Python layers.GlobalPoolLayer方法代码示例

# 需要导入模块: from lasagne import layers [as 别名]
# 或者: from lasagne.layers import GlobalPoolLayer [as 别名]
def ResNet_FullPreActivation(input_shape=(None, 3, PIXELS, PIXELS), input_var=None, n_classes=10, n=18):
    """
    Adapted from https://github.com/Lasagne/Recipes/tree/master/papers/deep_residual_learning.
    Tweaked to be consistent with 'Identity Mappings in Deep Residual Networks', Kaiming He et al. 2016 (https://arxiv.org/abs/1603.05027)

    Formula to figure out depth: 6n + 2
    """

    # Building the network
    l_in = InputLayer(shape=input_shape, input_var=input_var)

    # first layer, output is 16 x 32 x 32
    l = batch_norm(ConvLayer(l_in, num_filters=16, filter_size=(3, 3), stride=(1, 1), nonlinearity=rectify, pad='same', W=he_norm))

    # first stack of residual blocks, output is 16 x 32 x 32
    l = residual_block(l, first=True)
    for _ in range(1, n):
        l = residual_block(l)

    # second stack of residual blocks, output is 32 x 16 x 16
    l = residual_block(l, increase_dim=True)
    for _ in range(1, n):
        l = residual_block(l)

    # third stack of residual blocks, output is 64 x 8 x 8
    l = residual_block(l, increase_dim=True)
    for _ in range(1, n):
        l = residual_block(l)

    bn_post_conv = BatchNormLayer(l)
    bn_post_relu = NonlinearityLayer(bn_post_conv, rectify)

    # average pooling
    avg_pool = GlobalPoolLayer(bn_post_relu)

    # fully connected layer
    network = DenseLayer(avg_pool, num_units=n_classes, W=HeNormal(), nonlinearity=softmax)

    return network 

# 需要导入模块: from lasagne import layers [as 别名]
# 或者: from lasagne.layers import GlobalPoolLayer [as 别名]
def build_model():
    net = {}
    net['input'] = InputLayer((None, 3, None, None))
    net['conv1/7x7_s2'] = ConvLayer(
        net['input'], 64, 7, stride=2, pad=3, flip_filters=False)
    net['pool1/3x3_s2'] = PoolLayer(
        net['conv1/7x7_s2'], pool_size=3, stride=2, ignore_border=False)
    net['pool1/norm1'] = LRNLayer(net['pool1/3x3_s2'], alpha=0.00002, k=1)
    net['conv2/3x3_reduce'] = ConvLayer(
        net['pool1/norm1'], 64, 1, flip_filters=False)
    net['conv2/3x3'] = ConvLayer(
        net['conv2/3x3_reduce'], 192, 3, pad=1, flip_filters=False)
    net['conv2/norm2'] = LRNLayer(net['conv2/3x3'], alpha=0.00002, k=1)
    net['pool2/3x3_s2'] = PoolLayer(
      net['conv2/norm2'], pool_size=3, stride=2, ignore_border=False)

    net.update(build_inception_module('inception_3a',
                                      net['pool2/3x3_s2'],
                                      [32, 64, 96, 128, 16, 32]))
    net.update(build_inception_module('inception_3b',
                                      net['inception_3a/output'],
                                      [64, 128, 128, 192, 32, 96]))
    net['pool3/3x3_s2'] = PoolLayer(
      net['inception_3b/output'], pool_size=3, stride=2, ignore_border=False)

    net.update(build_inception_module('inception_4a',
                                      net['pool3/3x3_s2'],
                                      [64, 192, 96, 208, 16, 48]))
    net.update(build_inception_module('inception_4b',
                                      net['inception_4a/output'],
                                      [64, 160, 112, 224, 24, 64]))
    net.update(build_inception_module('inception_4c',
                                      net['inception_4b/output'],
                                      [64, 128, 128, 256, 24, 64]))
    net.update(build_inception_module('inception_4d',
                                      net['inception_4c/output'],
                                      [64, 112, 144, 288, 32, 64]))
    net.update(build_inception_module('inception_4e',
                                      net['inception_4d/output'],
                                      [128, 256, 160, 320, 32, 128]))
    net['pool4/3x3_s2'] = PoolLayer(
      net['inception_4e/output'], pool_size=3, stride=2, ignore_border=False)

