SYMBOL INDEX (412 symbols across 9 files)

FILE: code/chapter 11.py
  function cal_conf_matrix (line 10) | def cal_conf_matrix(labels, preds):
  function cal_PRF1 (line 30) | def cal_PRF1(labels, preds):
  function cal_PRcurve (line 41) | def cal_PRcurve(labels, preds):
  function cal_ROCcurve (line 62) | def cal_ROCcurve(labels, preds):
  function timeit (line 84) | def timeit(func):
  function area_auc (line 98) | def area_auc(labels, preds):
  function naive_auc (line 113) | def naive_auc(labels, preds):
  class KernelBase (line 133) | class KernelBase(ABC):
    method __init__ (line 135) | def __init__(self):
    method _kernel (line 141) | def _kernel(self, X, Y):
    method __call__ (line 144) | def __call__(self, X, Y=None):
    method __str__ (line 147) | def __str__(self):
    method summary (line 152) | def summary(self):
  class RBFKernel (line 160) | class RBFKernel(KernelBase):
    method __init__ (line 162) | def __init__(self, sigma=None):
    method _kernel (line 170) | def _kernel(self, X, Y=None):
  class KernelInitializer (line 189) | class KernelInitializer(object):
    method __init__ (line 191) | def __init__(self, param=None):
    method __call__ (line 194) | def __call__(self):
  class GPRegression (line 205) | class GPRegression:
    method __init__ (line 209) | def __init__(self, kernel="RBFKernel", sigma=1e-10):
    method fit (line 214) | def fit(self, X, y):
    method predict (line 229) | def predict(self, X_star, conf_interval=0.95):
  class BayesianOptimization (line 252) | class BayesianOptimization:
    method __init__ (line 254) | def __init__(self):
    method acquisition_function (line 257) | def acquisition_function(self, Xsamples):
    method opt_acquisition (line 263) | def opt_acquisition(self, X, n_samples=20):
    method fit (line 273) | def fit(self, f, X, y):

FILE: code/chapter5.py
  class NaiveBayes (line 7) | class NaiveBayes():
    method __init__ (line 9) | def __init__(self):
    method fit (line 14) | def fit(self, X, y):
    method _calculate_prior (line 27) | def _calculate_prior(self, c):
    method _calculate_likelihood (line 34) | def _calculate_likelihood(self, mean, var, X):
    method _calculate_probabilities (line 44) | def _calculate_probabilities(self, X):
    method predict (line 57) | def predict(self, X):
    method score (line 61) | def score(self, X, y):
  function Sigmoid (line 68) | def Sigmoid(x):
  class LogisticRegression (line 71) | class LogisticRegression():
    method __init__ (line 73) | def __init__(self, learning_rate=.1):
    method _initialize_parameters (line 78) | def _initialize_parameters(self, X):
    method fit (line 84) | def fit(self, X, y, n_iterations=4000):
    method predict (line 93) | def predict(self, X):
    method score (line 97) | def score(self, X, y):
  function linear_kernel (line 107) | def linear_kernel(**kwargs):
  function polynomial_kernel (line 115) | def polynomial_kernel(power, coef, **kwargs):
  function rbf_kernel (line 123) | def rbf_kernel(gamma, **kwargs):
  class SupportVectorMachine (line 132) | class SupportVectorMachine():
    method __init__ (line 134) | def __init__(self, kernel=linear_kernel, power=4, gamma=None, coef=4):
    method fit (line 144) | def fit(self, X, y):
    method predict (line 192) | def predict(self, X):
    method score (line 204) | def score(self, X, y):
  class KNN (line 211) | class KNN():
    method __init__ (line 213) | def __init__(self, k=10):
    method fit (line 216) | def fit(self, X, y):
    method predict (line 222) | def predict(self, X):
    method predict (line 242) | def predict(self, X):
    method score (line 254) | def score(self, X, y):
  class DecisionNode (line 261) | class DecisionNode():
    method __init__ (line 263) | def __init__(self, feature_i=None, threshold=None,
  function divide_on_feature (line 272) | def divide_on_feature(X, feature_i, threshold):
  class DecisionTree (line 288) | class DecisionTree(object):
    method __init__ (line 290) | def __init__(self, min_samples_split=2, min_impurity=1e-7,
    method fit (line 300) | def fit(self, X, y):
    method _build_tree (line 304) | def _build_tree(self, X, y, current_depth=0):
    method predict_value (line 362) | def predict_value(self, x, tree=None):
