def on_epoch_end(self, epoch, logs=None): logs = logs or {} logs['lr'] = K.get_value(self.model.optimizer.lr) current = logs.get(self.monitor) if current is None: warnings.warn( 'Learning Rate Plateau Reducing requires %s available!' % self.monitor, RuntimeWarning) else: if self.in_cooldown(): self.cooldown_counter -= 1 self.wait = 0 if self.monitor_op(current, self.best): self.best = current self.wait = 0 elif not self.in_cooldown(): if self.wait >= self.patience: old_lr = float(K.get_value(self.model.optimizer.lr)) if old_lr > self.min_lr + self.lr_epsilon: new_lr = old_lr * self.factor new_lr = max(new_lr, self.min_lr) K.set_value(self.model.optimizer.lr, new_lr) if self.verbose > 0: print( '\nEpoch %05d: reducing learning rate to %s.' % (epoch, new_lr)) self.cooldown_counter = self.cooldown self.wait = 0 self.wait += 1
def on_epoch_end(self, epoch, logs=None): logs = logs or {} logs['lr'] = K.get_value(self.model.optimizer.lr) current = logs.get(self.monitor) if current is None: logging.warning('Reduce LR on plateau conditioned on metric `%s` ' 'which is not available. Available metrics are: %s' % (self.monitor, ','.join(list(logs.keys())))) else: if self.in_cooldown(): self.cooldown_counter -= 1 self.wait = 0 if self.monitor_op(current, self.best): self.best = current self.wait = 0 elif not self.in_cooldown(): if self.wait >= self.patience: old_lr = float(K.get_value(self.model.optimizer.lr)) if old_lr > self.min_lr + self.lr_epsilon: new_lr = old_lr * self.factor new_lr = max(new_lr, self.min_lr) K.set_value(self.model.optimizer.lr, new_lr) if self.verbose > 0: print('\nEpoch %05d: reducing learning rate to %s.' % (epoch, new_lr)) self.cooldown_counter = self.cooldown self.wait = 0 self.wait += 1
def on_epoch_end(self, epoch, logs=None): logs = logs or {} logs['lr'] = K.get_value(self.model.optimizer.lr) current = logs.get(self.monitor) if current is None: warnings.warn('Learning Rate Plateau Reducing requires %s available!' % self.monitor, RuntimeWarning) else: if self.in_cooldown(): self.cooldown_counter -= 1 self.wait = 0 if self.monitor_op(current, self.best): self.best = current self.wait = 0 elif not self.in_cooldown(): if self.wait >= self.patience: old_lr = float(K.get_value(self.model.optimizer.lr)) if old_lr > self.min_lr + self.lr_epsilon: new_lr = old_lr * self.factor new_lr = max(new_lr, self.min_lr) K.set_value(self.model.optimizer.lr, new_lr) if self.verbose > 0: print('\nEpoch %05d: reducing learning rate to %s.' % (epoch, new_lr)) self.cooldown_counter = self.cooldown self.wait = 0 self.wait += 1
def get_config(self): config = { 'lr': float(K.get_value(self.lr)), 'decay': float(K.get_value(self.decay)), 'epsilon': self.epsilon } base_config = super(Adagrad, self).get_config() return dict(list(base_config.items()) + list(config.items()))
def get_config(self): config = { 'lr': float(K.get_value(self.lr)), 'momentum': float(K.get_value(self.momentum)), 'decay': float(K.get_value(self.decay)), 'nesterov': self.nesterov } base_config = super(SGD, self).get_config() return dict(list(base_config.items()) + list(config.items()))
def get_config(self): config = { 'lr': float(K.get_value(self.lr)), 'beta_1': float(K.get_value(self.beta_1)), 'beta_2': float(K.get_value(self.beta_2)), 'epsilon': self.epsilon, 'schedule_decay': self.schedule_decay } base_config = super(Nadam, self).get_config() return dict(list(base_config.items()) + list(config.items()))
def on_epoch_begin(self, epoch, logs={}): """Processes called at the beginning of each epoch during the training of the model :param epoch: epoch number :param logs: dictionary of logs """ old_lr = K.get_value(self.model.optimizer.lr) if epoch % 3 == 0 and epoch > 0: new_lr = self.decay * old_lr K.set_value(self.model.optimizer.lr, new_lr) logging.info("New value for the learning rate : {}".format( K.get_value(self.model.optimizer.lr))) else: K.set_value(self.model.optimizer.lr, old_lr)
def convert_all_kernels_in_model(model): """Converts all convolution kernels in a model from Theano to TensorFlow. Also works from TensorFlow to Theano. Arguments: model: target model for the conversion. """ # Note: SeparableConvolution not included # since only supported by TF. conv_classes = { 'Conv1D', 'Conv2D', 'Conv3D', 'Conv2DTranspose', } to_assign = [] for layer in model.layers: if layer.__class__.__name__ in conv_classes: original_kernel = K.get_value(layer.kernel) converted_kernel = convert_kernel(original_kernel) to_assign.append((layer.kernel, converted_kernel)) K.batch_set_value(to_assign)