Python keras.backend.dtype() Examples

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def probs_to_word_ix(pk, is_first):
	if is_first:
		pk[0] = 0.0
		pk /= np.sum(pk)
	else:
		pk *= pk
		pk /= np.sum(pk)
		#for i in range(3):
		#	max_val = np.amax(pk)
		#	if max_val > 0.5:
		#		break
		#	pk *= pk
		#	pk /= np.sum(pk)

	xk = np.arange(pk.shape[0], dtype=np.int32)
	custm = stats.rv_discrete(name='custm', values=(xk, pk))
	return custm.rvs() 

def pred_text(model, context, max_len=64):
	output = []
	context = np.expand_dims(context, axis=0)
	if MAKE_STATEFUL:
		past_sample = np.zeros((1,), dtype=np.int32)
	else:
		past_sample = np.zeros((SEQ_SIZE,), dtype=np.int32)
	while len(output) < max_len:
		pk = model.predict([context, np.expand_dims(past_sample, axis=0)], batch_size=1)[-1]
		if MAKE_STATEFUL:
			pk = pk[0]
		else:
			past_sample = np.roll(past_sample, 1 if IS_REVERSE else -1)
		new_sample = probs_to_word_ix(pk, len(output) == 0)
		past_sample[0 if IS_REVERSE else -1] = new_sample
		if new_sample == 0:
			break
		output.append(new_sample)

	model.reset_states()
	return output

#Load Keras and Theano 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999,
                 epsilon=None, decay=0., amsgrad=False, accum_iters=1, **kwargs):
        if accum_iters < 1:
            raise ValueError('accum_iters must be >= 1')
        super(AdamAccumulate, self).__init__(**kwargs)
        with K.name_scope(self.__class__.__name__):
            self.iterations = K.variable(0, dtype='int64', name='iterations')
            self.lr = K.variable(lr, name='lr')
            self.beta_1 = K.variable(beta_1, name='beta_1')
            self.beta_2 = K.variable(beta_2, name='beta_2')
            self.decay = K.variable(decay, name='decay')
        if epsilon is None:
            epsilon = K.epsilon()
        self.epsilon = epsilon
        self.initial_decay = decay
        self.amsgrad = amsgrad
        self.accum_iters = K.variable(accum_iters, K.dtype(self.iterations))
        self.accum_iters_float = K.cast(self.accum_iters, K.floatx()) 

def _correct_boxes(
            self, box_xy, box_wh, input_shape, image_shape):
        """Get corrected boxes, which are scaled to original shape."""
        box_yx = box_xy[..., ::-1]
        box_hw = box_wh[..., ::-1]
        input_shape = K.cast(input_shape, K.dtype(box_yx))
        image_shape = K.cast(image_shape, K.dtype(box_yx))
        new_shape = K.round(image_shape * K.min(input_shape / image_shape))
        offset = (input_shape - new_shape) / 2. / input_shape
        scale = input_shape / new_shape
        box_yx = (box_yx - offset) * scale
        box_hw *= scale

        box_mins = box_yx - (box_hw / 2.)
        box_maxes = box_yx + (box_hw / 2.)
        boxes = K.concatenate([
            box_mins[..., 0:1],  # y_min
            box_mins[..., 1:2],  # x_min
            box_maxes[..., 0:1],  # y_max
            box_maxes[..., 1:2]  # x_max
        ])

        # Scale boxes back to original image shape.
        boxes *= K.concatenate([image_shape, image_shape])
        return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):

    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],
        box_mins[..., 1:2],
        box_maxes[..., 0:1],
        box_maxes[..., 1:2]
    ])


