training_epochs = 1000 batch_size = 10 # early-stopping parameters patience = 20000 # look as this many examples regardless patience_increase = 2 # wait this much longer if new best found improvement_threshold = 0.995 # consider this improvement significant pretrain_vis_freq = False finetrain_vis_freq = False if __name__ == '__main__': logger = utils.logs.get_logger( __name__, update_stream_level=utils.logs.logging.DEBUG) logger.info('Loading data ...') source = data.Load_Data(location=data.data_loc) datasets = source.all() train_set_x, train_set_y = datasets[0] valid_set_x, valid_set_y = datasets[1] test_set_x, test_set_y = datasets[2] # compute number of minibatches for training, validation and testing n_train_batches = train_set_x.get_value(borrow=True).shape[0] // batch_size n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] // batch_size n_test_batches = test_set_x.get_value(borrow=True).shape[0] // batch_size # np random generator np_rng = np.random.RandomState(123) logger.info('Building the model ...')
training_epochs = 1000 batch_size = 10 # early-stopping parameters patience = 20000 # look as this many examples regardless patience_increase = 2 # wait this much longer if new best found improvement_threshold = 0.995 # consider this improvement significant pretrain_vis_freq = 200 finetrain_vis_freq = 1 if __name__ == '__main__': logger = utils.logs.get_logger(__name__, update_stream_level=utils.logs.logging.DEBUG) logger.info('Loading data ...') source = data.Load_Data() datasets = source.mnist() train_set_x, train_set_y = datasets[0] valid_set_x, valid_set_y = datasets[1] test_set_x, test_set_y = datasets[2] # compute number of minibatches for training, validation and testing n_train_batches = train_set_x.get_value(borrow=True).shape[0]// batch_size n_valid_batches = valid_set_x.get_value(borrow=True).shape[0]// batch_size n_test_batches = test_set_x.get_value(borrow=True).shape[0] // batch_size # np random generator np_rng = np.random.RandomState(123) logger.info('Building the model ...')
## early-stopping parameters patience = 50000 # look as this many examples regardless patience_increase = 2 # wait this much longer if new best is found improvement_threshold = 0.995 # consider this improvement significant # sample for plotting freq = 1 if __name__ == "__main__": logger = utils.logs.get_logger( __name__, update_stream_level=utils.logs.logging.DEBUG) logger.info('Loading data ...') source = data.Load_Data(location=data.data_loc, # search_pat='day1' ) datasets = source.all() train_set_x, train_set_y = datasets[0] valid_set_x, valid_set_y = datasets[1] test_set_x, test_set_y = datasets[2] # compute number of minibatches for training, validation and testing n_train_batches = train_set_x.get_value(borrow=True).shape[0] // batch_size n_valid_batches = valid_set_x.get_value(borrow=True).shape[0] // batch_size n_test_batches = test_set_x.get_value(borrow=True).shape[0] // batch_size logger.info('Building the model ...') # allocate symbolic variables for the data