Python keras.backend.std() Examples
The following are 17 code examples for showing how to use keras.backend.std(). These examples are extracted from open source projects. 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 check out the related API usage on the sidebar.
You may also want to check out all available functions/classes of the module
keras.backend
, or try the search function
.
Example 1
Project: keras-utility-layer-collection Author: zimmerrol File: layer_normalization.py License: MIT License | 6 votes |
def call(self, x): mean = K.mean(x, axis=-1) std = K.std(x, axis=-1) if len(x.shape) == 3: mean = K.permute_dimensions( K.repeat(mean, x.shape.as_list()[-1]), [0,2,1] ) std = K.permute_dimensions( K.repeat(std, x.shape.as_list()[-1]), [0,2,1] ) elif len(x.shape) == 2: mean = K.reshape( K.repeat_elements(mean, x.shape.as_list()[-1], 0), (-1, x.shape.as_list()[-1]) ) std = K.reshape( K.repeat_elements(mean, x.shape.as_list()[-1], 0), (-1, x.shape.as_list()[-1]) ) return self._g * (x - mean) / (std + self._epsilon) + self._b
Example 2
Project: Coloring-greyscale-images Author: emilwallner File: instance_normalization.py License: MIT License | 6 votes |
def call(self, inputs, training=None): input_shape = K.int_shape(inputs) reduction_axes = list(range(0, len(input_shape))) if (self.axis is not None): del reduction_axes[self.axis] del reduction_axes[0] mean = K.mean(inputs, reduction_axes, keepdims=True) stddev = K.std(inputs, reduction_axes, keepdims=True) + self.epsilon normed = (inputs - mean) / stddev broadcast_shape = [1] * len(input_shape) if self.axis is not None: broadcast_shape[self.axis] = input_shape[self.axis] if self.scale: broadcast_gamma = K.reshape(self.gamma, broadcast_shape) normed = normed * broadcast_gamma if self.center: broadcast_beta = K.reshape(self.beta, broadcast_shape) normed = normed + broadcast_beta return normed
Example 3
Project: se_relativisticgan Author: deepakbaby File: normalizations.py License: MIT License | 6 votes |
def call(self, inputs, training=None): input_shape = K.int_shape(inputs) reduction_axes = list(range(0, len(input_shape))) if (self.axis is not None): del reduction_axes[self.axis] del reduction_axes[0] mean = K.mean(inputs, reduction_axes, keepdims=True) stddev = K.std(inputs, reduction_axes, keepdims=True) + self.epsilon normed = (inputs - mean) / stddev broadcast_shape = [1] * len(input_shape) if self.axis is not None: broadcast_shape[self.axis] = input_shape[self.axis] if self.scale: broadcast_gamma = K.reshape(self.gamma, broadcast_shape) normed = normed * broadcast_gamma if self.center: broadcast_beta = K.reshape(self.beta, broadcast_shape) normed = normed + broadcast_beta return normed
Example 4
Project: keras-contrib Author: keras-team File: instancenormalization.py License: MIT License | 6 votes |
def call(self, inputs, training=None): input_shape = K.int_shape(inputs) reduction_axes = list(range(0, len(input_shape))) if self.axis is not None: del reduction_axes[self.axis] del reduction_axes[0] mean = K.mean(inputs, reduction_axes, keepdims=True) stddev = K.std(inputs, reduction_axes, keepdims=True) + self.epsilon normed = (inputs - mean) / stddev broadcast_shape = [1] * len(input_shape) if self.axis is not None: broadcast_shape[self.axis] = input_shape[self.axis] if self.scale: broadcast_gamma = K.reshape(self.gamma, broadcast_shape) normed = normed * broadcast_gamma if self.center: broadcast_beta = K.reshape(self.beta, broadcast_shape) normed = normed + broadcast_beta return normed
Example 5
Project: keras-examples Author: aidiary File: dream1.py License: MIT License | 6 votes |