    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def _preprocess_conv2d_input(x, data_format):
    """Transpose and cast the input before the conv2d.
    # Arguments
        x: input tensor.
        data_format: string, `"channels_last"` or `"channels_first"`.
    # Returns
        A tensor.
    """
    if dtype(x) == 'float64':
        x = tf.cast(x, 'float32')
    if data_format == 'channels_first':
        # TF uses the last dimension as channel dimension,
        # instead of the 2nd one.
        # TH input shape: (samples, input_depth, rows, cols)
        # TF input shape: (samples, rows, cols, input_depth)
        x = tf.transpose(x, (0, 2, 3, 1))
    return x 

def clip(x, min_value, max_value):
    """Element-wise value clipping.
    If min_value > max_value, clipping range is [min_value,min_value].
    # Arguments
        x: Tensor or variable.
        min_value: Tensor, float, int, or None.
            If min_value is None, defaults to -infinity.
        max_value: Tensor, float, int, or None.
            If max_value is None, defaults to infinity.
    # Returns
        A tensor.
    """
    if max_value is None:
        max_value = np.inf
    if min_value is None:
        min_value = -np.inf
    min_value = _to_tensor(min_value, x.dtype.base_dtype)
    max_value = _to_tensor(max_value, x.dtype.base_dtype)
    max_value = tf.maximum(min_value, max_value)
    return tf.clip_by_value(x, min_value, max_value) 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''

    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape / image_shape))
    offset = (input_shape - new_shape) / 2. / input_shape
    scale = input_shape / new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes = K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def get_updates(self, loss, params):
        grads = self.get_gradients(loss, params)
        self.updates = [K.update_add(self.iterations, 1)]

        t = K.cast(self.iterations, K.floatx()) + 1
        lr_t = self.learning_rate * (K.sqrt(1. - K.pow(self.beta_2, t)) / (1. - K.pow(self.beta_1, t)))

        ms = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]
        vs = [K.zeros(K.int_shape(p), dtype=K.dtype(p)) for p in params]
        self.weights = [self.iterations] + ms + vs

        for p, g, m, v in zip(params, grads, ms, vs):
            m_t = (self.beta_1 * m) + (1. - self.beta_1) * g
            v_t = (self.beta_2 * v) + (1. - self.beta_2) * K.square(g)
            p_t = lr_t * m_t / (K.sqrt(v_t) + self.epsilon)
            self.updates.append(K.update(m, m_t))
            self.updates.append(K.update(v, v_t))
            self.updates.append(K.update_sub(p, p_t))
        return self.updates 

def __init__(self, lr=0.001, final_lr=0.1, beta_1=0.9, beta_2=0.999, gamma=1e-3,
                 epsilon=None, decay=0., amsbound=False, weight_decay=0.0, **kwargs):
        super(AdaBound, self).__init__(**kwargs)

        if not 0. <= gamma <= 1.:
            raise ValueError("Invalid `gamma` parameter. Must lie in [0, 1] range.")

        with K.name_scope(self.__class__.__name__):
            self.iterations = K.variable(0, dtype='int64', name='iterations')
            self.lr = K.variable(lr, name='lr')
            self.beta_1 = K.variable(beta_1, name='beta_1')
            self.beta_2 = K.variable(beta_2, name='beta_2')
            self.decay = K.variable(decay, name='decay')

        self.final_lr = final_lr
        self.gamma = gamma

        if epsilon is None:
            epsilon = K.epsilon()
        self.epsilon = epsilon
        self.initial_decay = decay
        self.amsbound = amsbound

        self.weight_decay = float(weight_decay)
        self.base_lr = float(lr) 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_correct_boxes(box_xy, box_wh, input_shape, image_shape):
    '''Get corrected boxes'''
    box_yx = box_xy[..., ::-1]
    box_hw = box_wh[..., ::-1]
    input_shape = K.cast(input_shape, K.dtype(box_yx))
    image_shape = K.cast(image_shape, K.dtype(box_yx))
    new_shape = K.round(image_shape * K.min(input_shape/image_shape))
    offset = (input_shape-new_shape)/2./input_shape
    scale = input_shape/new_shape
    box_yx = (box_yx - offset) * scale
    box_hw *= scale

    box_mins = box_yx - (box_hw / 2.)
    box_maxes = box_yx + (box_hw / 2.)
    boxes =  K.concatenate([
        box_mins[..., 0:1],  # y_min
        box_mins[..., 1:2],  # x_min
        box_maxes[..., 0:1],  # y_max
        box_maxes[..., 1:2]  # x_max
    ])

