This article will summarize the Tensorflow pure dry goods learning resources, divided into three sections: tutorials, videos, and projects. It is very suitable for novice learners, and it is recommended that everyone collect them.
One, Tensorflow tutorial resources:
1) Tensorflow tutorials and code examples for beginners: (https://github.com/aymericdamien/TensorFlow-Examples) This tutorial not only provides some classic data sets, but also starts with the simplest implementation of "Hello World". , to the classic algorithm of machine learning, then to the common model of neural networks, step by step to take you from entry to master, is the best tutorial for beginners to learn Tensorflow.
2) From Tensorflow basic knowledge to interesting project applications: (https://github.com/pkmital/tensorflow_tutorials) is also a suitable for novice tutorial, from installation to project combat, teach you to build a neural network of your own.
3) TensorFlow Tutorial running with Jupyter Notebook: (https://github.com/sjchoi86/Tensorflow-101) This tutorial is based on the Tensorflow Tutorial for the Jupyter Notebook development environment. Jupyter Notebook is a very easy to use interactive development tool. , not only supports more than 40 kinds of programming languages, but also can run the code in real time, share documents, data visualization, support markdown, etc., suitable for machine learning, statistical modeling data processing, feature extraction and other fields.
4) Build your first TensorFlow Android application: (https://omid.al/posts/2017-02-20-Tutorial-Build-Your-First-Tensorflow-Android-App.html) This tutorial helps You start from scratch introducing the tensor flow model to your Android application.
5) Tensorflow code exercises:
(https://github.com/terryum/TensorFlow_Exercises) An easy-to-failure Tensorflow code exercise manual. Ideal for learning Tensorflow's buddies.
Second, Tensorflow video resources:
Next, we recommend some nice video tutorials for Tensorflow:
1) TF Girls Practice Guide:
(https://=TrWqRMJZU8A&list=PLwY2GJhAPWRcZxxVFpNhhfivuW0kX15yG&index=2) A Tensorflow public video lesson started from scratch. The course is based on basics and introduction, but the knowledge is very detailed.
2) Tensorflow Open Classes:
(https://=eAtGqz8ytOI&list=PLjSwXXbVlK6IHzhLOMpwHHLjYmINRstrk) Very good course, recommended to everyone.
3) Of course there is also a course on deep learning of the Taiwan National University Li Hongyi course that is worth recommending to everyone: https://link.zhihu.com/?target=https%3A//
4) Good English partner, also recommend some English courses for foreign students: https://?v=vq2nnJ4g6N0;http://bit.ly/1OX8s8Y;https://?v=GZBIPwdGtkk&feature=youtu. Be&list=PLBkISg6QfSX9HL6us70IBs9slFciFFa4W
5) Introduce so many courses, how can you lose Stanford University Tensorflow series course! ! ! Not much to say, directly on the link: https://?v=g-EvyKpZjmQ&index=1&list=PLIDllPt3EQZoS8gCP3cw273Cq9puuPLTg Course homepage: http://web.stanford.edu/class/cs20si/index.html All ppt notes and notes notes Download address: https://pan.baidu.com/s/1o8uOQpW Course-related actual github address: chiphuyen/tf-stanford-tutorials
6) In the end, how can you forget Google's father's video tutorial on the Tensorflow official website? For Tensorflow primary learning partners, it is a very good set of courses to help everyone get started quickly: https://developers.google.cn /machine-learning/crash-course/
Well, through the above resource documentation and video tutorials, we have a solid foundation for Tensorflow. Isn't it time to do some of the more difficult combat projects to enhance ourselves? So next time we recommend some project actual resources:
Third, Tensorflow project resources:
1) A case of random handwriting that implements Alex Graves's thesis: https://github.com/hardmaru/write-rnn-tensorflow
2) Tensorflow-based generation against text to image synthesis: https://github.com/zsdonghao/text-to-image As shown in the following figure, this project is based on Tensorflow's DCGAN model and teaches us step by step to generate text from confrontation. Image synthesis.
3) Attention-based image caption generator:
Https://github.com/yunjey/show-attend-and-tell. This model introduces a focus-based image header generator. You can turn its attention to the relevant part of the image and generate each word at the same time.
4) neural network rendering grayscale image:
Https://github.com/pavelgonchar/colornet A project that is very interesting and has a very wide range of applications, using neural networks to render grayscale images.
5) A simple embedded text classifier based on FastText in Facebook: https://github.com/apcode/tensorflow_fasttext. The project was inspired by FastText on Facebook and implemented in Tensorflow. FastText is a fast text classifier that provides a simple and efficient way to classify and characterize your texts.
6) Using Tensorflow to achieve "sentence-based convolutional neural networks": https://github.com/dennybritz/cnn-text-classification-tf
7) Training TensorFlow neural network using OpenStreetMap function and satellite imagery: https://github.com/jtoy/awesome-tensorflow This project trains neural networks using OpenStreetMap (OSM) data to classify features in satellite images.
8) Implement YOLO with Tenflow: "Real-Time Object Detection" and support a small project running on a mobile device in real time. https://github.com/thtrieu/darkflow Best interests for researchers in the field of computer vision.
Written at the end: These are some Tensorflow projects that Xiaobian thinks are good. If you can put these cases into practice, and understand the principles of each project, I believe that you have reached the understanding of Tensorflow and deep learning. Finally, we recommend several Tensorflow books for beginners to learn:
1) "Tensorflow: Actual Google Deep Learning Framework": This actual book of Google Tensorflow published by Electronic Industry Press is one of the earliest Tensorflow books. Although the content is not a special system, the CNN and RNN sections are not specific enough and do not involve the contents of deep reinforcement learning. However, the basic knowledge of the book is easy to understand. In addition, the visualization tool TensorBoard and distributed acceleration are added. The chapters add a lot to the overall rating of the book. It can be seen that the author is still more attentive, and the station can explain deep learning and Tensorflow's knowledge for beginners.
2) "Tensorflow Machine Learning Practical Guide": This book is a Tensorflow combat class book completed by senior data scientist Nick McClure. This book features a small part of the principle of each section, so that after the implementation of the corresponding code. Although the principle part is not very detailed, the code part is meticulously detailed. From machine learning to deep learning algorithms, the author speaks very thoroughly about each part of the code. For young people who like hand code, this book is still worth recommending.
3) "Vernacular Deep Learning and TensorFlow": Finally, we recommend a copy of "Vernacular Deep Learning and TensorFlow". Before reading the author's "Vernacular Big Data and Machine Learning," he liked the author's writing style. In the book, many mathematical formulae and deep learning principles have been described as vernacular and are very suitable for a book written by Xiao Bai. But because of the author's writing style, there are many places in the book that are not very rigorous; in addition, the code is not written in enough detail. The whole space is pasted and copied, and the code part is not very friendly to the reader.
0.50Mm Fpc Connector,0.5Mm Smt Pull-Out Fpc Connector,0.5Mm Right Angle Type Fpc Connector,0.5Mm Smt Right Angle Connectors
Shenzhen CGE Electronics Co.,Ltd , https://www.cgeconnector.com