Python tflib.param方法代碼示例

本文整理匯總了Python中tflib.param方法的典型用法代碼示例。如果您正苦於以下問題：Python tflib.param方法的具體用法？Python tflib.param怎麽用？Python tflib.param使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類tflib的用法示例。

在下文中一共展示了tflib.param方法的7個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。

示例1: Layernorm

# 需要導入模塊: import tflib [as 別名]
# 或者: from tflib import param [as 別名]
def Layernorm(name, norm_axes, inputs):
    mean, var = tf.nn.moments(inputs, norm_axes, keep_dims=True)

    # Assume the 'neurons' axis is the first of norm_axes. This is the case for fully-connected and BCHW conv layers.
    n_neurons = inputs.get_shape().as_list()[norm_axes[0]]

    offset = lib.param(name+'.offset', np.zeros(n_neurons, dtype='float32'))
    scale = lib.param(name+'.scale', np.ones(n_neurons, dtype='float32'))

    # Add broadcasting dims to offset and scale (e.g. BCHW conv data)
    offset = tf.reshape(offset, [-1] + [1 for i in xrange(len(norm_axes)-1)])
    scale = tf.reshape(scale, [-1] + [1 for i in xrange(len(norm_axes)-1)])

    result = tf.nn.batch_normalization(inputs, mean, var, offset, scale, 1e-5)

    return result

開發者ID:igul222，項目名稱:improved_wgan_training，代碼行數:18，代碼來源:layernorm.py

示例2: Layernorm

# 需要導入模塊: import tflib [as 別名]
# 或者: from tflib import param [as 別名]
def Layernorm(name, norm_axes, inputs):
    mean, var = tf.nn.moments(inputs, norm_axes, keep_dims=True)

    # Assume the 'neurons' axis is the first of norm_axes. This is the case for fully-connected and BCHW conv layers.
    n_neurons = inputs.get_shape().as_list()[norm_axes[0]]

    offset = lib.param(name+'.offset', np.zeros(n_neurons, dtype='float32'))
    #offset = np.zeros(n_neurons, dtype='float32')
    scale = lib.param(name+'.scale', np.ones(n_neurons, dtype='float32'))
    #scale = np.ones(n_neurons, dtype='float32')
    # Add broadcasting dims to offset and scale (e.g. BCHW conv data)
    offset = tf.reshape(offset, [-1] + [1 for i in range(len(norm_axes)-1)])
    scale = tf.reshape(scale, [-1] + [1 for i in range(len(norm_axes)-1)])

    result = tf.nn.batch_normalization(inputs, mean, var, offset, scale, 1e-5)

    return result

開發者ID:WuChenshen，項目名稱:MeRGAN，代碼行數:19，代碼來源:layernorm.py

示例3: Batchnorm

# 需要導入模塊: import tflib [as 別名]
# 或者: from tflib import param [as 別名]
def Batchnorm(name, axes, inputs, is_training=None, stats_iter=None, update_moving_stats=True, fused=True, labels=None, n_labels=None):
    """conditional batchnorm (dumoulin et al 2016) for BCHW conv filtermaps"""
    if axes != [0,2,3]:
        raise Exception('unsupported')
    #pdb.set_trace()
    mean, var = tf.nn.moments(inputs, axes, keep_dims=True)
    shape = mean.get_shape().as_list() # shape is [1,n,1,1]
    offset_m = lib.param(name+'.offset', np.zeros([n_labels,shape[1]], dtype='float32'))
    scale_m = lib.param(name+'.scale', np.ones([n_labels,shape[1]], dtype='float32'))
    moving_mean_m = lib.param(name+'.moving_mean', np.zeros([n_labels,shape[1]], dtype='float32'), trainable=False)
    moving_variance_m = lib.param(name+'.moving_variance', np.ones([n_labels,shape[1]], dtype='float32'), trainable=False)

    offset = tf.nn.embedding_lookup(offset_m, labels)
    scale = tf.nn.embedding_lookup(scale_m, labels)
    result = tf.nn.batch_normalization(inputs, mean, var, offset[:,:,None,None], scale[:,:,None,None], 1e-5)
    return result

開發者ID:WuChenshen，項目名稱:MeRGAN，代碼行數:18，代碼來源:cond_batchnorm.py

示例4: Layernorm

# 需要導入模塊: import tflib [as 別名]
# 或者: from tflib import param [as 別名]
def Layernorm(name, norm_axes, inputs):
    mean, var = tf.nn.moments(inputs, norm_axes, keep_dims=True)

    # Assume the 'neurons' axis is the first of norm_axes. This is the case for fully-connected and BCHW conv layers.
    n_neurons = inputs.get_shape().as_list()[norm_axes[0]]

    offset = lib.param(name+'.offset', np.zeros(n_neurons, dtype='float32'))
    scale = lib.param(name+'.scale', np.ones(n_neurons, dtype='float32'))

