无法挤压dim [1]，预期尺寸为1，得到2

Question

我有非常简单的输入：点，并且我试图对它们是否在某个区域中进行分类。因此，我的训练数据是形状的(1000000, 2)，这是一种形式的数组：
[ [x1,y1], [x2,y2],... ]
我的标签是一类似的形式的（异型(10000, 2)）：
[ [1,0], [0,1], [0,1],... ]
（[0,1]装置的点处于区域中，[1,0]装置是不）

我的模型是这样建立的：

import tensorflow as tf
from tensorflow import keras
import numpy as np

# Reads the points and labels from .csv format files
train_data = np.genfromtxt('data/train_data.csv', delimiter=',')
train_labels = np.genfromtxt('data/train_labels.csv', delimiter=',')

model = keras.models.Sequential()
model.add(keras.layers.Dense(128, activation='relu', input_shape=(2,)))
model.add(keras.layers.Dense(128, activation='relu'))
model.add(keras.layers.Dense(2, activation='softmax'))

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
model.fit(train_data, train_labels, epochs=1, batch_size=100, verbose=1) # ERROR

请注意，输入形状为(2,)，意味着（根据参考）该模型将期望使用形式的数组(*, 2)。

我收到错误消息：
tensorflow.python.framework.errors_impl.InvalidArgumentError: Can not squeeze dim[1], expected a dimension of 1, got 2

我不知道为什么 有什么建议？

堆栈跟踪：

Traceback (most recent call last):
  File "C:/Users/omer/Desktop/Dots/train.py", line 25, in <module>
    model.fit(train_data, train_labels, epochs=1, batch_size=100, verbose=1)
  File "C:\Users\omer\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training.py", line 880, in fit
    validation_steps=validation_steps)
  File "C:\Users\omer\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\engine\training_arrays.py", line 329, in model_iteration
    batch_outs = f(ins_batch)
  File "C:\Users\omer\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\keras\backend.py", line 3076, in __call__
    run_metadata=self.run_metadata)
  File "C:\Users\omer\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\client\session.py", line 1439, in __call__
    run_metadata_ptr)
  File "C:\Users\omer\AppData\Local\Programs\Python\Python37\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 528, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.InvalidArgumentError: Can not squeeze dim[1], expected a dimension of 1, got 2
     [[{{node metrics/acc/Squeeze}}]]

Answer 1

您的标签形状错误。请参阅文档：

使用sparse_categorical_crossentropy损失时，您的目标应该是 整数
目标。如果您有明确的目标，则应使用categorical_crossentropy

因此，您需要将标签转换为整数：

train_labels = np.argmax(train_labels, axis=1)