    method predict (line 386) | def predict(self, X):
    method score (line 390) | def score(self, X, y):
    method print_tree (line 395) | def print_tree(self, tree=None, indent=" "):
  function calculate_entropy (line 412) | def calculate_entropy(y):
  function calculate_gini (line 423) | def calculate_gini(y):
  class ClassificationTree (line 433) | class ClassificationTree(DecisionTree):
    method _calculate_gini_index (line 437) | def _calculate_gini_index(self, y, y1, y2):
    method _calculate_information_gain (line 449) | def _calculate_information_gain(self, y, y1, y2):
    method _majority_vote (line 460) | def _majority_vote(self, y):
    method fit (line 473) | def fit(self, X, y):
  function calculate_mse (line 479) | def calculate_mse(y):
  function calculate_variance (line 483) | def calculate_variance(y):
  class RegressionTree (line 489) | class RegressionTree(DecisionTree):
    method _calculate_mse (line 493) | def _calculate_mse(self, y, y1, y2):
    method _calculate_variance_reduction (line 505) | def _calculate_variance_reduction(self, y, y1, y2):
    method _mean_of_y (line 517) | def _mean_of_y(self, y):
    method fit (line 524) | def fit(self, X, y):
  class PCA (line 531) | class PCA():
    method __init__ (line 533) | def __init__(self):
    method fit (line 536) | def fit(self, X, n_components):
  function distEclud (line 553) | def distEclud(x,y):
  function randomCent (line 559) | def randomCent(dataSet,k):
  class KMeans (line 570) | class KMeans():
    method __init__ (line 572) | def __init__(self):
    method fit (line 576) | def fit(self, dataSet, k):

FILE: code/chapter6.py
  function sigmoid (line 15) | def sigmoid(x):
  function softmax (line 19) | def softmax(x):
  class LayerBase (line 24) | class LayerBase(ABC):
    method __init__ (line 26) | def __init__(self, optimizer="sgd"):
    method _init_params (line 34) | def _init_params(self, **kwargs):
    method forward (line 41) | def forward(self, X, **kwargs):
    method backward (line 48) | def backward(self, out, **kwargs):
    method flush_gradients (line 54) | def flush_gradients(self):
    method update (line 65) | def update(self):
  class FullyConnected (line 74) | class FullyConnected(LayerBase):
    method __init__ (line 79) | def __init__(self, n_out, acti_fn, init_w, optimizer=None):
    method _init_params (line 96) | def _init_params(self):
    method forward (line 104) | def forward(self, X, retain_derived=True):
    method backward (line 126) | def backward(self, dLda, retain_grads=True):
    method _bwd (line 149) | def _bwd(self, dLda, X):
    method hyperparams (line 162) | def hyperparams(self):
  class ObjectiveBase (line 178) | class ObjectiveBase(ABC):
    method __init__ (line 180) | def __init__(self):
    method loss (line 184) | def loss(self, y_true, y_pred):
    method grad (line 191) | def grad(self, y_true, y_pred, **kwargs):
  class SquaredError (line 198) | class SquaredError(ObjectiveBase):
    method __init__ (line 202) | def __init__(self):
    method __call__ (line 205) | def __call__(self, y_true, y_pred):
    method __str__ (line 208) | def __str__(self):
    method loss (line 212) | def loss(y_true, y_pred):
    method grad (line 222) | def grad(y_true, y_pred, z, acti_fn):
  class CrossEntropy (line 227) | class CrossEntropy(ObjectiveBase):
    method __init__ (line 231) | def __init__(self):
    method __call__ (line 234) | def __call__(self, y_true, y_pred):
    method __str__ (line 237) | def __str__(self):
    method loss (line 241) | def loss(y_true, y_pred):
    method grad (line 253) | def grad(y_true, y_pred):
  function minibatch (line 259) | def minibatch(X, batchsize=256, shuffle=True):
  class DFN (line 277) | class DFN(object):
    method __init__ (line 279) | def __init__(
    method _set_params (line 294) | def _set_params(self):
    method forward (line 314) | def forward(self, X_train):
    method backward (line 322) | def backward(self, grad):
    method update (line 330) | def update(self):
    method flush_gradients (line 338) | def flush_gradients(self, curr_loss=None):
    method fit (line 345) | def fit(self, X_train, y_train, n_epochs=20, batch_size=64, verbose=Fa...
