神经轴的TensorFlow步骤、保存程序和实用程序。Neuraxis是一个机器学习（ML）库，用于构建整洁的管道，提供正确的抽象，以简化ML应用程序的研究、开发和部署。
neuraxle-tensorflow的Python项目详细描述
神经轴张力流
Neuraxle的TensorFlow步骤、保存程序和实用程序。在
Neuraxlaxe是一个机器学习（ML）库，用于构建整洁的管道，提供正确的抽象以简化ML应用程序的研究、开发和部署。在
使用示例
张量流1
创建一个TensorFlow1模型步骤，给它一个图形、一个优化器和一个损失函数。在
defcreate_graph(step:TensorflowV1ModelStep,context:ExecutionContext):tf.placeholder('float',name='data_inputs')tf.placeholder('float',name='expected_outputs')tf.Variable(np.random.rand(),name='weight')tf.Variable(np.random.rand(),name='bias')returntf.add(tf.multiply(step['data_inputs'],step['weight']),step['bias'])"""# Note: you can also return a tuple containing two elements : tensor for training (fit), tensor for inference (transform)def create_graph(step: TensorflowV1ModelStep, context: ExecutionContext) # ... decoder_outputs_training = create_training_decoder(step, encoder_state, decoder_cell) decoder_outputs_inference = create_inference_decoder(step, encoder_state, decoder_cell) return decoder_outputs_training, decoder_outputs_inference"""defcreate_loss(step:TensorflowV1ModelStep,context:ExecutionContext):returntf.reduce_sum(tf.pow(step['output']-step['expected_outputs'],2))/(2*N_SAMPLES)defcreate_optimizer(step:TensorflowV1ModelStep,context:ExecutionContext):returntf.train.GradientDescentOptimizer(step.hyperparams['learning_rate'])model_step=TensorflowV1ModelStep(create_grah=create_graph,create_loss=create_loss,create_optimizer=create_optimizer,has_expected_outputs=True).set_hyperparams(HyperparameterSamples({'learning_rate':0.01})).set_hyperparams_space(HyperparameterSpace({'learning_rate':LogUniform(0.0001,0.01)}))
张量流2
创建一个TensorFlow2模型步骤，给它一个模型、一个优化器和一个损失函数。在
^{pr2}$深度学习管道
batch_size=100epochs=3validation_size=0.15max_plotted_validation_predictions=10seq2seq_pipeline_hyperparams=HyperparameterSamples({'hidden_dim':100,'layers_stacked_count':2,'lambda_loss_amount':0.0003,'learning_rate':0.006,'window_size_future':sequence_length,'output_dim':output_dim,'input_dim':input_dim})feature_0_metric=metric_3d_to_2d_wrapper(mean_squared_error)metrics={'mse':feature_0_metric}signal_prediction_pipeline=Pipeline([TrainOnly(DataShuffler()),WindowTimeSeries(),MeanStdNormalizer(),MiniBatchSequentialPipeline([Tensorflow2ModelStep(create_model=create_model,create_loss=create_loss,create_optimizer=create_optimizer,print_loss=True).set_hyperparams(seq2seq_pipeline_hyperparams)])])pipeline,outputs=pipeline.fit_transform(data_inputs,expected_outputs)
- 项目
标签：
欢迎加入QQ群-->： 979659372
