Function forward has a Cognitive Complexity of 9 (exceeds 5 allowed). Consider refactoring.

Open

    def forward(self, input, mask, c0=None, h0=None):
        assert np.ndim(input) == 3, 'Only support batch training.'

        # record
        self.last_input = input

• Read up
  Read up

Function forward has a Cognitive Complexity of 9 (exceeds 5 allowed). Consider refactoring.

Open

    def forward(self, input, c0=None, h0=None):
        """Forward propagation.
        
        Parameters
        ----------

• Read up
  Read up

Function __init__ has 7 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, embed_words=None, static=None,

Function __init__ has 7 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, num_inputs, num_hidden, num_outputs,

Avoid deeply nested control flow statements.

Open

                        for w in np.arange(new_w):
                            outputs[a, b, h, w] = np.mean(input[a, b, h:h + pool_h, w:w + pool_w])

Function __init__ has 6 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, nb_filter, filter_size, input_shape=None, stride=1,

Avoid deeply nested control flow statements.

Open

                        for h in np.arange(new_img_h):
                            for w in np.arange(new_img_w):
                                h_shift, w_shift = h * self.stride, w * self.stride
                                layer_grads[b, t, h_shift:h_shift + filter_h, w_shift:w_shift + filter_w] += \
                                    self.W[r, t] * delta[b, r, h, w]

Avoid deeply nested control flow statements.

Open

                        for w in np.arange(new_w):
                            patch = self.last_input[a, b, h:h + pool_h, w:w + pool_w]
                            max_idx = np.unravel_index(patch.argmax(), patch.shape)
                            h_shift, w_shift = h * pool_h + max_idx[0], w * pool_w + max_idx[1]
                            layer_grads[a, b, h_shift, w_shift] = pre_grad[a, b, a, w]

Avoid deeply nested control flow statements.

Open

                        for w in np.arange(new_w):
                            h_shift, w_shift = h * pool_h, w * pool_w
                            layer_grads[a, b, h_shift: h_shift + pool_h, w_shift: w_shift + pool_w] = \
                                pre_grad[a, b, h, w] / length

Function forward has a Cognitive Complexity of 8 (exceeds 5 allowed). Consider refactoring.

Open

    def forward(self, idxs, masks):
        ##############################
        # Encode
        ##############################

• Read up
  Read up

Avoid deeply nested control flow statements.

Open

                        for w in np.arange(new_w):
                            outputs[a, b, h, w] = np.max(input[a, b, h:h + pool_h, w:w + pool_w])

Function __init__ has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, beta1=0.9, beta2=0.999, epsilon=1e-8, *args, **kwargs):

Function __init__ has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, lr=0.001, clip=-1, decay=0., lr_min=0., lr_max=np.inf):

Function __init__ has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, epsilon=1e-6, momentum=0.9, axis=0,

Function __init__ has 5 arguments (exceeds 4 allowed). Consider refactoring.

Open

    def __init__(self, beta1=0.9, beta2=0.999, epsilon=1e-8, *args, **kwargs):

Function init_weights_from_hidden_layer_neurons_to_output_layer_neurons has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def init_weights_from_hidden_layer_neurons_to_output_layer_neurons(self, output_layer_weights):
        weight_num = 0
        for o in range(len(self.output_layer.neurons)):
            for h in range(len(self.hidden_layer.neurons)):
                if not output_layer_weights:

• Read up
  Read up

Function init_weights_from_inputs_to_hidden_layer_neurons has a Cognitive Complexity of 7 (exceeds 5 allowed). Consider refactoring.

Open

    def init_weights_from_inputs_to_hidden_layer_neurons(self, hidden_layer_weights):
        weight_num = 0
        for h in range(len(self.hidden_layer.neurons)):
            for i in range(self.num_inputs):
                if not hidden_layer_weights:

• Read up
  Read up

Avoid too many return statements within this function.

Open

        return copy.deepcopy(activation)

Avoid too many return statements within this function.

Open

            return LecunUniform()

Avoid too many return statements within this function.

Open

        return copy.deepcopy(optimizer)