
            helpers.conv2d(stage_2_pool, W_conv3) + b_conv3, alphas_conv3)

        # stage_3_pool = helpers.max_pool_2x2(layer_conv_3)
        # stage_3_pool_flat = tf.reshape(stage_3_pool, [-1, 4 * 4 * 256])

        W_conv3_b = helpers.weight_variable([5, 5, 128, 128], "W_conv3_b")
        b_conv3_b = helpers.bias_variable([128], 'bias_conv3_b')
        alphas_conv3_b = helpers.bias_variable([128], 'alpha_conv3_b')
        layer_conv_3_b = helpers.prelu(
            helpers.conv2d(layer_conv_3, W_conv3_b) + b_conv3_b,
            alphas_conv3_b)

        stage_3_pool = helpers.max_pool_2x2(layer_conv_3_b)
        stage_3_pool_flat = tf.reshape(stage_3_pool, [-1, 4 * 4 * 128])

    with tf.name_scope('fc_layer_1'):
        W_fc1 = helpers.weight_variable([4 * 4 * 128, 2], "W_fc1")
        # W_fc1 = helpers.weight_variable([7 * 7 * 64, 2], "W_fc1")
        b_fc1 = helpers.bias_variable([2], 'bias_fc1')
        alphas_fc1 = helpers.bias_variable([2], 'alpha_conv3')
        output = helpers.prelu(
            tf.matmul(stage_3_pool_flat, W_fc1) + b_fc1, alphas_fc1)

    # with tf.name_scope('fc_output'):
    #     W_output = helpers.weight_variable([500, 10], "W_putput")
    #     b_output = helpers.bias_variable([10], 'bias_output')
    #     output = tf.nn.relu(tf.matmul(h_fc1, W_output) + b_output)

    # with tf.name_scope('output'):
    #     W_output = helpers.weight_variable([2, 10], "W_output")
    #     b_output = helpers.bias_variable([10])
    #     output = tf.nn.relu(tf.matmul(h_fc2, W_output) + b_output)

    return x, output