def render_naive(layer_name, filter_index, img0=img_noise, iter_n=20, step=1.0): if layer_name not in layer_dict: print("ERROR: invalid layer name: %s" % layer_name) return layer = layer_dict[layer_name] print("{} < {}".format(filter_index, layer.output_shape[-1])) activation = K.mean(layer.output[:, :, :, filter_index]) grads = K.gradients(activation, input_tensor)[0] # DropoutやBNを含むネットワークはK.learning_phase()が必要 iterate = K.function([input_tensor, K.learning_phase()], [activation, grads]) img = img0.copy() for i in range(iter_n): # 学習はしないので0を入力 activation_value, grads_value = iterate([img, 0]) grads_value /= K.std(grads_value) + 1e-8 img += grads_value * step print(i, activation_value)
Example 6
Project: sam Author: marcellacornia File: models.py License: MIT License | 6 votes |
def nss(y_true, y_pred): max_y_pred = K.repeat_elements(K.expand_dims(K.repeat_elements(K.expand_dims(K.max(K.max(y_pred, axis=2), axis=2)), shape_r_out, axis=-1)), shape_c_out, axis=-1) y_pred /= max_y_pred y_pred_flatten = K.batch_flatten(y_pred) y_mean = K.mean(y_pred_flatten, axis=-1) y_mean = K.repeat_elements(K.expand_dims(K.repeat_elements(K.expand_dims(K.expand_dims(y_mean)), shape_r_out, axis=-1)), shape_c_out, axis=-1) y_std = K.std(y_pred_flatten, axis=-1) y_std = K.repeat_elements(K.expand_dims(K.repeat_elements(K.expand_dims(K.expand_dims(y_std)), shape_r_out, axis=-1)), shape_c_out, axis=-1) y_pred = (y_pred - y_mean) / (y_std + K.epsilon()) return -(K.sum(K.sum(y_true * y_pred, axis=2), axis=2) / K.sum(K.sum(y_true, axis=2), axis=2)) # Gaussian priors initialization
Example 7
Project: costar_plan Author: jhu-lcsr File: instance_normalization.py License: Apache License 2.0 | 6 votes |
def call(self, inputs, training=None): input_shape = K.int_shape(inputs) reduction_axes = list(range(0, len(input_shape))) if (self.axis is not None): del reduction_axes[self.axis] del reduction_axes[0] mean = K.mean(inputs, reduction_axes, keepdims=True) stddev = K.std(inputs, reduction_axes, keepdims=True) + self.epsilon normed = (inputs - mean) / stddev broadcast_shape = [1] * len(input_shape) if self.axis is not None: broadcast_shape[self.axis] = input_shape[self.axis] if self.scale: broadcast_gamma = K.reshape(self.gamma, broadcast_shape) normed = normed * broadcast_gamma if self.center: broadcast_beta = K.reshape(self.beta, broadcast_shape) normed = normed + broadcast_beta return normed
Example 8
Project: faceswap Author: deepfakes File: layers.py License: GNU General Public License v3.0 | 6 votes |
def call(self, inputs): """This is where the layer's logic lives. Parameters ---------- inputs: tensor Input tensor, or list/tuple of input tensors kwargs: dict Additional keyword arguments Returns ------- tensor A tensor or list/tuple of tensors """ if self.data_format == 'channels_last': pooled = K.std(inputs, axis=[1, 2]) else: pooled = K.std(inputs, axis=[2, 3]) return pooled
Example 9
Project: StyleGAN-Keras Author: manicman1999 File: AdaIN.py License: MIT License | 6 votes |
def call(self, inputs, training=None): input_shape = K.int_shape(inputs[0]) reduction_axes = list(range(0, len(input_shape))) beta = inputs[1] gamma = inputs[2] if self.axis is not None: del reduction_axes[self.axis] del reduction_axes[0] mean = K.mean(inputs[0], reduction_axes, keepdims=True) stddev = K.std(inputs[0], reduction_axes, keepdims=True) + self.epsilon normed = (inputs[0] - mean) / stddev return normed * gamma + beta
Example 10
Project: srcnn Author: qobilidop File: metrics.py License: MIT License | 6 votes |
def ssim(y_true, y_pred): """structural similarity measurement system.""" ## K1, K2 are two constants, much smaller than 1 K1 = 0.04 K2 = 0.06 ## mean, std, correlation mu_x = K.mean(y_pred) mu_y = K.mean(y_true) sig_x = K.std(y_pred) sig_y = K.std(y_true) sig_xy = (sig_x * sig_y) ** 0.5 ## L, number of pixels, C1, C2, two constants L = 33 C1 = (K1 * L) ** 2 C2 = (K2 * L) ** 2 ssim = (2 * mu_x * mu_y + C1) * (2 * sig_xy * C2) * 1.0 / ((mu_x ** 2 + mu_y ** 2 + C1) * (sig_x ** 2 + sig_y ** 2 + C2)) return ssim
Example 11
Project: dts Author: albertogaspar File: losses.py License: MIT License | 5 votes |
def nrmse_b(y_true, y_pred): " If this value is larger than 1, you 'd obtain a better model by simply generating a random time series " \ "of the same mean and standard deviation as Y." return K.sqrt(K.mean(K.sum(K.square(y_true - y_pred)))) / K.std(K.identity(y_true))
Example 12
Project: graph-representation-learning Author: vuptran File: ae.py License: MIT License | 5 votes |
def mvn(tensor): """Per row mean-variance normalization.""" epsilon = 1e-6 mean = K.mean(tensor, axis=1, keepdims=True) std = K.std(tensor, axis=1, keepdims=True) mvn = (tensor - mean) / (std + epsilon) return mvn
Example 13
Project: faceswap Author: deepfakes File: losses.py License: GNU General Public License v3.0 | 5 votes |
def gmsd_loss(y_true, y_pred): """ Gradient Magnitude Similarity Deviation Loss. Improved image quality metric over MS-SSIM with easier calculations Parameters ---------- y_true: tensor or variable The ground truth value y_pred: tensor or variable The predicted value Returns ------- tensor The loss value References ---------- http://www4.comp.polyu.edu.hk/~cslzhang/IQA/GMSD/GMSD.htm https://arxiv.org/ftp/arxiv/papers/1308/1308.3052.pdf """ true_edge = scharr_edges(y_true, True) pred_edge = scharr_edges(y_pred, True) ephsilon = 0.0025 upper = 2.0 * true_edge * pred_edge lower = K.square(true_edge) + K.square(pred_edge) gms = (upper + ephsilon) / (lower + ephsilon) gmsd = K.std(gms, axis=(1, 2, 3), keepdims=True) gmsd = K.squeeze(gmsd, axis=-1) return gmsd # Gaussian Blur is here as it is only used for losses. # It was previously kept in lib/model/masks but the import of keras backend # breaks plaidml
Example 14
Project: faceswap Author: deepfakes File: normalization.py License: GNU General Public License v3.0 | 5 votes |
def call(self, inputs, training=None): # pylint:disable=arguments-differ,unused-argument """This is where the layer's logic lives. Parameters ---------- inputs: tensor Input tensor, or list/tuple of input tensors Returns ------- tensor A tensor or list/tuple of tensors """ input_shape = K.int_shape(inputs) reduction_axes = list(range(0, len(input_shape))) if self.axis is not None: del reduction_axes[self.axis] del reduction_axes[0] mean = K.mean(inputs, reduction_axes, keepdims=True) stddev = K.std(inputs, reduction_axes, keepdims=True) + self.epsilon normed = (inputs - mean) / stddev broadcast_shape = [1] * len(input_shape) if self.axis is not None: broadcast_shape[self.axis] = input_shape[self.axis] if self.scale: broadcast_gamma = K.reshape(self.gamma, broadcast_shape) normed = normed * broadcast_gamma if self.center: broadcast_beta = K.reshape(self.beta, broadcast_shape) normed = normed + broadcast_beta return normed
Example 15
Project: StyleGAN-Keras Author: manicman1999 File: AdaIN.py License: MIT License | 5 votes |
def call(self, inputs, training=None): input_shape = K.int_shape(inputs[0]) beta = inputs[1] gamma = inputs[2] reduction_axes = [0, 1, 2] mean = K.mean(inputs[0], reduction_axes, keepdims=True) stddev = K.std(inputs[0], reduction_axes, keepdims=True) + self.epsilon normed = (inputs[0] - mean) / stddev return normed * gamma + beta
Example 16
Project: CIKM-AnalytiCup-2018 Author: zake7749 File: layers.py License: Apache License 2.0 | 5 votes |
def call(self, x): mean = K.mean(x, axis=-1, keepdims=True) std = K.std(x, axis=-1, keepdims=True) return self.gamma * (x - mean) / (std + self.eps) + self.beta
Example 17
Project: transformer-keras Author: GlassyWing File: core.py License: Apache License 2.0 | 5 votes |
def call(self, x, **kwargs): mean = K.mean(x, axis=-1, keepdims=True) std = K.std(x, axis=-1, keepdims=True) return self.gamma * (x - mean) / (std + self.eps) + self.beta