def __init__(self, 
                 my_data_set = "mnist", 
                 n_hidden_layers = 1, 
                 ay_nodes_layers = [0, 100, 0], # array which should have as much elements as n_hidden + 2
                 n_nodes_layer_out = 10,  # expected number of nodes in output layer 
                                                  
                 my_activation_function = "sigmoid", 
                 my_out_function        = "sigmoid",   
                 my_loss_function       = "LogLoss",   
                 
                 n_size_mini_batch = 50,  # number of data elements in a mini-batch 
                 
                 n_epochs      = 1,
                 n_max_batches = -1,  # number of mini-batches to use during epochs - > 0 only for testing 
                                      # a negative value uses all mini-batches 
                 
                 lambda2_reg = 0.1,     # factor for quadratic regularization term 
                 lambda1_reg = 0.0,     # factor for linear regularization term 
                 
                 vect_mode = 'cols', 
                 
                 learn_rate = 0.001,        # the learning rate (often called epsilon in textbooks) 
                 decrease_const = 0.00001,  # a factor for decreasing the learning rate with epochs
                 mom_rate   = 0.0005,       # a factor for momentum learning
                 
                 shuffle_batches = True,    # True: we mix the data for mini-batches in the X-train set at the start of each epoch
                 
                 print_period = 20,         # number of epochs for which to print the costs and the averaged error
                 
                 figs_x1=12.0, figs_x2=8.0, 
                 legend_loc='upper right',
                 
                 b_print_test_data = True
                 
                 ):
        '''
        Initialization of MyANN
        Input: 
            data_set: type of dataset; so far only the "mnist", "mnist_784" datsets are known 
                      We use this information to prepare the input data and learn about the feature dimension. 
                      This info is used in preparing the size of the input layer.     
            n_hidden_layers = number of hidden layers => between input layer 0 and output layer n 
            
            ay_nodes_layers = [0, 100, 0 ] : We set the number of nodes in input layer_0 and the output_layer to zero 
                              Will be set to real number afterwards by infos from the input dataset. 
                              All other numbers are used for the node numbers of the hidden layers.
            n_nodes_out_layer = expected number of nodes in the output layer (is checked); 
                                this number corresponds to the number of categories NC = number of labels to be distinguished
            
            my_activation_function : name of the activation function to use 
            my_out_function : name of the "activation" function of the last layer which produces the output values 
            my_loss_function : name of the "cost" or "loss" function used for optimization 
            
            n_size_mini_batch : Number of elements/samples in a mini-batch of training data 
                                The number of mini-batches will be calculated from this
            
            n_epochs : number of epochs to calculate during training
            n_max_batches : > 0: maximum of mini-batches to use during training 
                      
      < 0: use all mini-batches  
            
            lambda_reg2:    The factor for the quadartic regularization term 
            lambda_reg1:    The factor for the linear regularization term 
            
            vect_mode: Are 1-dim data arrays (vctors) ordered by columns or rows ?
            
            learn rate :     Learning rate - definies by how much we correct weights in the indicated direction of the gradient on the cost hyperplane.
            decrease_const:  Controls a systematic decrease of the learning rate with epoch number 
            mom_const:       Momentum rate. Controls a mixture of the last with the present weight corrections (momentum learning)
            
            shuffle_batches: True => vary composition of mini-batches with each epoch
            
            print_period:    number of periods between printing out some intermediate data 
                             on costs and the averaged error of the last mini-batch   
                       
            
            figs_x1=12.0, figs_x2=8.0 : Standard sizing of plots , 
            legend_loc='upper right': Position of legends in the plots
            
            b_print_test_data: Boolean variable to control the print out of some tests data 
             
         '''
        
        # Array (Python list) of known input data sets 
        self._input_data_sets = ["mnist", "mnist_784", "mnist_keras"]  
        self._my_data_set = my_data_set
        
        # X, y, X_train, y_train, X_test, y_test  
            # will be set by analyze_input_data 
            # X: Input array (2D) - at present status of MNIST image data, only.    
            # y: result (=classification data) [digits represent categories in the case of Mnist]
        self._X       = None 
        self._X_train = None 
        self._X_test  = None   
        self._y       = None 
        self._y_train = None 
        self._y_test  = None
        
