Python keras.backend.dtype() Examples
The following are 30 code examples for showing how to use keras.backend.dtype(). 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-yolo3 Author: bing0037 File: model.py License: MIT License | 6 votes |
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
Example 2
Project: multi-object-tracking Author: jguoaj File: model.py License: GNU General Public License v3.0 | 6 votes |
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
Example 3
Project: vision-web-service Author: sherlockchou86 File: model.py License: MIT License | 6 votes |
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
Example 4
Project: YouTubeCommenter Author: HackerPoet File: Generate.py License: MIT License | 6 votes |
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()
Example 5
Project: YouTubeCommenter Author: HackerPoet File: Generate.py License: MIT License | 6 votes |
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
Example 6
Project: YOLO-3D-Box Author: scutan90 File: model.py License: MIT License | 6 votes |
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
Example 7
Project: deep_sort_yolov3 Author: Qidian213 File: model.py License: GNU General Public License v3.0 | 6 votes |
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
Example 8
Project: keras-yolo3-master Author: lijialinneu File: model.py License: MIT License | 6 votes |
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
Example 9
Project: Coloring-greyscale-images Author: emilwallner File: AdamAccumulate.py License: MIT License | 6 votes |
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())
Example 10
Project: perceptron-benchmark Author: advboxes File: keras_yolov3.py License: Apache License 2.0 | 6 votes |
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
Example 11
Project: ImageAI Author: OlafenwaMoses File: utils.py License: MIT License | 6 votes |
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
Example 12
Project: se_relativisticgan Author: deepakbaby File: keras_contrib_backend.py License: MIT License | 6 votes |
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
Example 13
Project: se_relativisticgan Author: deepakbaby File: keras_contrib_backend.py License: MIT License | 6 votes |
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)
Example 14
Project: Vehicle-Detection-and-Tracking-Usig-YOLO-and-Deep-Sort-with-Keras-and-Tensorflow Author: Akhtar303 File: model.py License: MIT License | 6 votes |
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
Example 15
Project: yoloface Author: sthanhng File: model.py License: MIT License | 6 votes |
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
Example 16
Project: keras-lookahead Author: CyberZHG File: optimizers.py License: MIT License | 6 votes |
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
Example 17
Project: keras-adabound Author: titu1994 File: adabound.py License: MIT License | 6 votes |
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)
Example 18
Project: keras-yolov3-KF-objectTracking Author: mattzheng File: model.py License: MIT License | 6 votes |
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
Example 19
Project: MMdnn Author: microsoft File: utils.py License: MIT License | 6 votes |
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
Example 20
Project: keras-yolo3 Author: bing0037 File: model.py License: MIT License | 5 votes |
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
Example 21
Project: PiCamNN Author: PiSimo File: keras_yolo.py License: MIT License | 5 votes |
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
Example 22
Project: multi-object-tracking Author: jguoaj File: model.py License: GNU General Public License v3.0 | 5 votes |
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
Example 23
Project: vision-web-service Author: sherlockchou86 File: model.py License: MIT License | 5 votes |
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
Example 24
Project: keras-adamw Author: OverLordGoldDragon File: optimizers.py License: MIT License | 5 votes |
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
Example 25
Project: keras-adamw Author: OverLordGoldDragon File: optimizers.py License: MIT License | 5 votes |
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
Example 26
Project: keras-adamw Author: OverLordGoldDragon File: optimizers.py License: MIT License | 5 votes |
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
Example 27
Project: keras-adamw Author: OverLordGoldDragon File: optimizers_225.py License: MIT License | 5 votes |
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
Example 28
Project: keras-adamw Author: OverLordGoldDragon File: optimizers_225.py License: MIT License | 5 votes |
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
Example 29
Project: keras-adamw Author: OverLordGoldDragon File: optimizers_225.py License: MIT License | 5 votes |
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
Example 30
Project: YouTubeCommenter Author: HackerPoet File: Generate.py License: MIT License | 5 votes |
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