TensorFlow-ValueError：形状3，1和4，3不兼容

如何解决TensorFlow-ValueError：形状3，1和4，3不兼容

我是DL的新手，适合我的模型时遇到了这个错误

ValueError: Shapes (3,1) and (4,3) are incompatible

数据集：

Features: [0.22222222 0.625      0.06779661 0.04166667],Target: [1 0 0]
Features: [0.16666667 0.41666667 0.06779661 0.04166667],Target: [1 0 0]
Features: [0.11111111 0.5        0.05084746 0.04166667],Target: [1 0 0]
Features: [0.08333333 0.45833333 0.08474576 0.04166667],Target: [1 0 0]
Features: [0.19444444 0.66666667 0.06779661 0.04166667],Target: [1 0 0]

型号：

def build_fc_model():
  fc_model = tf.keras.Sequential([
      tf.keras.layers.Dense(4,activation=tf.nn.softmax),tf.keras.layers.Dense(4,tf.keras.layers.Dense(3,])
  return fc_model```

model.fit错误

model = build_fc_model()
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-1),loss='categorical_crossentropy',metrics=['accuracy'])

BATCH_SIZE = 10
EPOCHS = 5

model.fit(dataset,batch_size=BATCH_SIZE,epochs=EPOCHS)

感谢您的帮助

解决方法

在您的代码中 build_fc_model 中缺少 InputLayer ，因此请检查以下内容：

import tensorflow as tf
import numpy as np

def build_fc_model():
  fc_model = tf.keras.Sequential([
      tf.keras.layers.InputLayer((4,)),tf.keras.layers.Dense(4,activation=tf.nn.softmax),tf.keras.layers.Dense(3,])
  return fc_model


data = np.array([[0.22222222,0.625,0.06779661,0.04166667],[0.16666667,0.41666667,[0.11111111,0.5,0.05084746,[0.08333333,0.45833333,0.08474576,[0.19444444,0.66666667,0.04166667]])

target = np.array([[1,0],[1,0]])

model = build_fc_model()
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=1e-1),loss='categorical_crossentropy',metrics=['accuracy'])

BATCH_SIZE = 1
EPOCHS = 5

model.fit(data,target,batch_size=BATCH_SIZE,epochs=EPOCHS)

输出：

Epoch 1/5
5/5 [==============================] - 0s 991us/step - loss: 0.8198 - accuracy: 0.6000
Epoch 2/5
5/5 [==============================] - 0s 603us/step - loss: 0.1590 - accuracy: 1.0000
Epoch 3/5
5/5 [==============================] - 0s 593us/step - loss: 0.0372 - accuracy: 1.0000
Epoch 4/5
5/5 [==============================] - 0s 597us/step - loss: 0.0131 - accuracy: 1.0000
Epoch 5/5
5/5 [==============================] - 0s 680us/step - loss: 0.0064 - accuracy: 1.0000