Keras 未对整个数据集进行训练 [英] Keras not training on entire dataset

问题描述

所以我一直在关注 Google 的官方 tensorflow 指南，并尝试使用 Keras 构建一个简单的神经网络.但是在训练模型时，它没有使用整个数据集(有 60000 个条目)，而是仅使用 1875 个条目进行训练.任何可能的修复?

So I've been following Google's official tensorflow guide and trying to build a simple neural network using Keras. But when it comes to training the model, it does not use the entire dataset (with 60000 entries) and instead uses only 1875 entries for training. Any possible fix?

import tensorflow as tf
from tensorflow import keras
import numpy as np

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

train_images = train_images / 255.0
test_images = test_images / 255.0

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

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

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

model.fit(train_images, train_labels, epochs=10)

输出:

Epoch 1/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3183 - accuracy: 0.8866
Epoch 2/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3169 - accuracy: 0.8873
Epoch 3/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3144 - accuracy: 0.8885
Epoch 4/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3130 - accuracy: 0.8885
Epoch 5/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3110 - accuracy: 0.8883
Epoch 6/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3090 - accuracy: 0.8888
Epoch 7/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3073 - accuracy: 0.8895
Epoch 8/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3057 - accuracy: 0.8900
Epoch 9/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3040 - accuracy: 0.8905
Epoch 10/10
1875/1875 [==============================] - 3s 2ms/step - loss: 0.3025 - accuracy: 0.8915

<tensorflow.python.keras.callbacks.History at 0x7fbe0e5aebe0>

这是我一直在研究的原始 google colab 笔记本:https://colab.research.google.com/drive/1NdtzXHEpiNnelcMaJeEm6zmp34JMcN38

Here's the original google colab notebook where I've been working on this: https://colab.research.google.com/drive/1NdtzXHEpiNnelcMaJeEm6zmp34JMcN38

推荐答案

拟合模型时显示的数字1875不是训练样本；它是批次的数量.

The number 1875 shown during fitting the model is not the training samples; it is the number of batches.

model.fit 包含一个可选参数 batch_size，根据 文档:

model.fit includes an optional argument batch_size, which, according to the documentation:

如果未指定，batch_size 将默认为 32.

If unspecified, batch_size will default to 32.

所以，这里发生的情况是 - 您使用默认的批次大小 32(因为您没有指定任何不同的东西)，所以您的数据的总批次数是

So, what happens here is - you fit with the default batch size of 32 (since you have not specified anything different), so the total number of batches for your data is

60000/32 = 1875

这篇关于Keras 未对整个数据集进行训练的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！