Python nets.resnet_v2.resnet_arg_scope() Examples

The following are 3 code examples of nets.resnet_v2.resnet_arg_scope(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module nets.resnet_v2 , or try the search function .
Example #1
Source File: feature_extractor.py    From DeepLab_v3 with MIT License 5 votes vote down vote up 
def Resnet(n_layers, imgs_in, weight_decay, batch_norm_momentum, is_training):
    assert n_layers in {50, 101, 152, 200}, 'unsupported n_layers'

    network = getattr(resnet_v2, 'resnet_v2_{}'.format(n_layers))
    with tf.contrib.slim.arg_scope(resnet_v2.resnet_arg_scope(weight_decay=weight_decay, batch_norm_decay=batch_norm_momentum)):
        features, _ = network(imgs_in, is_training=is_training, global_pool=False, output_stride=16)

    return features
Example #2
Source File: resnet_v2_50.py    From vehicle-triplet-reid with MIT License 5 votes vote down vote up 
def endpoints(image, is_training):
    if image.get_shape().ndims != 4:
        raise ValueError('Input must be of size [batch, height, width, 3]')

    image = image - tf.constant(_RGB_MEAN, dtype=tf.float32, shape=(1,1,1,3))

    with tf.contrib.slim.arg_scope(resnet_arg_scope(batch_norm_decay=0.9, weight_decay=0.0)):
        _, endpoints = resnet_v2_50(image, num_classes=None, is_training=is_training, global_pool=True)

    endpoints['model_output'] = endpoints['global_pool'] = tf.reduce_mean(
        endpoints['resnet_v2_50/block4'], [1, 2], name='pool5', keep_dims=False)

    return endpoints, 'resnet_v2_50'
Example #3
Source File: attack_iter.py    From Translation-Invariant-Attacks with Apache License 2.0 4 votes vote down vote up 
def graph(x, y, i, x_max, x_min, grad):
    eps = 2.0 * FLAGS.max_epsilon / 255.0
    num_iter = FLAGS.num_iter
    alpha = eps / num_iter
    momentum = FLAGS.momentum
    num_classes = 1001

    # should keep original x here for output

    with slim.arg_scope(inception_v3.inception_v3_arg_scope()):
        logits_v3, end_points_v3 = inception_v3.inception_v3(
            input_diversity(x), num_classes=num_classes, is_training=False)

    with slim.arg_scope(inception_v4.inception_v4_arg_scope()):
        logits_v4, end_points_v4 = inception_v4.inception_v4(
            input_diversity(x), num_classes=num_classes, is_training=False)

    with slim.arg_scope(inception_resnet_v2.inception_resnet_v2_arg_scope()):
        logits_res_v2, end_points_res_v2 = inception_resnet_v2.inception_resnet_v2(
            input_diversity(x), num_classes=num_classes, is_training=False, reuse=True)

    with slim.arg_scope(resnet_v2.resnet_arg_scope()):
        logits_resnet, end_points_resnet = resnet_v2.resnet_v2_152(
            input_diversity(x), num_classes=num_classes, is_training=False)

    logits = (logits_v3 + logits_v4 + logits_res_v2 + logits_resnet) / 4
    auxlogits = (end_points_v3['AuxLogits'] + end_points_v4['AuxLogits'] + end_points_res_v2['AuxLogits']) / 3
    cross_entropy = tf.losses.softmax_cross_entropy(y,
                                                    logits,
                                                    label_smoothing=0.0,
                                                    weights=1.0)
    cross_entropy += tf.losses.softmax_cross_entropy(y,
                                                     auxlogits,
                                                     label_smoothing=0.0,
                                                     weights=0.4)
    noise = tf.gradients(cross_entropy, x)[0]
    noise = tf.nn.depthwise_conv2d(noise, stack_kernel, strides=[1, 1, 1, 1], padding='SAME')
    noise = noise / tf.reduce_mean(tf.abs(noise), [1, 2, 3], keep_dims=True)
    noise = momentum * grad + noise
    x = x + alpha * tf.sign(noise)
    x = tf.clip_by_value(x, x_min, x_max)
    i = tf.add(i, 1)
    return x, y, i, x_max, x_min, noise