    # Add broadcasting dims to offset and scale (e.g. BCHW conv data)
    offset = tf.reshape(offset, [-1] + [1 for i in xrange(len(norm_axes)-1)])
    scale = tf.reshape(scale, [-1] + [1 for i in xrange(len(norm_axes)-1)])

    result = tf.nn.batch_normalization(inputs, mean, var, offset, scale, 1e-5)

    return result

# not working yet

開發者ID:alex-sage，項目名稱:logo-gen，代碼行數:20，代碼來源:layernorm.py

示例5: Layernorm_cond

# 需要導入模塊: import tflib [as 別名]
# 或者: from tflib import param [as 別名]
def Layernorm_cond(name, norm_axes, inputs, labels, n_labels):
    mean, var = tf.nn.moments(inputs, norm_axes, keep_dims=True)

    # Assume the 'neurons' axis is the first of norm_axes. This is the case for fully-connected and BCHW conv layers.
    n_neurons = inputs.get_shape().as_list()[norm_axes[0]]

    offset_m = lib.param(name+'.offset', np.zeros([n_labels,n_neurons], dtype='float32'))
    scale_m = lib.param(name+'.scale', np.ones([n_labels,n_neurons], dtype='float32'))
    offset = tf.nn.embedding_lookup(offset_m, labels)
    scale = tf.nn.embedding_lookup(scale_m, labels)

    # Add broadcasting dims to offset and scale (e.g. BCHW conv data)
    offset = tf.reshape(offset, [-1] + [1 for i in xrange(len(norm_axes)-1)])
    scale = tf.reshape(scale, [-1] + [1 for i in xrange(len(norm_axes)-1)])

    result = tf.nn.batch_normalization(inputs, mean, var, offset, scale, 1e-5)

    return result

開發者ID:alex-sage，項目名稱:logo-gen，代碼行數:20，代碼來源:layernorm.py

示例6: Layernorm

# 需要導入模塊: import tflib [as 別名]
# 或者: from tflib import param [as 別名]
def Layernorm(name, norm_axes, inputs):
    mean, var = tf.nn.moments(inputs, norm_axes, keep_dims=True)

    # Assume the 'neurons' axis is the first of norm_axes. This is the case for fully-connected and BCHW conv layers.
    n_neurons = inputs.get_shape().as_list()[norm_axes[0]]

    offset = lib.param(name+'.offset', np.zeros(n_neurons, dtype='float32'))
    scale = lib.param(name+'.scale', np.ones(n_neurons, dtype='float32'))

    # Add broadcasting dims to offset and scale (e.g. BCHW conv data)
    offset = tf.reshape(offset, [-1] + [1 for i in range(len(norm_axes)-1)])
    scale = tf.reshape(scale, [-1] + [1 for i in range(len(norm_axes)-1)])

    result = tf.nn.batch_normalization(inputs, mean, var, offset, scale, 1e-5)

    return result

開發者ID:YuguangTong，項目名稱:improved_wgan_training，代碼行數:18，代碼來源:layernorm.py

示例7: Batchnorm

# 需要導入模塊: import tflib [as 別名]
# 或者: from tflib import param [as 別名]
def Batchnorm(name, axes, inputs, is_training=None, stats_iter=None, update_moving_stats=True, fused=True, labels=None, n_labels=None):
    """conditional batchnorm (dumoulin et al 2016) for BCHW conv filtermaps"""
    if axes != [0,2,3]:
        raise Exception('unsupported')
    mean, var = tf.nn.moments(inputs, axes, keep_dims=True)
    shape = mean.get_shape().as_list() # shape is [1,n,1,1]
    offset_m = lib.param(name+'.offset', np.zeros([n_labels,shape[1]], dtype='float32'))
    scale_m = lib.param(name+'.scale', np.ones([n_labels,shape[1]], dtype='float32'))
    offset = tf.nn.embedding_lookup(offset_m, labels)
    scale = tf.nn.embedding_lookup(scale_m, labels)
    result = tf.nn.batch_normalization(inputs, mean, var, offset[:,:,None,None], scale[:,:,None,None], 1e-5)
    return result

開發者ID:igul222，項目名稱:improved_wgan_training，代碼行數:14，代碼來源:cond_batchnorm.py

注：本文中的tflib.param方法示例由純淨天空整理自Github/MSDocs等開源代碼及文檔管理平台，相關代碼片段篩選自各路編程大神貢獻的開源項目，源碼版權歸原作者所有，傳播和使用請參考對應項目的License；未經允許，請勿轉載。