首页标签TensorFlow

#TensorFlow

开源软件库,用于各种感知和语言理解任务的机器学习

Convolutional Neural Network (CNN)

XianxinMao

我自己写的代码和该教程略有不一样,有三处改动,第一个地方是用归一化(均值为0,方差为1)代替数值缩放([0, 1]),代替的理由是能提升准确率

4000

Introduction to the Keras Tuner

XianxinMao

The Keras Tuner is a library that helps you pick the optimal set of hyperparamet...

4200

Text classification with TensorFlow Hub: Movie reviews

XianxinMao

This notebook uses tf.keras, a high-level API to build and train models in Tenso...

2100

Tensorflow日常随笔(一)

XianxinMao

TensorFlow is an end-to-end open source platform for machine learning

8720

Building deep retrieval models

XianxinMao

In the featurization tutorial we incorporated multiple features into our models,...

3800

使用transformer BERT预训练模型进行文本分类 及Fine-tuning

大鹅

腾讯 · 后台开发 (已认证)

Bert 全称为 Bidirectional Encoder Representations from Transformers(Bert)。和 ELMo 不同...

14940

使用transformer BERT预训练模型进行文本分类 及Fine-tuning

大鹅

腾讯 · 后台开发 (已认证)

Bert 全称为 Bidirectional Encoder Representations from Transformers(Bert)。和 ELMo 不同...

11320

Taking advantage of context features

XianxinMao

In the featurization tutorial we incorporated multiple features beyond just user...

6300

Using side features: feature preprocessing

XianxinMao

One of the great advantages of using a deep learning framework to build recommen...

9130

TensorFlow Recommenders: Quickstart

XianxinMao

In this tutorial, we build a simple matrix factorization model using the MovieLe...

10560

Tensorflow serving with docker

XianxinMao

如上图所示,执行 pull 之后,我们看到本地已经存在 tensorflow/serving:latest

5210

花朵分类(一)

XianxinMao

首先我们来介绍下数据集,该数据集有5种花,一共有3670张图片,分别是daisy、dandelion、roses、sunflowers、tulips,数据存放结...

7620

Load and preprocess images

XianxinMao

So far, this tutorial has focused on loading data off disk. You can also find a ...

5430

Tensorflow小技巧(一)

XianxinMao

To select rows whose column value equals a scalar, some_value, use ==:

9450

Recommending movies: retrieval

XianxinMao

In TFRS, both components can be packaged into a single exportable model, giving ...

6510

stack overflow 问题分类

XianxinMao

本教程的目的是带领大家学会如何给 stack overflow 上的问题进行打标签

8020

根据译文片段预测翻译作者

XianxinMao

本次用到的数据集是三个 txt 文本,分别是 cowper.txt、derby.txt、butler.txt ,该文本已经经过一些预处理,去除了表头,页眉等

6430

汽车燃料效率预测

XianxinMao

本教程的目的是要预测汽车的燃料效率,相比于之前的分类,这是一个回归问题,回归是针对连续变量的,分类是针对离散变量的

9020

TensorFlow 2 quickstart for experts

XianxinMao

Use tf.data to batch and shuffle the dataset:

6920

TensorFlow 2 quickstart for beginners

XianxinMao

Load and prepare the MNIST dataset. Convert the samples from integers to floatin...

10220

扫码关注云+社区

领取腾讯云代金券