    # Scale boxes back to original image shape.
    boxes *= K.concatenate([image_shape, image_shape])
    return boxes 

def yolo_head(feats, anchors, num_classes, input_shape, calc_loss=False):
    """Convert final layer features to bounding box parameters."""
    num_anchors = len(anchors)
    # Reshape to batch, height, width, num_anchors, box_params.
    anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])

    grid_shape = K.shape(feats)[1:3] # height, width
    grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
        [1, grid_shape[1], 1, 1])
    grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
        [grid_shape[0], 1, 1, 1])
    grid = K.concatenate([grid_x, grid_y])
    grid = K.cast(grid, K.dtype(feats))

    feats = K.reshape(
        feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])

    # Adjust preditions to each spatial grid point and anchor size.
    box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
    box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.sigmoid(feats[..., 5:])

    if calc_loss == True:
        return grid, feats, box_xy, box_wh
    return box_xy, box_wh, box_confidence, box_class_probs 

def yolo_eval(yolo_outputs,
              image_shape,
              max_boxes=10,
              score_threshold=.6,
              iou_threshold=.5):
    """Evaluate YOLO model on given input batch and return filtered boxes."""
    box_xy, box_wh, box_confidence, box_class_probs = yolo_outputs
    boxes = yolo_boxes_to_corners(box_xy, box_wh)
    boxes, scores, classes = yolo_filter_boxes(
        boxes, box_confidence, box_class_probs, threshold=score_threshold)

    # Scale boxes back to original image shape.
    height = image_shape[0]
    width = image_shape[1]
    image_dims = K.stack([height, width, height, width])
    image_dims = K.reshape(image_dims, [1, 4])
    boxes = boxes * image_dims

    # TODO: Something must be done about this ugly hack!
    max_boxes_tensor = K.variable(max_boxes, dtype='int32')
    K.get_session().run(tf.variables_initializer([max_boxes_tensor]))
    nms_index = tf.image.non_max_suppression(
        boxes, scores, max_boxes_tensor, iou_threshold=iou_threshold)
    boxes = K.gather(boxes, nms_index)
    scores = K.gather(scores, nms_index)
    classes = K.gather(classes, nms_index)
    return boxes, scores, classes 

def yolo_head(feats, anchors, num_classes, input_shape):
    """Convert final layer features to bounding box parameters."""
    num_anchors = len(anchors)
    # Reshape to batch, height, width, num_anchors, box_params.
    anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])

    grid_shape = K.shape(feats)[1:3] # height, width
    grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
        [1, grid_shape[1], 1, 1])
    grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
        [grid_shape[0], 1, 1, 1])
    grid = K.concatenate([grid_x, grid_y])
    grid = K.cast(grid, K.dtype(feats))

    feats = K.reshape(
        feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])

    box_xy = K.sigmoid(feats[..., :2])
    box_wh = K.exp(feats[..., 2:4])
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.sigmoid(feats[..., 5:])

    # Adjust preditions to each spatial grid point and anchor size.
    box_xy = (box_xy + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
    box_wh = box_wh * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))

    return box_xy, box_wh, box_confidence, box_class_probs 

def yolo_head(feats, anchors, num_classes, input_shape, calc_loss=False):
    """Convert final layer features to bounding box parameters."""
    num_anchors = len(anchors)
    # Reshape to batch, height, width, num_anchors, box_params.
    anchors_tensor = K.reshape(K.constant(anchors), [1, 1, 1, num_anchors, 2])

    grid_shape = K.shape(feats)[1:3] # height, width
    grid_y = K.tile(K.reshape(K.arange(0, stop=grid_shape[0]), [-1, 1, 1, 1]),
        [1, grid_shape[1], 1, 1])
    grid_x = K.tile(K.reshape(K.arange(0, stop=grid_shape[1]), [1, -1, 1, 1]),
        [grid_shape[0], 1, 1, 1])
    grid = K.concatenate([grid_x, grid_y])
    grid = K.cast(grid, K.dtype(feats))

    feats = K.reshape(
        feats, [-1, grid_shape[0], grid_shape[1], num_anchors, num_classes + 5])

