python - reshape 数组后keras中的索引错误

Question

我将 .csv 文件用于图像数据，我将其 reshape 为 2d numpy 数组来表示图像。
我不确定我错过了什么，并且在拟合模型时我不断收到“IndexError:list index out of range”。

train_data = pd.read_csv('sign_mnist_train.csv')
test_data = pd.read_csv('sign_mnist_test.csv')

train_labels = train_data.pop('label').to_numpy().reshape(-1, 1)
test_labels = test_data.pop('label').to_numpy().reshape(-1, 1)

train_images = train_data.to_numpy().reshape(-1, 28, 28, 1) / 255.0
test_images = test_data.to_numpy().reshape(-1, 28, 28, 1) / 255.0

def make_model():
    model = models.Sequential()
    
    model.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=(28, 28, 1)))
    model.add(layers.MaxPool2D((2,2)))
    model.add(layers.Conv2D(64, (3,3), activation='relu'))
    model.add(layers.MaxPool2D(2,2))
    model.add(layers.Conv2D(64, (3,3), activation='relu'))

    model.add(layers.Flatten())
    model.add(layers.Dense(64))
    model.add(layers.Dense(25))

    model.compile(optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy,
                  metrics=['accuracy'])
    
    return model

model = make_model()
model.fit(train_images, train_labels, epochs=5, validation_data(test_images, test_labels))

完整的追溯:
1 2 3

Answer 1

我想问题出在 train.data ，根据您命名的测试图像 test_data .
此外，您正在将它们 reshape 为 4D 张量，而不是基于代码的 2D 张量。

train_images = train_data.to_numpy().reshape(-1, 28, 28, 1) 
test_images = test_data.to_numpy().reshape(-1, 28, 28, 1) 

train_images = train_images / 255.0
test_images = test_images / 255.0

编辑:
检查对目标变量应用 one-hot 编码是否有帮助

train_labels = tf.keras.utils.to_categorical(train_labels)