我目前正在使用Keras在MNIST数据集上训练卷积神经网络。我使用格式
加载数据集X_train
但是为了减少迭代所有数据,我想只从{0}的每个0-9类中选择前10000个样本,同样从Y_train
中选择。我怎么能这样做?
答案 0 :(得分:1)
MNIST数据集说它返回:
Return:
2 tuples:
X_train, X_test: uint8 array of grayscale image data with shape (nb_samples, 28, 28).
y_train, y_test: uint8 array of digit labels (integers in range 0-9) with shape (nb_samples,).
所以你需要切片你想要保留的部分。我相信pandas / numpy的语法类似于:
X_train = X_train[:10000,:,:]
X_test = X_test[:10000,:,:]
y_train = y_train[:10000]
y_test = y_test[:10000]
答案 1 :(得分:0)
from keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train[:1000,:,:]
x_test = x_test[:500,:,:]
y_train = y_train[:1000]
y_test = y_test[:500]
print(len(x_train))
print(len(y_train))
print(len(x_test))
print(len(y_test))
#输出
> 1000
> 1000
> 500
> 500