Clarity question about number of layers

[owensca]

If I set layers = 5, then from the code below it seems that the number of down-layers will be 5 and the number of up-layers will be 4. This would yield a total of 9 convolutional layers altogether. Is this correct?

From 'unet.py':

# down layers
    for layer in range(0, layers):
        features = 2**layer*features_root
        stddev = np.sqrt(2 / (filter_size**2 * features))
        if layer == 0:
            w1 = weight_variable([filter_size, filter_size, channels, features], stddev)
        else:
            w1 = weight_variable([filter_size, filter_size, features//2, features], stddev)

        w2 = weight_variable([filter_size, filter_size, features, features], stddev)
        b1 = bias_variable([features])
        b2 = bias_variable([features])

        conv1 = conv2d(in_node, w1, keep_prob)
        tmp_h_conv = tf.nn.relu(conv1 + b1)
        conv2 = conv2d(tmp_h_conv, w2, keep_prob)
        dw_h_convs[layer] = tf.nn.relu(conv2 + b2)

        weights.append((w1, w2))
        biases.append((b1, b2))
        convs.append((conv1, conv2))

        size -= 4
        if layer < layers-1:
            pools[layer] = max_pool(dw_h_convs[layer], pool_size)
            in_node = pools[layer]
            size /= 2

    in_node = dw_h_convs[layers-1]

    # up layers
    for layer in range(layers-2, -1, -1):
        features = 2**(layer+1)*features_root
        stddev = np.sqrt(2 / (filter_size**2 * features))

        wd = weight_variable_devonc([pool_size, pool_size, features//2, features], stddev)
        bd = bias_variable([features//2])
        h_deconv = tf.nn.relu(deconv2d(in_node, wd, pool_size) + bd)
        h_deconv_concat = crop_and_concat(dw_h_convs[layer], h_deconv)
        deconv[layer] = h_deconv_concat

        w1 = weight_variable([filter_size, filter_size, features, features//2], stddev)
        w2 = weight_variable([filter_size, filter_size, features//2, features//2], stddev)
        b1 = bias_variable([features//2])
        b2 = bias_variable([features//2])

        conv1 = conv2d(h_deconv_concat, w1, keep_prob)
        h_conv = tf.nn.relu(conv1 + b1)
        conv2 = conv2d(h_conv, w2, keep_prob)
        in_node = tf.nn.relu(conv2 + b2)
        up_h_convs[layer] = in_node

        weights.append((w1, w2))
        biases.append((b1, b2))
        convs.append((conv1, conv2))

        size *= 2
        size -= 4

[jakeret]

Yes this is correct and corresponds to Fig. 1 in Ronnebergs et al paper