        # relevant dimensions 
        # from input data information;  will be set in handle_input_data()
        self._dim_sets     = 0  
        self._dim_features = 0  
        self._n_labels     = 0   # number of unique labels - will be extracted from y-data 
        
        # Img sizes 
        self._dim_img      = 0 # should be sqrt(dim_features) - we assume square like images  
        self._img_h        = 0 
        self._img_w        = 0 
        
        # Layers
        # ------
        # number of hidden layers 
        self._n_hidden_layers = n_hidden_layers
        # Number of total layers 
        self._n_total_layers = 2 + self._n_hidden_layers  
        # Nodes for hidden layers 
        self._ay_nodes_layers = np.array(ay_nodes_layers)
        # Number of nodes in output layer - will be checked against information from target arrays
        self._n_nodes_layer_out = n_nodes_layer_out
        
        # Weights 
        # --------
        # empty List for all weight-matrices for all layer-connections
        # Numbering : 
        # w[0] contains the weight matrix which connects layer 0 (input layer ) to hidden layer 1 
        # w[1] contains the weight matrix which connects layer 1 (input layer ) to (hidden?) layer 2 
        self._li_w = []
        
        # Arrays for encoded output labels - will be set in _encode_all_mnist_labels()
        # -------------------------------
        self._ay_onehot = None
        self._ay_oneval = None
        
        # Known Randomizer methods ( 0: np.random.randint, 1: np.random.uniform )  
        # ------------------
        self.__ay_known_randomizers = [0, 1]

        # Types of activation functions and output functions 
        # ------------------
        self.__ay_activation_functions = ["sigmoid"] # later also relu 
        self.__ay_output_functions     = ["sigmoid"] # later also 
softmax 
        
        # Types of cost functions 
        # ------------------
        self.__ay_loss_functions = ["LogLoss", "MSE" ] # later also other types of cost/loss functions  


        # the following dictionaries will be used for indirect function calls 
        self.__d_activation_funcs = {
            'sigmoid': self._sigmoid, 
            'relu':    self._relu
            }
        self.__d_output_funcs = { 
            'sigmoid': self._sigmoid, 
            'softmax': self._softmax
            }  
        self.__d_loss_funcs = { 
            'LogLoss': self._loss_LogLoss, 
            'MSE': self._loss_MSE
            }  
        # Derivative functions 
        self.__d_D_activation_funcs = {
            'sigmoid': self._D_sigmoid, 
            'relu':    self._D_relu
            }
        self.__d_D_output_funcs = { 
            'sigmoid': self._D_sigmoid, 
            'softmax': self._D_softmax
            }  
        self.__d_D_loss_funcs = { 
            'LogLoss': self._D_loss_LogLoss, 
            'MSE': self._D_loss_MSE
            }  
        
        
        # The following variables will later be set by _check_and set_activation_and_out_functions()            
        
        self._my_act_func  = my_activation_function
        self._my_out_func  = my_out_function
        self._my_loss_func = my_loss_function
        self._act_func = None    
        self._out_func = None    
        self._loss_func = None    
        
        # number of data samples in a mini-batch 
        self._n_size_mini_batch = n_size_mini_batch
        self._n_mini_batches = None  # will be determined by _get_number_of_mini_batches()

        # maximum number of epochs - we set this number to an assumed maximum 
        # - as we shall build a backup and reload functionality for training, this should not be a major problem 
        self._n_epochs = n_epochs
        
        # maximum number of batches to handle ( if < 0 => all!) 
        self._n_max_batches = n_max_batches
        # actual number of batches 
        self._n_batches = None

        # regularization parameters
        self._lambda2_reg = lambda2_reg
        self._lambda1_reg = lambda1_reg
        
        # parameter for momentum learning 
        self._learn_rate = learn_rate
        self._decrease_const = decrease_const
        self._mom_rate   = mom_rate
        self._li_mom = [None] *  self._n_total_layers
        