    # Adjust preditions to each spatial grid point and anchor size.
    box_xy = (K.sigmoid(feats[..., :2]) + grid) / K.cast(grid_shape[::-1], K.dtype(feats))
    box_wh = K.exp(feats[..., 2:4]) * anchors_tensor / K.cast(input_shape[::-1], K.dtype(feats))
    box_confidence = K.sigmoid(feats[..., 4:5])
    box_class_probs = K.sigmoid(feats[..., 5:])

    if calc_loss == True:
        return grid, feats, box_xy, box_wh
    return box_xy, box_wh, box_confidence, box_class_probs 

def __init__(self, learning_rate=0.001, beta_1=0.9, beta_2=0.999,
                 amsgrad=False, model=None, zero_penalties=True,
                 batch_size=32, total_iterations=0, total_iterations_wd=None,
                 use_cosine_annealing=False, lr_multipliers=None,
                 weight_decays=None, init_verbose=True,
                 eta_min=0, eta_max=1, t_cur=0, **kwargs):
        if total_iterations > 1:
            weight_decays = _init_weight_decays(model, zero_penalties,
                                                weight_decays)

        self.initial_decay = kwargs.pop('decay', 0.0)
        self.epsilon = kwargs.pop('epsilon', K.epsilon())
        learning_rate = kwargs.pop('lr', learning_rate)
        eta_t = kwargs.pop('eta_t', 1.)
        super(AdamW, self).__init__(**kwargs)

        with K.name_scope(self.__class__.__name__):
            self.iterations = K.variable(0, dtype='int64', name='iterations')
            self.learning_rate = K.variable(learning_rate, name='learning_rate')
            self.beta_1 = K.variable(beta_1, name='beta_1')
            self.beta_2 = K.variable(beta_2, name='beta_2')
            self.decay = K.variable(self.initial_decay, name='decay')
            self.eta_min = K.constant(eta_min, name='eta_min')
            self.eta_max = K.constant(eta_max, name='eta_max')
            self.eta_t = K.variable(eta_t, dtype='float32', name='eta_t')
            self.t_cur = K.variable(t_cur, dtype='int64', name='t_cur')

        self.batch_size = batch_size
        self.total_iterations = total_iterations
        self.total_iterations_wd = total_iterations_wd or total_iterations
        self.amsgrad = amsgrad
        self.lr_multipliers = lr_multipliers
        self.weight_decays = weight_decays or {}
        self.init_verbose = init_verbose
        self.use_cosine_annealing = use_cosine_annealing

        _check_args(self, total_iterations, use_cosine_annealing, weight_decays)
        self._init_lr = learning_rate  # to print lr_mult setup
        self._init_notified = False 

def __init__(self, learning_rate=0.002, beta_1=0.9, beta_2=0.999,
                 model=None, zero_penalties=True, batch_size=32,
                 total_iterations=0, total_iterations_wd=None,
                 use_cosine_annealing=False, lr_multipliers=None,
                 weight_decays=None, init_verbose=True,
                 eta_min=0, eta_max=1, t_cur=0, **kwargs):
        if total_iterations > 1:
            weight_decays = _init_weight_decays(model, zero_penalties,
                                                weight_decays)

        self.schedule_decay = kwargs.pop('schedule_decay', 0.004)
        self.epsilon = kwargs.pop('epsilon', K.epsilon())
        learning_rate = kwargs.pop('lr', learning_rate)
        eta_t = kwargs.pop('eta_t', 1.)
        super(NadamW, self).__init__(**kwargs)

        with K.name_scope(self.__class__.__name__):
            self.iterations = K.variable(0, dtype='int64', name='iterations')
            self.m_schedule = K.variable(1., name='m_schedule')
            self.learning_rate = K.variable(learning_rate, name='learning_rate')
            self.beta_1 = K.variable(beta_1, name='beta_1')
            self.beta_2 = K.variable(beta_2, name='beta_2')
            self.eta_min = K.constant(eta_min, name='eta_min')
            self.eta_max = K.constant(eta_max, name='eta_max')
            self.eta_t = K.variable(eta_t, dtype='float32', name='eta_t')
            self.t_cur = K.variable(t_cur, dtype='int64', name='t_cur')

        self.batch_size = batch_size
        self.total_iterations = total_iterations
        self.total_iterations_wd = total_iterations_wd or total_iterations
        self.lr_multipliers = lr_multipliers
        self.weight_decays = weight_decays or {}
        self.use_cosine_annealing = use_cosine_annealing
        self.init_verbose = init_verbose

