腾讯云开发者社区-腾讯云

开发者社区

文档建议反馈控制台

最新优惠活动

文章/答案/技术大牛

发布

深度学习框架

专栏作者

32

文章

13085

阅读量

12

订阅数

图像之场景分类实验研究

pytorch 卷积神经网络图像识别深度学习人工智能

最后一起看下训练的结果日志，如下图所示，可以看到 testAcc = 93.86%，此处用的是双卡 2080Ti，比单卡来说，训练的 batch_size 更大，所以准确率略微提升:

2021-09-01

4420

Tensorflow随笔(三)

tensorflow 深度学习卷积神经网络人工智能

上图我们可以发现，对于simple_cnn来说，数据增强有很明显的作用，可以显著提高val_acc，也就是模型的泛化性。

2021-08-10

2160

Tensorflow随笔(二)

tensorflow keras 深度学习人工智能

When training with methods such as tf.GradientTape(), use tf.summary to log the required information.

2021-08-07

3080

Tensorflow API(一)

tensorflow 人工智能深度学习

Return a list of physical devices visible to the host runtime.

2021-08-07

3700

Tensorflow随笔(一)

tensorflow 人工智能深度学习神经网络

In machine learning, to improve something you often need to be able to measure it. TensorBoard is a tool for providing the measurements and visualizations needed during the machine learning workflow. It enables tracking experiment metrics like loss and accuracy, visualizing the model graph, projecting embeddings to a lower dimensional space, and much more.

2021-08-07

2250

人工智能深度学习神经网络 NLP 服务

本篇介绍深度学习在自然语言处理(NLP)中的应用，从词向量开始，到最新最强大的BERT等预训练模型，梗概性的介绍了深度学习近20年在NLP中的一些重大的进展

2021-08-03

3890

NLP 服务人工智能深度学习

20 世纪50 年代中期到80 年代初期的感知器，20世纪80 年代初期至21世纪初期的专家系统，以及最近十年的深度学习技术，分别是三次热潮的代表性产物

2021-08-03

2760

Convolutional Neural Network (CNN)

tensorflow 图像识别深度学习卷积神经网络

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

2021-08-01

2630

Building deep retrieval models

tensorflow 推荐系统深度学习 NLP 服务

In the featurization tutorial we incorporated multiple features into our models, but the models consist of only an embedding layer. We can add more dense layers to our models to increase their expressive power. In general, deeper models are capable of learning more complex patterns than shallower models. For example, our user model incorporates user ids and timestamps to model user preferences at a point in time. A shallow model (say, a single embedding layer) may only be able to learn the simplest relationships between those features and movies: a given movie is most popular around the time of its release, and a given user generally prefers horror movies to comedies. To capture more complex relationships, such as user preferences evolving over time, we may need a deeper model with multiple stacked dense layers.

2021-07-30

3200

Taking advantage of context features

tensorflow 深度学习推荐系统 NLP 服务

In the featurization tutorial we incorporated multiple features beyond just user and movie identifiers into our models, but we haven't explored whether those features improve model accuracy.

2021-07-30

2110

Using side features: feature preprocessing

tensorflow keras 推荐系统深度学习 NLP 服务

One of the great advantages of using a deep learning framework to build recommender models is the freedom to build rich, flexible feature representations.

2021-07-30

3960

TensorFlow Recommenders: Quickstart

tensorflow 推荐系统 keras 深度学习

In this tutorial, we build a simple matrix factorization model using the MovieLens 100K dataset with TFRS. We can use this model to recommend movies for a given user.

2021-07-30

3720

Load and preprocess images

tensorflow python 深度学习

This tutorial shows how to load and preprocess an image dataset in three ways. First, you will use high-level Keras preprocessing utilities and layers to read a directory of images on disk. Next, you will write your own input pipeline from scratch using tf.data. Finally, you will download a dataset from the large catalog available in TensorFlow Datasets.

2021-07-29

6340

没有更多了

社区活动

腾讯技术创作狂欢月

“码”上创作 21 天，分 10000 元奖品池！

Python精品学习库

代码在线跑，知识轻松学

博客搬家 | 分享价值百万资源包

自行/邀约他人一键搬运博客，速成社区影响力并领取好礼

技术创作特训营·精选知识专栏

往期视频·千货材料·成员作品最新动态