python - Keras错误: Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected

Question

我正在关注https://www.tensorflow.org/tutorials/keras/basic_classification解决 Kaggle 挑战。

但是，我不明白应该将什么样的数据输入到拟合函数中。

我将训练数据集拆分为 X_train、y_train、X_test 和 y_test。 X_train 的形状为 (13125, 32, 32, 3)。

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(32, 32, 3)),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(10, activation=tf.nn.softmax)
])

model.compile(optimizer='adam', 
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

model.fit(X_train, y_train, epochs=5)

我收到错误:

Error when checking model target: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), but instead got the following list of 13125 arrays:

更新:

# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow import keras

# Helper libraries
import numpy as np
import matplotlib.pyplot as plt

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(32,32,3)),
    keras.layers.Dense(128, activation=tf.nn.relu),
    keras.layers.Dense(10, activation=tf.nn.softmax)
])

model.compile(optimizer='adam', 
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])


X_train_stack = np.vstack(X_train)
model.fit(X_train_stack, y_train, epochs=5)

我收到一个错误:

Error when checking input: expected flatten_7_input to have 4 dimensions, but got array with shape (420000, 32, 3)

#read in training set
train_img = []
train_lb = []
for i in range(len(cactus_label)):
    row = cactus_label.iloc[i]
    fileName = row['id']
    train_lb.append(row['has_cactus'])
    path = "../input/train/train/{}".format(fileName)
    im = mpimg.imread(path)
    train_img.append(im)

X_train, X_test, y_train, y_test = train_test_split(train_img, train_lb) 
X_train = np.array(X_train)
X_test = np.array(X_test)

Answer 1

您需要传递 numpy 数组，但您传递的是 numpy 数组列表。使用 np.stack() 从 numpy 数组列表创建单个 numpy 数组:

X_train = np.stack(X_train, axis=0)