    net.update(build_inception_module('inception_5a',
                                      net['pool4/3x3_s2'],
                                      [128, 256, 160, 320, 32, 128]))
    net.update(build_inception_module('inception_5b',
                                      net['inception_5a/output'],
                                      [128, 384, 192, 384, 48, 128]))

    net['pool5/7x7_s1'] = GlobalPoolLayer(net['inception_5b/output'])
    net['loss3/classifier'] = DenseLayer(net['pool5/7x7_s1'],
                                         num_units=1000,
                                         nonlinearity=linear)
    net['prob'] = NonlinearityLayer(net['loss3/classifier'],
                                    nonlinearity=softmax)
    return net 

# 需要导入模块: from lasagne import layers [as 别名]
# 或者: from lasagne.layers import GlobalPoolLayer [as 别名]
def ResNet_BottleNeck_FullPreActivation(input_shape=(None, 3, PIXELS, PIXELS), input_var=None, n_classes=10, n=18):
    '''
    Adapted from https://github.com/Lasagne/Recipes/tree/master/papers/deep_residual_learning.
    Tweaked to be consistent with 'Identity Mappings in Deep Residual Networks', Kaiming He et al. 2016 (https://arxiv.org/abs/1603.05027)

    Judging from https://github.com/KaimingHe/resnet-1k-layers/blob/master/resnet-pre-act.lua.
    Number of filters go 16 -> 64 -> 128 -> 256

    Forumala to figure out depth: 9n + 2
    '''

    # Building the network
    l_in = InputLayer(shape=input_shape, input_var=input_var)

    # first layer, output is 16x16x16
    l = batch_norm(ConvLayer(l_in, num_filters=16, filter_size=(3, 3), stride=(1, 1), nonlinearity=rectify, pad='same', W=he_norm))

    # first stack of residual blocks, output is 64x16x16
    l = residual_bottleneck_block(l, first=True)
    for _ in range(1, n):
        l = residual_bottleneck_block(l)

    # second stack of residual blocks, output is 128x8x8
    l = residual_bottleneck_block(l, increase_dim=True)
    for _ in range(1, n):
        l = residual_bottleneck_block(l)

    # third stack of residual blocks, output is 256x4x4
    l = residual_bottleneck_block(l, increase_dim=True)
    for _ in range(1, n):
        l = residual_bottleneck_block(l)

    bn_post_conv = BatchNormLayer(l)
    bn_post_relu = NonlinearityLayer(bn_post_conv, rectify)

    # average pooling
    avg_pool = GlobalPoolLayer(bn_post_relu)

    # fully connected layer
    network = DenseLayer(avg_pool, num_units=n_classes, W=HeNormal(), nonlinearity=softmax)

    return network 

# 需要导入模块: from lasagne import layers [as 别名]
# 或者: from lasagne.layers import GlobalPoolLayer [as 别名]
def ResNet_FullPre_Wide(input_shape=(None, 3, PIXELS, PIXELS), input_var=None, n_classes=10, n=6, k=4):
    """
    Adapted from https://github.com/Lasagne/Recipes/tree/master/papers/deep_residual_learning.

    Tweaked to be consistent with 'Identity Mappings in Deep Residual Networks', Kaiming He et al. 2016 (https://arxiv.org/abs/1603.05027)

    And 'Wide Residual Networks', Sergey Zagoruyko, Nikos Komodakis 2016 (http://arxiv.org/pdf/1605.07146v1.pdf)

    Depth = 6n + 2
    """
    n_filters = {0: 16, 1: 16*k, 2: 32*k, 3: 64*k}

    # Building the network
    l_in = InputLayer(shape=input_shape, input_var=input_var)

    # first layer, output is 16 x 64 x 64
    l = batch_norm(ConvLayer(l_in, num_filters=n_filters[0], filter_size=(3, 3), stride=(1, 1), nonlinearity=rectify, pad='same', W=he_norm))

