Class Model

examples/basics/mnist-tflayers.py:23–92

class Model(ModelDesc):
    def inputs(self):
        """
        Define all the inputs (with type, shape, name) that the graph will need.
        """
        return [tf.TensorSpec((None, IMAGE_SIZE, IMAGE_SIZE), tf.float32, 'input'),
                tf.TensorSpec((None,), tf.int32, 'label')]

    def build_graph(self, image, label):
        """This function should build the model which takes the input variables
        and return cost at the end"""

        # In tensorflow, inputs to convolution function are assumed to be
        # NHWC. Add a single channel here.
        image = tf.expand_dims(image, 3)

        image = image * 2 - 1   # center the pixels values at zero

        # The context manager `argscope` sets the default option for all the layers under
        # this context. Here we use 32 channel convolution with shape 3x3
        with argscope([tf.layers.conv2d], padding='same', activation=tf.nn.relu):
            l = tf.layers.conv2d(image, 32, 3, name='conv0')
            l = tf.layers.max_pooling2d(l, 2, 2, padding='valid')
            l = tf.layers.conv2d(l, 32, 3, name='conv1')
            l = tf.layers.conv2d(l, 32, 3, name='conv2')
            l = tf.layers.max_pooling2d(l, 2, 2, padding='valid')
            l = tf.layers.conv2d(l, 32, 3, name='conv3')
            l = tf.layers.flatten(l)
            l = tf.layers.dense(l, 512, activation=tf.nn.relu, name='fc0')
            l = tf.layers.dropout(l, rate=0.5, training=self.training)
        logits = tf.layers.dense(l, 10, activation=tf.identity, name='fc1')

        # a vector of length B with loss of each sample
        cost = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=label)
        cost = tf.reduce_mean(cost, name='cross_entropy_loss')  # the average cross-entropy loss

        correct = tf.cast(tf.nn.in_top_k(logits, label, 1), tf.float32, name='correct')
        accuracy = tf.reduce_mean(correct, name='accuracy')

        # This will monitor training error & accuracy (in a moving average fashion). The value will be automatically
        # 1. written to tensosrboard
        # 2. written to stat.json
        # 3. printed after each epoch
        train_error = tf.reduce_mean(1 - correct, name='train_error')
        summary.add_moving_summary(train_error, accuracy)

        # Use a regex to find parameters to apply weight decay.
        # Here we apply a weight decay on all W (weight matrix) of all fc layers
        # If you don't like regex, you can certainly define the cost in any other methods.
        wd_cost = tf.multiply(1e-5,
                              regularize_cost('fc.*/kernel', tf.nn.l2_loss),
                              name='regularize_loss')
        total_cost = tf.add_n([wd_cost, cost], name='total_cost')
        summary.add_moving_summary(cost, wd_cost, total_cost)

        # monitor histogram of all weight (of conv and fc layers) in tensorboard
        summary.add_param_summary(('.*/kernel', ['histogram', 'rms']))
        # the function should return the total cost to be optimized