使用 tensorFlow 為 Fashion-MNIST 數據集創建 one-hot

Question

以下情況是否應該為標簽創建一個熱編碼？

我還嘗試創建一個熱門編碼，但一直出錯。 這是怎么做到的？

注意：我在 googles colab 工作。

謝謝你。

import tensorflow as tf
from tensorflow import keras
import numpy as np
import matplotlib.pyplot as plt

fashion = keras.datasets.fashion_mnist
(train_images,train_labels),(test_images,test_labels) = fashion.load_data()

class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress','Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

train_images =  tf.cast(train_images, tf.float32) / 255.0
test_images = tf.cast(test_images, tf.float32) / 255.0

model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])

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


model.fit(train_images, train_labels, epochs=10, batch_size=512, shuffle=True, validation_split=0.1)

要添加 one-hot 編碼，我嘗試將數據更改為：

train_images =  tf.cast(train_images, tf.float32) / 255.0
test_images = tf.cast(test_images, tf.float32) / 255.0

train_labels = tf.one_hot(tf.cast(train_labels, tf.int64), depth=10)
test_labels = tf.one_hot(tf.cast(test_labels, tf.int64), depth=10)

這給出了錯誤：

InvalidArgumentError Traceback (最近一次調用最后一次) in () 27 28 ---> 29 model.fit(train_images, train_labels, epochs=10, batch_size=512, shuffle=True, validation_split=0.1) 30

Answer 1

我認為這段代碼應該可以工作。 它沒有 one-hot 編碼，但它工作得很好。

import tensorflow as tf    
from tensorflow import keras    
import numpy as np    
import matplotlib.pyplot as plt 
       
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data() 
   
class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'] 
train_images = train_images / 255.0    
test_images = test_images / 255.0
        
model = keras.Sequential([keras.layers.Flatten(input_shape=(28, 28)),keras.layers.Dense(128, activation=tf.nn.relu),   keras.layers.Dense(10, activation=tf.nn.softmax)])
model.compile(optimizer=tf.train.AdamOptimizer(),    loss='sparse_categorical_crossentropy',metrics=['accuracy'])        
    
model.fit(train_images, train_labels, epochs=20)

Answer 2

我找到了答案。 請參閱Sparse_categorical_crossentropy vs categorical_crossentropy (keras, accuracy)

要修復 one-hot 編碼的代碼，您應該修復代碼：

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

至：

model.fit(train_images, one_hot_train_labels, epochs=10, batch_size=128, shuffle=True, validation_split=0.1)