    method evaluate (line 389) | def evaluate(self, X_test, y_test, batch_size=128):
    method hyperparams (line 402) | def hyperparams(self):

FILE: code/chapter7.py
  class RegularizerBase (line 9) | class RegularizerBase(ABC):
    method __init__ (line 11) | def __init__(self, **kwargs):
    method loss (line 15) | def loss(self, **kwargs):
    method grad (line 19) | def grad(self, **kwargs):
  class L1Regularizer (line 22) | class L1Regularizer(RegularizerBase):
    method __init__ (line 24) | def __init__(self, lambd=0.001):
    method loss (line 28) | def loss(self, params):
    method grad (line 36) | def grad(self, params):
  class L2Regularizer (line 41) | class L2Regularizer(RegularizerBase):
    method __init__ (line 43) | def __init__(self, lambd=0.001):
    method loss (line 47) | def loss(self, params):
    method grad (line 53) | def grad(self, params):
  class RegularizerInitializer (line 58) | class RegularizerInitializer(object):
    method __init__ (line 60) | def __init__(self, regular_name="l2"):
    method __call__ (line 63) | def __call__(self):
  class Image (line 77) | class Image(object):
    method __init__ (line 79) | def __init__(self, image):
    method _set_params (line 82) | def _set_params(self, image):
    method Translation (line 88) | def Translation(self, delta_x, delta_y):
    method Resize (line 100) | def Resize(self, alpha):
    method HorMirror (line 111) | def HorMirror(self):
    method VerMirror (line 119) | def VerMirror(self):
    method Rotate (line 127) | def Rotate(self, angle):
    method operate (line 138) | def operate(self):
    method __call__ (line 153) | def __call__(self, act):
  function early_stopping (line 171) | def early_stopping(valid):
  function bootstrap_sample (line 183) | def bootstrap_sample(X, Y):
  class BaggingModel (line 188) | class BaggingModel(object):
    method __init__ (line 190) | def __init__(self, n_models):
    method fit (line 198) | def fit(self, X, Y):
    method predict (line 207) | def predict(self, X):
    method _vote (line 211) | def _vote(self, predictions):
    method evaluate (line 215) | def evaluate(self, X_test, y_test):
  class Dropout (line 224) | class Dropout(ABC):
    method __init__ (line 226) | def __init__(self, wrapped_layer, p):
    method _init_wrapper_params (line 237) | def _init_wrapper_params(self):
    method flush_gradients (line 241) | def flush_gradients(self):
    method update (line 247) | def update(self):
    method forward (line 253) | def forward(self, X, is_train=True):
    method backward (line 266) | def backward(self, dLda):
    method hyperparams (line 270) | def hyperparams(self):
  function get_random_subsets (line 287) | def get_random_subsets(X, y, n_subsets, replacements=True):
  class Bagging (line 309) | class Bagging():
    method __init__ (line 313) | def __init__(self, n_estimators=100, max_features=None, min_samples_sp...