        # shuffle data in X_train? 
        self._shuffle_batches = shuffle_batches
        
        # epoch period for printing 
        self._print_period = print_period
        
        # book-keeping for epochs and mini-batches 
        # -------------------------------
        # range for epochs - will be set by _prepare-epochs_and_batches() 
        self._rg_idx_epochs = None
        # range for mini-batches 
        self._rg_idx_batches = None
        # dimension of the numpy arrays for book-keeping - will be set in _prepare_epochs_and_batches() 
        self._shape_epochs_batches = None    # (n_epochs, n_batches, 1) 

        # list for error values at outermost layer for minibatches and epochs during training
        # we use a numpy array here because we can redimension it
        self._ay_theta = None
        # list for cost values of mini-batches during training 
        # The list will later be split into sections for epochs 
        self._ay_costs = None
        
        
        # Data elements for back propagation
        # ----------------------------------
        
        # 2-dim array of partial derivatives of the elements of an additive cost function 
        # The derivative is taken with respect to the output results a_j = ay_ANN_out[j]
        # The array dimensions account for nodes and sampls of a 
mini_batch. The array will be set in function 
        # self._initiate_bw_propagation()
        self._ay_delta_out_batch = None
        

        # parameter to allow printing of some test data 
        self._b_print_test_data = b_print_test_data

        # Plot handling 
        # --------------
        # Alternatives to resize plots 
        # 1: just resize figure  2: resize plus create subplots() [figure + axes] 
        self._plot_resize_alternative = 1 
        # Plot-sizing
        self._figs_x1 = figs_x1
        self._figs_x2 = figs_x2
        self._fig = None
        self._ax  = None 
        # alternative 2 does resizing and (!) subplots() 
        self.initiate_and_resize_plot(self._plot_resize_alternative)        
        
        
        # ***********
        # operations 
        # ***********
        
        # check and handle input data 
        self._handle_input_data()
        # set the ANN structure 
        self._set_ANN_structure()
        
        # Prepare epoch and batch-handling - sets ranges, limits num of mini-batches and initializes book-keeping arrays
        self._rg_idx_epochs, self._rg_idx_batches = self._prepare_epochs_and_batches()
        
        # perform training 
        start_c = time.perf_counter()
        self._fit(b_print=True, b_measure_batch_time=False)
        end_c = time.perf_counter()
        print('\n\n ------') 
        print('Total training Time_CPU: ', end_c - start_c) 
        print("\nStopping program regularily")

    ''' -- Method to set the number of batches based on given batch size -- '''
    def _fit(self, b_print = False, b_measure_batch_time = False):
        '''
        Parameters: 
            b_print:                 Do we print intermediate results of the training at all? 
            b_print_period:          For which period of epochs do we print? 
            b_measure_batch_time:    Measure CPU-Time for a batch
        '''
        rg_idx_epochs  = self._rg_idx_epochs 
        rg_idx_batches = self._rg_idx_batches
        if (b_print):    
            print("\nnumber of epochs = " + str(len(rg_idx_epochs)))
            print("max number of batches = " + str(len(rg_idx_batches)))
       
        # loop over epochs
        for idxe in rg_idx_epochs:
            if (b_print and (idxe % self._print_period == 0) ):
                print("\n ---------")
                print("\nStarting epoch " + str(idxe+1))
                
            # sinmple adaption of the learning rate 
            self._learn_rate /= (1.0 + self._decrease_const * idxe)
            
            # shuffle indices for a variation of the mini-batches with each epoch
            if self._shuffle_batches:
                shuffled_index = np.random.permutation(self._dim_sets)
                self._X_train, self._y_train, self._ay_onehot = self._X_train[shuffled_index], self._y_train[shuffled_index], self._ay_onehot[:, shuffled_index]
                
