def solver_generator(params): solver_params = { 'batch_size': 1000, 'eval_batch_size': 2500, 'epochs': 10, 'evaluate_test': True, 'eval_flexible': False, } cnn_model(params) solver = hype.TensorflowSolver(data=data, hyper_params=params, **solver_params) return solver
def solver_generator(self, params): solver_params = { 'batch_size': self.config.batch_size, 'eval_batch_size': self.config.batch_size, 'epochs': self.config.epochs, 'evaluate_test': True, 'eval_flexible': False, 'save_dir': os.path.join(self.config.models,'optimizer-{date}-{random_id}'), # 'save_accuracy_limit': 0.9930, } Tiramisu(config=params) solver = hyper.TensorflowSolver(data=self.hyper_data, hyper_params=self.hyper_params_spec, **solver_params) return solver
def solver_generator(params): solver_params = { 'batch_size': 200, 'eval_batch_size': 200, 'epochs': 20, 'evaluate_test': True, 'eval_flexible': False, 'save_dir': 'temp-sms-spam/model-zoo/example-3-2-{date}-{random_id}', 'save_accuracy_limit': 0.97, } data = rnn_model(params) solver = hype.TensorflowSolver(data=data, hyper_params=params, **solver_params) return solver
def solver_generator(params): solver_params = { 'batch_size': 1000, 'eval_batch_size': 2500, 'epochs': 10, 'stop_condition': curve_predictor.stop_condition(), 'result_metric': curve_predictor.result_metric(), 'evaluate_test': True, 'eval_flexible': False, 'save_dir': 'temp-mnist/model-zoo/example-1-5-{date}-{random_id}', 'save_accuracy_limit': 0.9930, } cnn_model(params) solver = hype.TensorflowSolver(data=data, hyper_params=params, **solver_params) return solver
flat = tf.reshape(pool2, [-1, pool2.shape[1] * pool2.shape[2] * pool2.shape[3]]) dense = tf.layers.dense(inputs=flat, units=1024, activation=tf.nn.relu) logits = tf.layers.dense(inputs=dense, units=10) loss_op = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits, labels=y), name='loss') optimizer = tf.train.AdamOptimizer(learning_rate=0.001) train_op = optimizer.minimize(loss_op, name='minimize') accuracy = tf.reduce_mean(tf.cast( tf.equal(tf.argmax(logits, 1), tf.argmax(y, 1)), tf.float32), name='accuracy') tf_data_sets = input_data.read_data_sets('temp-mnist/data', one_hot=True) convert = lambda data_set: hype.DataSet( data_set.images.reshape((-1, 28, 28, 1)), data_set.labels) data = hype.Data(train=convert(tf_data_sets.train), validation=convert(tf_data_sets.validation), test=convert(tf_data_sets.test)) solver_params = { 'batch_size': 1000, 'eval_batch_size': 2500, 'epochs': 10, 'evaluate_test': True, 'eval_flexible': False, } solver = hype.TensorflowSolver(data=data, **solver_params) solver.train()