索引11513超出轴0的大小为10000的范围

Question

我正在练习一个简单的MNIST示例，我得到一个像标题一样的错误，我不知道11513的索引是什么意思。 以下是完整的代码。

np.random.seed(3)

(x_train, y_train), (x_test, y_test) = mnist.load_data()

x_val = x_train[50000:]
y_val = y_train[50000:]
x_train = x_train[:50000]
y_train = y_train[:50000]


x_train = x_train.reshape(50000, 784).astype('float32') / 255.0
x_val = x_val.reshape(10000, 784).astype('float32') / 255.0
x_test = x_test.reshape(10000, 784).astype('float32') / 255.0

train_rand_idxs = np.random.choice(50000, 700)
val_rand_idxs = np.random.choice(10000, 300)
x_train = x_train[train_rand_idxs]
y_train = y_train[train_rand_idxs]
x_val = x_val[train_rand_idxs]#***This is where the error occurred***
y_val = y_val[train_rand_idxs]

y_train = np_utils.to_categorical(y_train)
y_test = np_utils.to_categorical(y_test)
y_val = np_utils.to_categorical(y_val)

model = Sequential()
model.add(Dense(units=2 , input_dim= 28*28, activation='relu'))
model.add(Dense(units=10 , activation='softmax'))

model.compile(loss='categorical_crossentropy' , optimizer='sgd' , metrics=         ['accuracy'])

hist = model.fit(x_train, y_train, epochs =1000 , batch_size=10 ,     validation_data =(x_val, y_val))

Answer 1

您的x_val仅重新变换了10000行：

x_val = x_val.reshape(10000, 784).astype('float32') / 255.0

但train_rand_idxs的索引值最高为50000：

train_rand_idxs = np.random.choice(50000, 700)

当您尝试使用列车索引对x_val进行分组时：

x_val = x_val[train_rand_idxs]

您收到错误，因为[0,50000)中采样的某些指数大于[0,10000)指数的x_val范围。

尝试使用x_val代替x_val[val_rand_idxs]。