            
            # loop over mini-batches
            for idxb in rg_idx_batches:
                if b_measure_batch_time: 
                    start_0 = time.perf_counter()
                # deal with a mini-batch
                self._handle_mini_batch(num_batch = idxb, num_epoch=idxe, b_print_y_vals = False, b_print = False)
                if b_measure_batch_time: 
                    end_0 = time.perf_counter()
                    print('Time_CPU for batch ' + str(idxb+1), end_0 - start_0) 
                
            if (b_print and (idxe % self._print_period == 0) ):
                print("\ntotal costs of mini_batch = ", self._ay_costs[idxe, idxb])
      
          print("avg total error of mini_batch = ", self._ay_theta[idxe, idxb])
                
        return None

number of epochs = 1500
max number of batches = 120
---------
Starting epoch 1
total costs of mini_batch =  1757.7650929607967
avg total error of mini_batch =  0.17086198431410954
---------
Starting epoch 61
total costs of mini_batch =  511.7001121819204
avg total error of mini_batch =  0.030287362041332373
---------
Starting epoch 121
total costs of mini_batch =  435.2513093033654
avg total error of mini_batch =  0.023445601362614754
----------
Starting epoch 181
total costs of mini_batch =  361.8665831722295
avg total error of mini_batch =  0.018540003201911136
---------
Starting epoch 241
total costs of mini_batch =  293.31230634431023
avg total error of mini_batch =  0.0138237366634751
---------
Starting epoch 301
total costs of mini_batch =  332.70394217467936
avg total error of mini_batch =  0.017697548541363246
---------
Starting epoch 361
total costs of mini_batch =  249.26400606039937
avg total error of mini_batch =  0.011765164578232358
---------
Starting epoch 421
total costs of mini_batch =  240.0503762160913
avg total error of mini_batch =  0.011650843329895542
---------
Starting epoch 481
total costs of mini_batch =  222.89422430417295
avg total error of mini_batch =  0.011503859412784031
---------
Starting epoch 541
total costs of mini_batch =  200.1195962051405
avg total error of mini_batch =  0.009962020519104173
---------
tarting epoch 601
total costs of mini_batch =  206.74753168607685
avg total error of mini_batch =  0.01067995191155135
---------
Starting epoch 661
total costs of mini_batch =  171.14090717705736
avg total error of mini_batch =  0.0077091934178393105
---------
Starting epoch 721
total costs of mini_batch =  158.44967190977957
avg total error of mini_batch =  0.0070760922760890735
---------
Starting epoch 781
total costs of mini_batch =  165.4047453537401
avg total error of mini_batch =  0.008622788115637027
---------
Starting epoch 841
total costs of mini_batch =  140.52762105883642
avg total error of mini_batch =  0.0067360505574077766
---------
Starting epoch 901
total costs of mini_batch =  163.9117184790982
avg total error of mini_batch =  0.007431666926365192
---------
Starting epoch 961
total costs of mini_batch =  126.05539161877512
avg total error of mini_batch =  0.005982378079899406
---------
Starting epoch 1021
total costs of mini_batch =  114.89943308334199
avg total error of mini_batch =  0.005122976288751798
---------
Starting epoch 1081
total costs of mini_batch =  117.22051220670932
avg total error of mini_batch 
=  0.005185936692097749
---------
Starting epoch 1141
total costs of mini_batch =  140.88969853048422
avg total error of mini_batch =  0.007665464508660714
---------
Starting epoch 1201
total costs of mini_batch =  113.27223303239667
avg total error of mini_batch =  0.0059791015452599705
---------
Starting epoch 1261
total costs of mini_batch =  105.55343407063131
avg total error of mini_batch =  0.005000503315756879
---------
Starting epoch 1321
total costs of mini_batch =  130.48116668827038
avg total error of mini_batch =  0.006287118265324945
---------
Starting epoch 1381
total costs of mini_batch =  109.04042315247389
avg total error of mini_batch =  0.005874339148860562
---------
Starting epoch 1441
total costs of mini_batch =  121.01379412127089
avg total error of mini_batch =  0.0065105907117289944
---------
Starting epoch 1461
total costs of mini_batch =  103.08774822996196
avg total error of mini_batch =  0.005299079778792264
---------
Starting epoch 1481
total costs of mini_batch =  106.21334182056928
avg total error of mini_batch =  0.005343967730134955
-------
Total training Time_CPU:  1963.8792177759988

