python - 如何在 TFLearn 中使用多个数据行作为单个输入？

Question

我正在尝试使用 TFLearn（或直接使用 TensorFlow）来重建嘈杂的（如谐波）信号。我的输入有 168 列要转换为 84 个输出。我想将每一列对视为一个像素。我不必实时运行，所以我想使用多行输入来生成单个输出。我想我需要至少 20 行输入（两边各 10 行）来计算单行输出。如何适当地重塑我的数据？例如看评论：

def learn1(data, answers): 
    # data.shape == 5000x168, answers.shape = 5003x84
    network = tflearn.input_data(shape=[None, 20, 84, 2])
    ... set up 2D convolutional network ...
    model = tflearn.DNN(network)

    X = # data reshaped into overlapping groups of 20 -- what goes here?
    Y = # I don't have any labels. What goes here?
    Y_test = # what goes here?
    model.fit(X, Y, n_epoch=50, shuffle=False, 
        validation_set=(answers, Y_test), batch_size=10)

我可以随意生成测试数据。谢谢你的帮助。