Python 用于添加两个致密层的keras

有两个输入x和u，它们生成输出y。x、u和y之间存在线性关系，即y=xwx+uwx。我试图根据数据计算wx和wu。以下是模型构造/装配的代码

    n_train = 400
    n_val = 100
    train_u = u[:(n_train+n_val)]
    train_x = x[:(n_train+n_val)]
    train_y = y[:(n_train+n_val)]
    test_u = u[(n_train+n_val):]
    test_x = x[(n_train+n_val):]
    test_y = y[(n_train+n_val):]
    val_u = train_u[-n_val:]
    val_x = train_x[-n_val:]
    val_y = train_y[-n_val:]
    train_u = train_u[:-n_val]
    train_x = train_x[:-n_val]
    train_y = train_y[:-n_val]

    # RNN derived classes want a shape of (batch_size, timesteps, input_dim)
    # batch_size. One sequence is one sample. A batch is comprised of one or more samples.
    # timesteps. One time step is one point of observation in the sample.
    # input_dim. number of observation at a time step.
    # I believe n_train = one_epoch = batch_size * time_steps, features = nx_lags or nu_lags
    # I also thing an epoch is one pass through the training data

    n_batches_per_epoch = 8
    n_iterations_per_batch = round(n_train / n_batches_per_epoch)
    batch_size = n_batches_per_epoch
    time_steps = n_iterations_per_batch
    features_x = train_x.shape[1]
    features_u = train_u.shape[1]
    features_y = train_y.shape[1]

    keras_train_u = train_u.values.reshape((batch_size, time_steps, features_u))
    keras_train_x = train_x.values.reshape((batch_size, time_steps, features_x))
    keras_train_y = train_y.reshape((batch_size, time_steps, features_y))
    keras_val_u = val_u.values.reshape((2, time_steps, features_u))
    keras_val_x = val_x.values.reshape((2, time_steps, features_x))
    keras_val_y = val_y.reshape((2, time_steps, features_y))
    keras_test_u = test_u.values.reshape((1, test_u.shape[0], features_u))
    keras_test_x = test_x.values.reshape((1, test_u.shape[0], features_x))
    keras_test_y = test_y.reshape((1, test_u.shape[0], features_y))

    print('u.values.shape: ', u.values.shape)
    # Now try a tensorflow model
    # x_input = keras.Input(shape=(batch_size, time_steps, features_x), name='x_input')
    # u_input = keras.Input(shape=(batch_size, time_steps, features_u), name='u_input')
    x_input = keras.Input(shape=(time_steps, features_x), name='x_input')
    u_input = keras.Input(shape=(time_steps, features_u), name='u_input')
    da = layers.Dense(ny, name='dense_a', use_bias=False)(x_input)
    db = layers.Dense(ny, name='dense_b', use_bias=False)(u_input)
    output = layers.Add()([da, db])

    model = keras.Model(inputs=[x_input, u_input], outputs=output)

    model.compile(optimizer=keras.optimizers.RMSprop(),  # Optimizer
                  # Loss function to minimize
                  loss=keras.losses.SparseCategoricalCrossentropy(),
                  # List of metrics to monitor
                  metrics=[keras.metrics.SparseCategoricalAccuracy()])
    print(model.summary())
    print('keras_train_x.shape: ', keras_train_x.shape)
    print('keras_train_u.shape: ', keras_train_u.shape)
    print('keras_train_y.shape: ', keras_train_y.shape)
    print('keras_val_x.shape: ', keras_val_x.shape)
    print('keras_val_u.shape: ', keras_val_u.shape)
    print('keras_val_y.shape: ', keras_val_y.shape)
    history = model.fit([keras_train_x, keras_train_u], keras_train_y,
                        batch_size=64,
                        epochs=3,
                        # We pass some validation for
                        # monitoring validation loss and metrics
                        # at the end of each epoch
                        validation_data=([keras_val_x, keras_val_u], keras_val_y))

这是输出，有错误

Model: "model"
__________________________________________________________________________________________________
Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
x_input (InputLayer)            [(None, 50, 7)]      0                                            
__________________________________________________________________________________________________
u_input (InputLayer)            [(None, 50, 7)]      0                                            
__________________________________________________________________________________________________
dense_a (Dense)                 (None, 50, 2)        14          x_input[0][0]                    
__________________________________________________________________________________________________
dense_b (Dense)                 (None, 50, 2)        14          u_input[0][0]                    
__________________________________________________________________________________________________
add (Add)                       (None, 50, 2)        0           dense_a[0][0]                    
                                                                 dense_b[0][0]                    
==================================================================================================
Total params: 28
Trainable params: 28
Non-trainable params: 0
__________________________________________________________________________________________________
None
keras_train_x.shape:  (8, 50, 7)
keras_train_u.shape:  (8, 50, 7)
keras_train_y.shape:  (8, 50, 2)
keras_val_x.shape:  (2, 50, 7)
keras_val_u.shape:  (2, 50, 7)
keras_val_y.shape:  (2, 50, 2)
Train on 8 samples, validate on 2 samples