Starting epoch 1001
total costs of mini_batch =  67.98542512352101
avg total error of mini_batch =  0.007449654093429594
---------
nStarting epoch 1051
total costs of mini_batch =  56.69195783294443
avg total error of mini_batch =  0.0063384571747725415
---------
Starting epoch 1101
total costs of mini_batch =  51.81035466850738
avg total error of mini_batch =  0.005939699354987233
---------
Starting epoch 1151
total costs of mini_batch =  52.23157716632318
avg total error of mini_batch =  0.006373981433882217
---------
Starting epoch 1201
total costs of mini_batch =  48.40298652277855
avg total error of mini_batch =  0.005653856253701317
---------
Starting epoch 1251
total costs of mini_batch =  45.00623540189525
avg total error of mini_batch =  0.005245339176038497
---------
Starting epoch 1301
total costs of mini_batch =  36.88409532579881
avg total error of mini_batch =  0.004600719544961844
---------
Starting epoch 1351
total costs of mini_batch =  36.53543045554845
avg total error of mini_batch =  0.003993852242709943
---------
Starting epoch 1401
total costs of mini_batch =  38.80422469954769
avg total error of mini_batch =  0.00464620714991714
---------
Starting epoch 1451
total costs of mini_batch =  42.39371261881638
avg total error of mini_batch =  0.005294796697150631
------
Total training Time_CPU:  2118.4527089519997

Starting epoch 1251
total costs of mini_batch =  128.00827405482318
avg total error of mini_batch =  0.007276206815511017
---------
Starting epoch 1301
total costs of mini_batch =  107.62983581797556
avg total error of mini_batch =  0.005535653858885446
---------
Starting epoch 1351
total costs of mini_batch =  107.83630092292944
avg total error of mini_batch =  0.
005446805325519184
---------
Starting epoch 1401
total costs of mini_batch =  119.7648277329852
avg total error of mini_batch =  0.00729466852297802
---------
Starting epoch 1451
total costs of mini_batch =  106.74254206278933
avg total error of mini_batch =  0.005343124456075227

          
Starting epoch 1151
total costs of mini_batch =  109.77341617599176
avg total error of mini_batch =  0.005494982077591186
---------
Starting epoch 1201
total costs of mini_batch =  113.5293680548904
avg total error of mini_batch =  0.005352117137100675
---------
Starting epoch 1251
total costs of mini_batch =  116.26371170820423
avg total error of mini_batch =  0.0072335516486698
---------
Starting epoch 1301
total costs of mini_batch =  99.7268420386945
avg total error of mini_batch =  0.004850817052601995
---------
Starting epoch 1351
total costs of mini_batch =  101.16579732551999
avg total error of mini_batch =  0.004831600835072556
---------
Starting epoch 1401
total costs of mini_batch =  98.45208584213253
avg total error of mini_batch =  0.004796133492821962
---------
Starting epoch 1451
total costs of mini_batch =  99.279344780807
avg total error of mini_batch =  0.005289728162205425
------
Total training Time_CPU:  2159.5880855739997

Starting epoch 1201
total costs of mini_batch =  104.4420759423322
avg total error of mini_batch =  0.0037985801450468246
---------
Starting epoch 1251
total costs of mini_batch =  102.80878647657674
avg total error of mini_batch =  0.003926855904089417
---------
Starting epoch 1301
total costs of mini_batch =  100.01189950545002
avg total error of mini_batch =  0.0037743225368465773
---------
Starting epoch 1351
total 
costs of mini_batch =  97.34294880936079
avg total error of mini_batch =  0.0035513092392408865
---------
Starting epoch 1401
total costs of mini_batch =  93.15432903284587
avg total error of mini_batch =  0.0032916082743134206
---------
Starting epoch 1451
total costs of mini_batch =  89.79127326241868
avg total error of mini_batch =  0.0033628384147655283
------
Total training Time_CPU:  4254.479082876998