python - Keras 没有在整个数据集上进行训练
问题描述
所以我一直在关注谷歌官方的 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,它并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?
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
解决方案
拟合模型时显示的数字1875
不是训练样本;它是批次数。
model.fit
包括一个可选参数batch_size
,根据文档:
如果未指定,
batch_size
将默认为 32。
因此,这里发生的情况是 - 您适合 32 的默认批次大小(因为您没有指定任何不同的内容),因此您的数据的批次总数为
60000/32 = 1875
推荐阅读
- c# - ERROR !!! OpenQA.Selenium.DriverServiceNotFoundException is showing even tho i have installed all the drivers required
- vue.js - How to add dynamically v-model and it's initial values to existed html elements by vuejs
- c# - 找不到或打开 PDB 文件,调试本机代码
- python - How do I pass a variable defined as (Entry.get()) from one function to another?
- python - 哈希算法(sha-512)不返回固定长度的位
- javascript - Unexpected Results Splicing on Spreaded Array
- python - Error when im trying add a column to a ListCtrl in wxPython(4.0.6)
- python - 通过匹配元素对子列表进行排序
- azure - Azure Windows Server 许可证未激活
- excel - 使用数组是解决这个 VBA 问题的正确方法吗?