    method fit (line 330) | def fit(self, X, y):
    method predict (line 338) | def predict(self, X):
    method score (line 352) | def score(self, X, y):
  class RandomForest (line 359) | class RandomForest():
    method __init__ (line 363) | def __init__(self, n_estimators=100, max_features=None, min_samples_sp...
    method fit (line 381) | def fit(self, X, y):
    method predict (line 401) | def predict(self, X):
    method score (line 417) | def score(self, X, y):
  class DecisionStump (line 425) | class DecisionStump():
    method __init__ (line 427) | def __init__(self):
  class Adaboost (line 433) | class Adaboost():
    method __init__ (line 437) | def __init__(self, n_estimators=5):
    method fit (line 441) | def fit(self, X, y):
    method predict (line 489) | def predict(self, X):
    method score (line 504) | def score(self, X, y):
  class Loss (line 511) | class Loss(ABC):
    method __init__ (line 513) | def __init__(self):
    method loss (line 517) | def loss(self, y_true, y_pred):
    method grad (line 521) | def grad(self, y, y_pred):
  class SquareLoss (line 524) | class SquareLoss(Loss):
    method __init__ (line 526) | def __init__(self):
    method loss (line 529) | def loss(self, y, y_pred):
    method grad (line 532) | def grad(self, y, y_pred):
    method hess (line 535) | def hess(self, y, y_pred):
  class CrossEntropyLoss (line 538) | class CrossEntropyLoss(Loss):
    method __init__ (line 540) | def __init__(self):
    method loss (line 543) | def loss(self, y, y_pred):
    method grad (line 546) | def grad(self, y, y_pred):
    method hess (line 549) | def hess(self, y, y_pred):
  function softmax (line 553) | def softmax(x):
  function line_search (line 558) | def line_search(self, y, y_pred, h_pred):
  function to_categorical (line 564) | def to_categorical(x, n_classes=None):
  class GradientBoostingDecisionTree (line 575) | class GradientBoostingDecisionTree(object):
    method __init__ (line 579) | def __init__(self, n_estimators, learning_rate=1, min_samples_split=2,
    method fit (line 594) | def fit(self, X, Y):
    method predict (line 629) | def predict(self, X):
    method score (line 643) | def score(self, X, y):
  class GradientBoostingRegressor (line 649) | class GradientBoostingRegressor(GradientBoostingDecisionTree):
    method __init__ (line 651) | def __init__(self, n_estimators=200, learning_rate=1, min_samples_spli...
  class GradientBoostingClassifier (line 662) | class GradientBoostingClassifier(GradientBoostingDecisionTree):
    method __init__ (line 664) | def __init__(self, n_estimators=200, learning_rate=1, min_samples_spli...
  class XGBoostRegressionTree (line 676) | class XGBoostRegressionTree(DecisionTree):
    method __init__ (line 680) | def __init__(self, min_samples_split=2, min_impurity=1e-7,
    method _split (line 689) | def _split(self, y):
    method _gain (line 695) | def _gain(self, y, y_pred):
    method _gain_by_taylor (line 701) | def _gain_by_taylor(self, y, y1, y2):
    method _approximate_update (line 712) | def _approximate_update(self, y):
    method fit (line 720) | def fit(self, X, y):
  class XGBoost (line 726) | class XGBoost(object):
    method __init__ (line 730) | def __init__(self, n_estimators=200, learning_rate=0.001, min_samples_...
    method fit (line 746) | def fit(self, X, Y):
    method predict (line 783) | def predict(self, X):
    method score (line 797) | def score(self, X, y):
  class XGBRegressor (line 803) | class XGBRegressor(XGBoost):
    method __init__ (line 805) | def __init__(self, n_estimators=200, learning_rate=1, min_samples_spli...
  class XGBClassifier (line 818) | class XGBClassifier(XGBoost):
    method __init__ (line 820) | def __init__(self, n_estimators=200, learning_rate=1, min_samples_spli...