    # first stack of residual blocks, output is 32 x 64 x 64
    l = residual_wide_block(l, first=True, filters=n_filters[1])
    for _ in range(1, n):
        l = residual_wide_block(l, filters=n_filters[1])

    # second stack of residual blocks, output is 64 x 32 x 32
    l = residual_wide_block(l, increase_dim=True, filters=n_filters[2])
    for _ in range(1, (n+2)):
        l = residual_wide_block(l, filters=n_filters[2])

    # third stack of residual blocks, output is 128 x 16 x 16
    l = residual_wide_block(l, increase_dim=True, filters=n_filters[3])
    for _ in range(1, (n+2)):
        l = residual_wide_block(l, filters=n_filters[3])

    bn_post_conv = BatchNormLayer(l)
    bn_post_relu = NonlinearityLayer(bn_post_conv, rectify)

    # average pooling
    avg_pool = GlobalPoolLayer(bn_post_relu)

    # fully connected layer
    network = DenseLayer(avg_pool, num_units=n_classes, W=HeNormal(), nonlinearity=softmax)

    return network 

# 需要导入模块: from lasagne import layers [as 别名]
# 或者: from lasagne.layers import GlobalPoolLayer [as 别名]
def build_resnet_model():

    log.i('BUILDING RESNET MODEL...')

    # Random Seed
    lasagne_random.set_rng(cfg.getRandomState())

    # Input layer for images
    net = l.InputLayer((None, cfg.IM_DIM, cfg.IM_SIZE[1], cfg.IM_SIZE[0]))

    # First Convolution
    net = l.Conv2DLayer(net,
                        num_filters=cfg.FILTERS[0],
                        filter_size=cfg.KERNEL_SIZES[0],
                        pad='same',
                        W=initialization(cfg.NONLINEARITY),
                        nonlinearity=None)
    
    log.i(("\tFIRST CONV OUT SHAPE:", l.get_output_shape(net), "LAYER:", len(l.get_all_layers(net)) - 1))

    # Residual Stacks
    for i in range(0, len(cfg.FILTERS)):
        net = resblock(net, filters=cfg.FILTERS[i] * cfg.RESNET_K, kernel_size=cfg.KERNEL_SIZES[i], stride=2, num_groups=cfg.NUM_OF_GROUPS[i])
        for _ in range(1, cfg.RESNET_N):
            net = resblock(net, filters=cfg.FILTERS[i] * cfg.RESNET_K, kernel_size=cfg.KERNEL_SIZES[i], num_groups=cfg.NUM_OF_GROUPS[i], preactivated=False)
        log.i(("\tRES STACK", i + 1, "OUT SHAPE:", l.get_output_shape(net), "LAYER:", len(l.get_all_layers(net)) - 1))
        
    # Post Activation
    net = batch_norm(net)
    net = l.NonlinearityLayer(net, nonlinearity=nonlinearity(cfg.NONLINEARITY))
        
    # Pooling
    net = l.GlobalPoolLayer(net)
    log.i(("\tFINAL POOLING SHAPE:", l.get_output_shape(net), "LAYER:", len(l.get_all_layers(net)) - 1))

    # Classification Layer    
    net = l.DenseLayer(net, len(cfg.CLASSES), nonlinearity=nonlinearity('identity'), W=initialization('identity'))
    net = l.NonlinearityLayer(net, nonlinearity=nonlinearity('softmax'))

    log.i(("\tFINAL NET OUT SHAPE:", l.get_output_shape(net), "LAYER:", len(l.get_all_layers(net))))
    log.i("...DONE!")

    # Model stats
    log.i(("MODEL HAS", (sum(hasattr(layer, 'W') for layer in l.get_all_layers(net))), "WEIGHTED LAYERS"))
    log.i(("MODEL HAS", l.count_params(net), "PARAMS"))

    return net

################## PASPBERRY PI NET #####################