        _check_args(self, total_iterations, use_cosine_annealing, weight_decays)
        self._init_lr = learning_rate  # to print lr_mult setup
        self._init_notified = False 

def __init__(self, learning_rate=0.01, momentum=0., nesterov=False,
                 model=None, zero_penalties=True, batch_size=32,
                 total_iterations=0, total_iterations_wd=None,
                 use_cosine_annealing=False, lr_multipliers=None,
                 weight_decays=None, init_verbose=True,
                 eta_min=0, eta_max=1, t_cur=0, **kwargs):
        if total_iterations > 1:
            weight_decays = _init_weight_decays(model, zero_penalties,
                                                weight_decays)

        self.initial_decay = kwargs.pop('decay', 0.0)
        learning_rate = kwargs.pop('lr', learning_rate)
        eta_t = kwargs.pop('eta_t', 1.)
        super(SGDW, self).__init__(**kwargs)

        with K.name_scope(self.__class__.__name__):
            self.iterations = K.variable(0, dtype='int64', name='iterations')
            self.learning_rate = K.variable(learning_rate, name='learning_rate')
            self.momentum = K.variable(momentum, name='momentum')
            self.decay = K.variable(self.initial_decay, name='decay')
            self.eta_min = K.constant(eta_min, name='eta_min')
            self.eta_max = K.constant(eta_max, name='eta_max')
            self.eta_t = K.variable(eta_t, dtype='float32', name='eta_t')
            self.t_cur = K.variable(t_cur, dtype='int64', name='t_cur')

        self.batch_size = batch_size
        self.total_iterations = total_iterations
        self.total_iterations_wd = total_iterations_wd or total_iterations
        self.nesterov = nesterov
        self.lr_multipliers = lr_multipliers
        self.weight_decays = weight_decays or {}
        self.init_verbose = init_verbose
        self.use_cosine_annealing = use_cosine_annealing

        _check_args(self, total_iterations, use_cosine_annealing, weight_decays)
        self._init_lr = learning_rate  # to print lr_mult setup
        self._init_notified = False 

def __init__(self, lr=0.001, beta_1=0.9, beta_2=0.999, amsgrad=False,
                 epsilon=None, decay=0.0, model=None, zero_penalties=True,
                 batch_size=32, total_iterations=0, total_iterations_wd=None,
                 use_cosine_annealing=False, lr_multipliers=None,
                 weight_decays=None, init_verbose=True,
                 eta_min=0, eta_max=1, t_cur=0, **kwargs):
        if total_iterations > 1:
            weight_decays = _init_weight_decays(model, zero_penalties,
                                                weight_decays)
        eta_t = kwargs.pop('eta_t', 1.)
        super(AdamW, self).__init__(**kwargs)

        with K.name_scope(self.__class__.__name__):
            self.iterations = K.variable(0, dtype='int64', name='iterations')
            self.lr = K.variable(lr, name='lr')
            self.beta_1 = K.variable(beta_1, name='beta_1')
            self.beta_2 = K.variable(beta_2, name='beta_2')
            self.decay = K.variable(decay, name='decay')
            self.eta_min = K.constant(eta_min, name='eta_min')
            self.eta_max = K.constant(eta_max, name='eta_max')
            self.eta_t = K.variable(eta_t, dtype='float32', name='eta_t')
            self.t_cur = K.variable(t_cur, dtype='int64', name='t_cur')

        self.initial_decay = decay
        self.epsilon = epsilon or K.epsilon()
        self.batch_size = batch_size
        self.total_iterations = total_iterations
        self.total_iterations_wd = total_iterations_wd or total_iterations
        self.amsgrad = amsgrad
        self.lr_multipliers = lr_multipliers
        self.weight_decays = weight_decays or {}
        self.init_verbose = init_verbose
        self.use_cosine_annealing = use_cosine_annealing