FILE: code/chapter8.py
  class BatchNorm1D (line 11) | class BatchNorm1D(LayerBase):
    method __init__ (line 13) | def __init__(self, momentum=0.9, epsilon=1e-5, optimizer=None):
    method _init_params (line 36) | def _init_params(self):
    method reset_running_stats (line 54) | def reset_running_stats(self):
    method forward (line 58) | def forward(self, X, is_train=True, retain_derived=True):
    method backward (line 94) | def backward(self, dLda, retain_grads=True):
    method _bwd (line 117) | def _bwd(self, dLda, X):
    method hyperparams (line 136) | def hyperparams(self):

FILE: code/chapter9.py
  function calc_pad_dims_sameconv_2D (line 8) | def calc_pad_dims_sameconv_2D(X_shape, out_dim, kernel_shape, stride, di...
  function pad2D (line 52) | def pad2D(X, pad, kernel_shape=None, stride=None, dilation=1):
  function conv2D (line 95) | def conv2D(X, W, stride, pad, dilation=1):
  function _im2col_indices (line 145) | def _im2col_indices(X_shape, fr, fc, p, s, d=1):
  function im2col (line 177) | def im2col(X, W_shape, pad, stride, dilation=1):
  function conv2D_gemm (line 214) | def conv2D_gemm(X, W, stride=0, pad='same', dilation=1):
  class Conv2D (line 256) | class Conv2D(LayerBase):
    method __init__ (line 258) | def __init__(
    method _init_params (line 300) | def _init_params(self):
    method forward (line 310) | def forward(self, X, retain_derived=True):
    method backward (line 341) | def backward(self, dLda, retain_grads=True):
    method hyperparams (line 398) | def hyperparams(self):
  function col2im (line 417) | def col2im(X_col, X_shape, W_shape, pad, stride, dilation=0):
  class Conv2D_gemm (line 452) | class Conv2D_gemm(LayerBase):
    method __init__ (line 454) | def __init__(
    method _init_params (line 496) | def _init_params(self):
    method forward (line 506) | def forward(self, X, retain_derived=True):
    method backward (line 537) | def backward(self, dLda, retain_grads=True):
    method _bwd (line 565) | def _bwd(self, dLda, X, Y):
    method hyperparams (line 586) | def hyperparams(self):
  class Pool2D (line 605) | class Pool2D(LayerBase):
    method __init__ (line 607) | def __init__(self, kernel_shape, stride=1, pad=0, mode="max", optimize...
    method _init_params (line 629) | def _init_params(self):
    method forward (line 633) | def forward(self, X, retain_derived=True):
    method backward (line 678) | def backward(self, dLdy, retain_grads=True):
    method hyperparams (line 729) | def hyperparams(self):
  class Flatten (line 747) | class Flatten(LayerBase):
    method __init__ (line 749) | def __init__(self, keep_dim="first", optimizer=None):
    method _init_params (line 764) | def _init_params(self):
    method forward (line 770) | def forward(self, X, retain_derived=True):
    method backward (line 785) | def backward(self, dLdy, retain_grads=True):
    method hyperparams (line 803) | def hyperparams(self):
  class LeNet (line 815) | class LeNet(object):
    method __init__ (line 817) | def __init__(
    method _set_params (line 859) | def _set_params(self):
    method forward (line 916) | def forward(self, X_train):
    method backward (line 924) | def backward(self, grad):
    method update (line 932) | def update(self):
    method flush_gradients (line 940) | def flush_gradients(self, curr_loss=None):
    method fit (line 947) | def fit(self, X_train, y_train, n_epochs=20, batch_size=64, verbose=Fa...