Epoch 1/3
Traceback (most recent call last):
  File "arx_rnn.py", line 487, in <module>
    main()
  File "/arx_rnn.py", line 481, in main
    rnn_prediction = x.rnn_n_steps(y_measured, u_control, n_to_predict)
  File "arx_rnn.py", line 387, in rnn_n_steps
    validation_data=([keras_val_x, keras_val_u], keras_val_y))
  File "venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 780, in fit
    steps_name='steps_per_epoch')
  File "venv\lib\site-packages\tensorflow\python\keras\engine\training_arrays.py", line 363, in model_iteration
    batch_outs = f(ins_batch)
  File "venv\lib\site-packages\tensorflow\python\keras\backend.py", line 3292, in __call__
    run_metadata=self.run_metadata)
  File "venv\lib\site-packages\tensorflow\python\client\session.py", line 1458, in __call__
    run_metadata_ptr)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Can not squeeze dim[2], expected a dimension of 1, got 2
     [[{{node metrics/sparse_categorical_accuracy/Squeeze}}]]

Process finished with exit code 1

模型：“模型”
__________________________________________________________________________________________________
层（类型）输出形状参数#连接到
==================================================================================================
x_输入（输入层）[（无，50，7）]0
__________________________________________________________________________________________________
u_输入（输入层）[（无，50，7）]0
__________________________________________________________________________________________________
密集型（密集型）（无，50，2）14 x_输入[0][0]
__________________________________________________________________________________________________
密集型（密集型）（无，50，2）14 u_输入[0][0]
__________________________________________________________________________________________________
加(加)(无,50,2)0
密集_b[0][0]
==================================================================================================
总数：28
可培训参数：28
不可训练参数：0
__________________________________________________________________________________________________
没有一个
凯拉斯火车形状：（8,50,7）
凯拉斯火车形状：（8,50,7）
凯拉斯列车y形：（8,50,2）
keras_val_x.形状：（2,50,7）
凯拉斯瓦卢形状：（2,50,7）
keras_val_y.形状：（2,50,2）
培训8个样本，验证2个样本
纪元1/3
回溯（最近一次呼叫最后一次）：
文件“arx_rnn.py”，第487行，在
main（）
文件“/arx_rnn.py”，第481行，主目录
rnn_预测=x.rnn_n_步数（y_测量，u_控制，n_到u预测）
文件“arx_rnn.py”，第387行，按rnn_步骤
验证数据=（[keras_val_x，keras_val_]，keras_val_y））
文件“venv\lib\site packages\tensorflow\python\keras\engine\training.py”，第780行，以fit格式
步骤（名称=“每个时代的步骤”）
文件“venv\lib\site packages\tensorflow\python\keras\engine\training\u arrays.py”，第363行，在model\u迭代中
批量输出=f（批量输入）
文件“venv\lib\site packages\tensorflow\python\keras\backend.py”，第3292行，在调用中__
run\u元数据=self.run\u元数据）
文件“venv\lib\site packages\tensorflow\python\client\session.py”，第1458行，在调用中__
运行_元数据_ptr）
tensorflow.python.framework.errors\u impl.InvalidArgumentError:无法压缩dim[2]，预期维度为1，实际维度为2
[{{node metrics/sparse\u categorical\u accurity/squence}}]
进程已完成，退出代码为1

---

错误消息告诉了我什么，以及如何更正？

Keras分类精度指标期望输出和标签的形状为

（批次大小、数量类）

。错误消息中的

尺寸[2]

指示输出形状为3d:

（无，50,2）

简单的解决方法是，通过任何方式，确保输出层对每个批次的每个类给出一个预测，即具有shape

（batch\u size，num\u classes）

，这可以通过

重塑

，或

展平

更好的解决方法是根据设计需要改变输入输出拓扑——即，您到底在分类什么？您的数据维度建议您尝试对单个时间步进行分类—在这种情况下，一次只提供一个时间步的数据：

（批大小、特性）

。或者，在批次轴中进给时间步，一次一批，因此1000个时间步将对应于

（1000，功能）

——但如果模型有任何

有状态的

层，将每个批次轴条目视为一个独立的序列，则不要这样做

---

要使用

timesteps>1对序列进行分类，再次确保层数据流最终产生2d输出。
矩阵x、u和y有nt行，或595行。Y有两列，对应于两个输出。x和u都有7列。x包含y的先前值，使实际问题有状态，但是，如本文所述，问题是无状态的，因为y不依赖于x的先前行。wx和wu的权重是已知的，但我尝试使用fit计算这些权重。稍后我将更改形状并报告更新的状态。目标是预测y的下一个值。“目标是预测y的下一个值”-在这种情况下，主要的，如果不是唯一的错误，这里是损失度量；所有
分类
或
准确性
指标很少涉及非分类
loss='mse'
是您所需要的。（有关所有指标，请参阅）