Question

我正在尝试通过构建来学习 AI 算法。我在 Stackoverflow 上发现了一个问题，它是 here。我复制了这段代码试了一下，然后修改成这个。

import numpy as np
import tensorflow as tf
from tensorflow import keras as keras
from tensorflow.keras.layers import Dense, Activation
from tensorflow.keras.models import Sequential
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from tensorflow.python.keras import activations
# Importing the dataset
dataset = np.genfromtxt("data.txt", delimiter='')
X = dataset[:, :-1]
y = dataset[:, -1]

# Splitting the dataset into the Training set and Test set
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.08, random_state = 0)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)



# Initialising the ANN
#model = Sequential()

# Adding the input layer and the first hidden layer
#model.add(Dense(32, activation = 'relu', input_dim = 6))

# Adding the second hidden layer
#model.add(Dense(units = 32, activation = 'relu'))

# Adding the third hidden layer
#model.add(Dense(units = 32, activation = 'relu'))

# Adding the output layer

#model.add(Dense(units = 1))
#model = Sequential([
#    keras.Input(shape= (6),name= "digits"),
#    Dense(units = 32, activation = "relu"),
#    Dense(units = 32, activation = "relu"),
#    Dense(units = 1 , name = "predict")##

#])
#
input = keras.Input(shape= (6),name= "digits")
#x0 = Dense(units = 6)(input)
x1 = Dense(units = 32, activation = "relu")(input)
x2 = Dense(units = 32, activation = "relu")(x1)
output = Dense(units = 1 , name = "predict")(x2)

model = keras.Model(inputs = input , outputs= output)
#model.add(Dense(1))
# Compiling the ANN
#model.compile(optimizer = 'adam', loss = 'mean_squared_error')

# Fitting the ANN to the Training set
#model.fit(X_train, y_train, batch_size = 10, epochs = 200)

optimizer = keras.optimizers.Adam(learning_rate=1e-3)
loss = keras.losses.MeanSquaredError()

epochs = 200

for epoch in range(epochs):
    print("\nStart of epoch %d" % (epoch,))

    # Iterate over the batches of the dataset.
    for step in range(len(X_train)):

        # Open a GradientTape to record the operations run
        # during the forward pass, which enables auto-differentiation.
        with tf.GradientTape() as tape:

            # Run the forward pass of the layer.
            # The operations that the layer applies
            # to its inputs are going to be recorded
            # on the GradientTape.
            logits = model( X_train[step] , training=True)  # Logits for this minibatch

            # Compute the loss value for this minibatch.
            loss_value = loss(y_train[step], logits)

        # Use the gradient tape to automatically retrieve
        # the gradients of the trainable variables with respect to the loss.
        grads = tape.gradient(loss_value, model.trainable_weights)

        # Run one step of gradient descent by updating
        # the value of the variables to minimize the loss.
        optimizer.apply_gradients(zip(grads, model.trainable_weights))

        # Log every 200 batches.
        if step % 200 == 0:
            print(
                "Training loss (for one batch) at step %d: %.4f"
                % (step, float(loss_value))
            )
            print("Seen so far: %s samples" % ((step + 1) * 64))


y_pred = model.predict(X_test)

plt.plot(y_test, color = 'red', label = 'Real data')
plt.plot(y_pred, color = 'blue', label = 'Predicted data')
plt.title('Prediction')
plt.legend()
plt.show()

我修改了处理时创建数据的代码。如果我使用 model.fit，它会使用我提供的数据，但我想在 epochs 开始从模拟中创建数据然后对其进行处理时使用它。（对不起，英语不好。如果我不能很好地解释）

当我在第 81 行开始代码时：

Exception has occurred: ValueError
Input 0 of layer dense is incompatible with the layer: : expected min_ndim=2, found ndim=1. Full shape received: (6,)

它给出了一个例外。我尝试使用 shape=(6,) shape=(6,1) 或类似的，但它没有解决任何问题。

Answer 1

调用keras模型时需要添加batch维度：

logits = model( X_train[step][np.newaxis,:] , training=True)  # Logits for this minibatch

批量维度用于向网络提供多个样本。默认情况下，Keras 假定输入具有批处理维度。要提供一个样本，Keras 需要一批 1 个样本。在这种情况下，它意味着 (1,6) 的形状。如果要喂入一批 2 个样本，那么形状将是 (2,6) 等

输入层错误上的 Keras 输入层形状

1 个答案: