如何通過重塑對 MNIST 數據集進行預測？

Question

I'm working on a simple example of a ANN using the MNIST dataset. I think I understand the basic breakdown of the model, including reshaping the data, but I'm having trouble with the prediction aspect. 

model = keras.Sequential([
    layers.Dense(512, activation='relu'),
    layers.Dense(100, activation='relu'),
    layers.Dense(10, activation='softmax')
])

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

train_images = train_images.reshape((60000, 28 * 28))
train_images = train_images.astype("float32") / 255
test_images = test_images.reshape((10000, 28 * 28))
test_images = test_images.astype("float32") / 255

model.fit(train_images, train_labels, epochs=5, batch_size=128)
model.predict(test_images)

img = test_images[4].reshape(28, 28)
plt.imshow(img)

model.predict(test_images[4])

當我預測“img”時，我收到以下錯誤：“ValueError：層順序的輸入 0 與層不兼容：輸入形狀的預期軸 -1 具有值 784，但接收到的輸入形狀為（無，1）。 " 但是，我重新塑造了“IMG”，所以我不確定如何修復錯誤來測試模型的預測。 我也試過 model.predict(img)。 請指教。

Answer 1

在下面更改您的代碼：

train_images = train_images.reshape((60000, 28 * 28))
train_images = train_images.astype("float32") / 255
test_images = test_images.reshape((10000, 28 * 28))
test_images = test_images.astype("float32") / 255

使用此代碼：您的圖層沒有得到正確的輸入形狀

X_train, X_test = X_train / 255, X_test /255
X_train = np.expand_dims(X_train, -1)
X_test = np.expand_dims(X_test, -1)

X_train.shape    // Shape should be (60000,28,28,1)

//Before using labels do this
y_train = to_categorical(y_train, K)
y_test = to_categorical(y_test, K)