I recently want to learn python deep learning, because I want to use python for Image Recognition and related entry books. The best Chinese. It is to give a picture to identify what the plot looks like. I recently want to learn python deep learning, because I want to use python for Image Recognition and related entry books. The best Chinese.
It is to give a picture to identify what the plot looks like. Reply content: This is
Relatively completeThe learning path for Image Recognition Using deep learning, not deep learning
Shortcuts!
1. Pattern Recognition
From the perspective of Your Problem Description Language, the subject does not seem to have a high understanding of pattern recognition.
Therefore, before performing Image Recognition Based on deep learning, we recommend that you read the books related to pattern recognition and computer vision. First
Understand the image information itselfTo try to identify.
Learning OpenCVI think it is a very good entry-level book in the above fields and also has a python interface.
2. Machine Learning
I don't know how much you know about machine learning and related fields. Before learning the deep learning theory, we recommend that you learn the shallow Model and Its Theory. Of course, there are no excellent Chinese books. However, machine learning and statistical learning methods are worth looking. Pattern Recognition and Machine Learning and
Machine Learning: a Probabilistic Perspective, which contains the chapter on Deep Neural Networks.
3. Deep Learning
Finally, deep learning first introduced Theano (Welcome-Theano 0.6 documentation) of the University of Montreal in python.
). It has a corresponding English version of deep learning tutorial (Contents-DeepLearning 0.1 documentation
), Will involve
Expansion from a shallow model to a deep Model.
I have translated some documents into Chinese and put them on github. Poor quality. If you are interested, join them (Syndrome777/DeepLearningTutorial GitHub
).
In addition, there is a Stanford document that mainly describes the automatic failover machine. Some Chinese scholars have completed the translation (UFLDL tutorial-Ufldl
).
Deep Learning is so popular that some of you are eager to join us. However, it is recommended that you have a basic knowledge of pattern recognition and machine learning before learning.
It will be awesome only after the fight. Deep learning is a very popular topic in machine learning, and machine learning is precisely a direction of computer science and a cross-discipline of computer science and statistics. Python is a computer programming language.
Therefore, in theory, python can implement any algorithm, including deep learning algorithms. Deep learning algorithms can also be implemented in any computer language. Therefore, the subject has a question.
I guess the subject wants to know which algorithm packages are available in python. Scikit-learn: machine learning in python
. Opencv is a well-known and comprehensive library in the aspect of CV.
As for deep learning, it is better to first understand the most basic machine learning algorithms, and then you can look at various tutorial and paper, essentially neural networks. None of python's best deep learning materials.
Deep Learning Tutorials
Programming Computer Vision with Python: Techniques and Libraries for Imaging and Retrieving Information
@ Issac Syndrome has a complete answer. Here we will add two additional materials for deep learning:
- Hinton Neural Network Course at coursera: https://www.coursera.org/course/neuralnets
- On the other hand, if you do deep learning, you may need to use GPU parallel computing technology, the most popular GPU computing framework is CUDA (https://developer.nvidia.com/cuda-downloads), Which is also the supporting technology behind theano.
Stanford recently opened a course to introduce convolutional neural networks (a common deep learning model). The job is also based on python. If you are interested in it, take a look.
Stanford University CS231n: Convolutional Neural Networks for Visual Recognition
