我正在遵循面向初学者的 Keras mnist 示例。我尝试更改标签以适合我自己的数据,该数据有 3 个不同的文本分类。我正在使用“to_categorical”来实现这一点。形状对我来说看起来不错,但“fit”出现错误:
train_labels = keras.utils.to_categorical(train_labels, num_classes=3)
print(train_images.shape)
print(train_labels.shape)
model = keras.Sequential([
keras.layers.Flatten(input_shape=(28, 28)),
keras.layers.Dense(128, activation=tf.nn.relu),
keras.layers.Dense(3, activation=tf.nn.softmax)
])
model.compile(optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy'])
model.fit(train_images, train_labels, epochs=5)
(7074, 28, 28)
(7074, 3)
Blockquote Blockquote Traceback (most recent call last): File "C:/Users/lawrence/PycharmProjects/tester2019/KeraTest.py", line 131, in model.fit(train_images, train_labels, epochs=5) File "C:\Users\lawrence\PycharmProjects\tester2019\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1536, in fit validation_split=validation_split) File "C:\Users\lawrence\PycharmProjects\tester2019\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 992, in _standardize_user_data class_weight, batch_size) File "C:\Users\lawrence\PycharmProjects\tester2019\venv\lib\site-packages\tensorflow\python\keras\engine\training.py", line 1154, in _standardize_weights exception_prefix='target') File "C:\Users\lawrence\PycharmProjects\tester2019\venv\lib\site-packages\tensorflow\python\keras\engine\training_utils.py", line 332, in standardize_input_data ' but got array with shape ' + str(data_shape)) ValueError: Error when checking target: expected dense_1 to have shape (1,) but got array with shape (3,)
最佳答案
您需要使用 categorical_crossentropy
而不是 sparse_categorical_crossentropy
作为损失,因为您的标签是热编码的。
或者,如果您不对标签进行热编码,则可以使用sparse_categorical_crossentropy
。在这种情况下,标签的形状应为 (batch_size, 1)
。
关于python - 为什么我会出现 Keras 形状不匹配的情况?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/54513759/