    method evaluate (line 991) | def evaluate(self, X_test, y_test, batch_size=128):
    method hyperparams (line 1004) | def hyperparams(self):
  class LeNet_gemm (line 1029) | class LeNet_gemm(object):
    method __init__ (line 1031) | def __init__(
    method _set_params (line 1073) | def _set_params(self):
    method forward (line 1130) | def forward(self, X_train):
    method backward (line 1138) | def backward(self, grad):
    method update (line 1146) | def update(self):
    method flush_gradients (line 1154) | def flush_gradients(self, curr_loss=None):
    method fit (line 1161) | def fit(self, X_train, y_train, n_epochs=20, batch_size=64, verbose=Fa...
    method evaluate (line 1205) | def evaluate(self, X_test, y_test, batch_size=128):
    method hyperparams (line 1218) | def hyperparams(self):

FILE: code/method/activation/activation.py
  class ActivationBase (line 6) | class ActivationBase(ABC):
    method __init__ (line 8) | def __init__(self, **kwargs):
    method __call__ (line 11) | def __call__(self, z):
    method forward (line 17) | def forward(self, z):
    method grad (line 21) | def grad(self, x, **kwargs):
  class Sigmoid (line 25) | class Sigmoid(ActivationBase):
    method __init__ (line 30) | def __init__(self):
    method __str__ (line 33) | def __str__(self):
    method forward (line 36) | def forward(self, z):
    method grad (line 39) | def grad(self, x):
  class Tanh (line 43) | class Tanh(ActivationBase):
    method __init__ (line 48) | def __init__(self):
    method __str__ (line 51) | def __str__(self):
    method forward (line 54) | def forward(self, z):
    method grad (line 57) | def grad(self, x):
  class ReLU (line 61) | class ReLU(ActivationBase):
    method __init__ (line 68) | def __init__(self):
    method __str__ (line 71) | def __str__(self):
    method forward (line 74) | def forward(self, z):
    method grad (line 77) | def grad(self, x):
  class LeakyReLU (line 81) | class LeakyReLU(ActivationBase):
    method __init__ (line 88) | def __init__(self, alpha=0.3):
    method __str__ (line 92) | def __str__(self):
    method forward (line 95) | def forward(self, z):
    method grad (line 100) | def grad(self, x):
  class Affine (line 106) | class Affine(ActivationBase):
    method __init__ (line 111) | def __init__(self, slope=1, intercept=0):
    method __str__ (line 116) | def __str__(self):
    method forward (line 119) | def forward(self, z):
    method grad (line 122) | def grad(self, x):
  class SoftPlus (line 126) | class SoftPlus(ActivationBase):
    method __init__ (line 131) | def __init__(self):
    method __str__ (line 134) | def __str__(self):
    method forward (line 137) | def forward(self, z):
    method grad (line 140) | def grad(self, x):
  class ELU (line 144) | class ELU(ActivationBase):
    method __init__ (line 151) | def __init__(self, alpha=1.0):
    method __str__ (line 155) | def __str__(self):
    method forward (line 158) | def forward(self, z):
    method grad (line 161) | def grad(self, x):
  class Exponential (line 165) | class Exponential(ActivationBase):
    method __init__ (line 170) | def __init__(self):
    method __str__ (line 173) | def __str__(self):
    method forward (line 176) | def forward(self, z):
    method grad (line 179) | def grad(self, x):
  class SELU (line 183) | class SELU(ActivationBase):
    method __init__ (line 190) | def __init__(self):
    method __str__ (line 196) | def __str__(self):
    method forward (line 199) | def forward(self, z):
    method grad (line 202) | def grad(self, x):
  class HardSigmoid (line 208) | class HardSigmoid(ActivationBase):
    method __init__ (line 216) | def __init__(self):
    method __str__ (line 219) | def __str__(self):
    method forward (line 222) | def forward(self, z):
    method grad (line 225) | def grad(self, x):
  class ActivationInitializer (line 229) | class ActivationInitializer(object):
    method __init__ (line 231) | def __init__(self, acti_name="affine(slope=1, intercept=0)"):
    method __call__ (line 234) | def __call__(self):

FILE: code/method/optimizer/optimizer.py
  class OptimizerBase (line 6) | class OptimizerBase(ABC):
    method __init__ (line 8) | def __init__(self):
    method __call__ (line 11) | def __call__(self, params, params_grad, params_name):
    method update (line 21) | def update(self, params, params_grad, params_name):
  class SGD (line 25) | class SGD(OptimizerBase):
    method __init__ (line 30) | def __init__(self, lr=0.01):
    method __str__ (line 35) | def __str__(self):
    method update (line 38) | def update(self, params, params_grad, params_name):
    method hyperparams (line 43) | def hyperparams(self):
  class Momentum (line 49) | class Momentum(OptimizerBase):
    method __init__ (line 51) | def __init__(
    method __str__ (line 64) | def __str__(self):
    method update (line 67) | def update(self, param, param_grad, param_name):
    method hyperparams (line 79) | def hyperparams(self):
  class AdaGrad (line 87) | class AdaGrad(OptimizerBase):
    method __init__ (line 89) | def __init__(self, lr=0.001, eps=1e-7, **kwargs):
    method __str__ (line 100) | def __str__(self):
    method update (line 103) | def update(self, param, param_grad, param_name):
    method hyperparams (line 116) | def hyperparams(self):
  class RMSProp (line 124) | class RMSProp(OptimizerBase):
    method __init__ (line 126) | def __init__(
    method __str__ (line 141) | def __str__(self):
    method update (line 146) | def update(self, param, param_grad, param_name):
    method hyperparams (line 160) | def hyperparams(self):
  class AdaDelta (line 169) | class AdaDelta(OptimizerBase):
    method __init__ (line 171) | def __init__(
    method __str__ (line 186) | def __str__(self):
    method update (line 189) | def update(self, param, param_grad, param_name):
    method hyperparams (line 207) | def hyperparams(self):
  class Adam (line 215) | class Adam(OptimizerBase):
    method __init__ (line 217) | def __init__(
    method __str__ (line 239) | def __str__(self):
    method update (line 244) | def update(self, param, param_grad, param_name, cur_loss=None):
    method hyperparams (line 271) | def hyperparams(self):
  class OptimizerInitializer (line 281) | class OptimizerInitializer(ABC):
    method __init__ (line 283) | def __init__(self, opti_name="sgd"):
    method __call__ (line 286) | def __call__(self):

FILE: code/method/weight/weight.py
  function calc_fan (line 6) | def calc_fan(weight_shape):
  class random_uniform (line 24) | class random_uniform:
    method __init__ (line 31) | def __init__(self, b=1.0):
    method __call__ (line 34) | def __call__(self, weight_shape):
  class random_normal (line 38) | class random_normal:
    method __init__ (line 46) | def __init__(self, std=0.01):
    method __call__ (line 49) | def __call__(self, weight_shape):
  class he_uniform (line 74) | class he_uniform:
    method __init__ (line 81) | def __init__(self):
    method __call__ (line 84) | def __call__(self, weight_shape):
  class he_normal (line 90) | class he_normal:
    method __init__ (line 97) | def __init__(self):
    method __call__ (line 100) | def __call__(self, weight_shape):
  class glorot_uniform (line 131) | class glorot_uniform:
    method __init__ (line 139) | def __init__(self, gain=1.0):
    method __call__ (line 142) | def __call__(self, weight_shape):
  class glorot_normal (line 148) | class glorot_normal:
    method __init__ (line 156) | def __init__(self, gain=1.0):
    method __call__ (line 159) | def __call__(self, weight_shape):
  function truncated_normal (line 191) | def truncated_normal(mean, std, out_shape):
  class WeightInitializer (line 209) | class WeightInitializer(object):
    method __init__ (line 211) | def __init__(self, mode="he_normal"):
    method __call__ (line 235) | def __call__(self, weight_shape):