Class Model

examples/basics/mnist-visualizations.py:66–114

class Model(ModelDesc):
    def inputs(self):
        return [tf.TensorSpec((None, IMAGE_SIZE, IMAGE_SIZE), tf.float32, 'input'),
                tf.TensorSpec((None,), tf.int32, 'label')]

    def build_graph(self, image, label):
        image = tf.expand_dims(image * 2 - 1, 3)

        with argscope(Conv2D, kernel_shape=3, nl=tf.nn.relu, out_channel=32):
            c0 = Conv2D('conv0', image)
            p0 = MaxPooling('pool0', c0, 2)
            c1 = Conv2D('conv1', p0)
            c2 = Conv2D('conv2', c1)
            p1 = MaxPooling('pool1', c2, 2)
            c3 = Conv2D('conv3', p1)
            fc1 = FullyConnected('fc0', c3, 512, nl=tf.nn.relu)
            fc1 = Dropout('dropout', fc1, 0.5)
            logits = FullyConnected('fc1', fc1, out_dim=10, nl=tf.identity)

        with tf.name_scope('visualizations'):
            visualize_conv_weights(c0.variables.W, 'conv0')
            visualize_conv_activations(c0, 'conv0')
            visualize_conv_weights(c1.variables.W, 'conv1')
            visualize_conv_activations(c1, 'conv1')
            visualize_conv_weights(c2.variables.W, 'conv2')
            visualize_conv_activations(c2, 'conv2')
            visualize_conv_weights(c3.variables.W, 'conv3')
            visualize_conv_activations(c3, 'conv3')

            tf.summary.image('input', (image + 1.0) * 128., 3)

        cost = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=label)
        cost = tf.reduce_mean(cost, name='cross_entropy_loss')

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

        wd_cost = tf.multiply(1e-5,
                              regularize_cost('fc.*/W', tf.nn.l2_loss),
                              name='regularize_loss')
        return tf.add_n([wd_cost, cost], name='total_cost')

    def optimizer(self):
        lr = tf.train.exponential_decay(
            learning_rate=1e-3,
            global_step=get_global_step_var(),
            decay_steps=468 * 10,
            decay_rate=0.3, staircase=True, name='learning_rate')
        tf.summary.scalar('lr', lr)
        return tf.train.AdamOptimizer(lr)


def get_data():