        _check_args(self, total_iterations, use_cosine_annealing, weight_decays)
        self._init_lr = lr  # to print lr_mult setup
        self._init_notified = False 

def __init__(self, lr=0.002, beta_1=0.9, beta_2=0.999,
                 schedule_decay=0.004, epsilon=None,
                 model=None, zero_penalties=True, batch_size=32,
                 total_iterations=0, total_iterations_wd=None,
                 use_cosine_annealing=False, lr_multipliers=None,
                 weight_decays=None, init_verbose=True,
                 eta_min=0, eta_max=1, t_cur=0, **kwargs):
        if total_iterations > 1:
            weight_decays = _init_weight_decays(model, zero_penalties,
                                                weight_decays)
        eta_t = kwargs.pop('eta_t', 1.)
        super(NadamW, self).__init__(**kwargs)

        with K.name_scope(self.__class__.__name__):
            self.iterations = K.variable(0, dtype='int64', name='iterations')
            self.m_schedule = K.variable(1., name='m_schedule')
            self.lr = K.variable(lr, name='lr')
            self.beta_1 = K.variable(beta_1, name='beta_1')
            self.beta_2 = K.variable(beta_2, name='beta_2')
            self.eta_min = K.constant(eta_min, name='eta_min')
            self.eta_max = K.constant(eta_max, name='eta_max')
            self.eta_t = K.variable(eta_t, dtype='float32', name='eta_t')
            self.t_cur = K.variable(t_cur, dtype='int64', name='t_cur')

        self.epsilon = epsilon or K.epsilon()
        self.schedule_decay = schedule_decay
        self.batch_size = batch_size
        self.total_iterations = total_iterations
        self.total_iterations_wd = total_iterations_wd or total_iterations
        self.lr_multipliers = lr_multipliers
        self.weight_decays = weight_decays or {}
        self.use_cosine_annealing = use_cosine_annealing
        self.init_verbose = init_verbose

        _check_args(self, total_iterations, use_cosine_annealing, weight_decays)
        self._init_lr = lr  # to print lr_mult setup
        self._init_notified = False 

def __init__(self, lr=0.01, momentum=0., nesterov=False, decay=0.0,
                 model=None, zero_penalties=True, batch_size=32,
                 total_iterations=0, total_iterations_wd=None,
                 use_cosine_annealing=False, lr_multipliers=None,
                 weight_decays=None, init_verbose=True,
                 eta_min=0, eta_max=1, t_cur=0, **kwargs):
        if total_iterations > 1:
            weight_decays = _init_weight_decays(model, zero_penalties,
                                                weight_decays)
        eta_t = kwargs.pop('eta_t', 1.)
        super(SGDW, self).__init__(**kwargs)

        with K.name_scope(self.__class__.__name__):
            self.iterations = K.variable(0, dtype='int64', name='iterations')
            self.lr = K.variable(lr, name='lr')
            self.momentum = K.variable(momentum, name='momentum')
            self.decay = K.variable(decay, name='decay')
            self.eta_min = K.constant(eta_min, name='eta_min')
            self.eta_max = K.constant(eta_max, name='eta_max')
            self.eta_t = K.variable(eta_t, dtype='float32', name='eta_t')
            self.t_cur = K.variable(t_cur, dtype='int64', name='t_cur')

        self.initial_decay = decay
        self.batch_size = batch_size
        self.total_iterations = total_iterations
        self.total_iterations_wd = total_iterations_wd or total_iterations
        self.nesterov = nesterov
        self.lr_multipliers = lr_multipliers
        self.weight_decays = weight_decays or {}
        self.init_verbose = init_verbose
        self.use_cosine_annealing = use_cosine_annealing

        _check_args(self, total_iterations, use_cosine_annealing, weight_decays)
        self._init_lr = lr  # to print lr_mult setup
        self._init_notified = False 

def new_sparse_categorical_accuracy(y_true, y_pred):
	y_pred_rank = ops.convert_to_tensor(y_pred).get_shape().ndims
	y_true_rank = ops.convert_to_tensor(y_true).get_shape().ndims
	# If the shape of y_true is (num_samples, 1), squeeze to (num_samples,)
	if (y_true_rank is not None) and (y_pred_rank is not None) and (len(K.int_shape(y_true)) == len(K.int_shape(y_pred))):
		y_true = array_ops.squeeze(y_true, [-1])
	y_pred = math_ops.argmax(y_pred, axis=-1)
	# If the predicted output and actual output types don't match, force cast them
	# to match.
	if K.dtype(y_pred) != K.dtype(y_true):
		y_pred = math_ops.cast(y_pred, K.dtype(y_true))
	return math_ops.cast(math_ops.equal(y_true, y_pred), K.floatx())

#Load the model