Last time, I wrote a quick start on TensorFlow and PyTorch, which received a lot of praise and readers strongly recommended me to write another quick start on Keras. After translating and searching resources on the Internet, I recommend four quick start materials, hoping that they will be helpful to you.

Note: Two additional introductory materials

Quick start on TensorFlow

Quick start for PyTorch at ** **

Very responsible to say: after reading these materials, Keras basic entry-level, then encountered a problem can look up information to solve! (Huang Haiguang)

Recommended Information \

1. Python Deep Learning and Chinese annotation code

Josh Gordon of the TensorFlow team recommends this book, TF2.0 is based on Keras. If you’re new to deep learning, it’s a good place to start. Of course the code in this book needs to be changed, but it’s very simple:

import keras -> from tensorflow import keras
Copy the code

Written by Francois Chollet, the father of Keras and now a researcher of Artificial intelligence at Google, Python Deep Learning provides a detailed introduction to the exploration and practice of deep learning using Python and Keras, including computer vision, natural language processing, generative modeling, and more. The book contains more than 30 code examples and detailed step-by-step explanations. \

The author posted the code on Github, which covers almost everything in this book. After learning this book, readers will have the ability to build their own deep learning environment, build image recognition models, and generate images and words. But there is one small regret: the code is explained and commented entirely in English, which can be a struggle even for those with good English skills.

We believe that this book and code are the best tools for beginners to get started with deep learning and Keras.

Huang haiguang explained and annotated all the codes in Chinese, and downloaded some data sets required by the codes (especially the “Cat and dog War” data set), and localized some of the images, and all the codes passed the test. (Please run in file order, there is some correlation before and after the code). \

The following code contains about 80% of the knowledge point of the book, code directory:

  • 2.1: A first look at A neural network

  • 53: reapparating movie reviews (类 类) \

  • Apparition of newswires

  • 3.7: Predicting House prices

  • 4.4: Underfitting and overfitting \

  • 5.1: Introduction to ConvNets (Convolutional Neural Networks) \

  • 5.2: Using convnets with Small Datasets (Train a convolution on a small dataset from scratch

  • Using a Pre-trained Convolutional Neural Network

  • 5.4: Visualizing what Convnets Learn

  • 6.1: One-hot Encoding of words or characters (One-hot encoding of words or characters) \

  • 6.1: Using Word Embeddings

  • 6.2: Understanding RNNs

  • 6.3: Advanced Usage of RNNs

  • 6.4: Sequence processing with convnets

  • 8.1: Text Generation with LSTM \

  • 8.2: DeepDream (DeepDream)

  • 8.3: Neural style Transfer

  • 8.4: Generating Images with VAEs

  • 8.5: Introduction to GANs (Generative Adversarial Networks)

Chinese notes and explanations are shown as follows:

Figure: Chinese annotation and explanation of code \

The author’s Github:

Github.com/fchollet/de…

Chinese comment code:

Github.com/fengdu78/ma…

2. Sample code for Keras

Resource Address:

Github.com/erhwenkuo/d…

Resources:

The Github repository contains ErhWen Kuo’s notes and exercises on Keras. I hope I can find some good information and examples in the learning process and help students who want to learn how to use Keras to solve problems. Notebooks are the result of running Python 3.6 and Keras 2.1.1 on a Windows 10 machine with Nivida 1080Ti, but some of the notebooks are interlaced with Tensorflow and other functional libraries.

Configuration environment:

Above Python 3.6, Keras 2.1.1

Resource directory: \

Image data set/tool introduction \

  • 0.0: COCO API commentary and simple examples
  • 0.1: image data set of homemade playing cards for earth cannon
  • 0.2: Use Pillow for image processing

1. Keras API example

  • 1.0: Use image enhancement for deep learning
  • 1.1: How to use Keras functional API for deep learning
  • 1.2: Build a VGG network from scratch to learn Keras
  • 1.3: Use pre-trained models to classify objects in photos
  • 1.4: Use image enhancement to train small data sets
  • 1.5: Use the pre-trained convolutional network model
  • 1.6: What visualization does the convolutional network model learn
  • 1.7: Build Autoencoder
  • 1.8: Introduction to seQ-to-SEQ learning
  • 1.9: One-HOT coding tool program introduction
  • 1.10: Introduction to recurrent Neural networks (RNN)
  • 1.11: Difference between LSTM return sequence and return state
  • 1.12: Use LSTM to learn English alphabetical order

2. Image Classification

  • 2.0: Julia (Chars74K) letter image classification
  • 2.1: Classification of traffic sign images
  • 2.2: Simpson cartoon image character classification
  • 2.3: Fashion clothing image classification
  • 2.4: Face key point recognition
  • 2.5: Captcha verification code classification
  • 2.6 Mnist Handwritten Image Classification (MLP)
  • 2.7: Mnist Handwritten Image Classification (CNN)

3. Object Recognition

  • 3.0: YOLO target detection algorithm concept and introduction
  • 3.1: YOLOv2 target detection example
  • 3.2: Racoon detection -YOLOv2 model training and adjustment
  • 3.3: Racoon detection – use of YOLOv2 model
  • 3.4: Kangaroo (Kangaroo) detection -YOLOv2 model training and adjustment
  • 3.5: Hands detection -YOLOv2 model training and adjustment
  • 3.6 Simpson image role (Simpson) detection -YOLOv2 model training and adjustment
  • 3.7: MS COCO image detection -YOLOv2 model training and adjustment

4. Object Segmentation

5. Keypoint Detection

6. Image Caption

7. Face Detection and Recognition

  • 7.0: Face Detection – OpenCV (Haar Feature Classifier)
  • 7.1: Face detection – MTCNN (Multi-Task Cascaded Convolutional Networks)
  • 7.2: Face recognition – face detection, alignment & cropping
  • 7.3: Face recognition – human face feature extraction & face classifier
  • 7.4: Face recognition – conversion, alignment, cropping, feature extraction and comparison
  • 7.5: Face Key Point Detection (DLIB)
  • 7.6: Head Pose Estimation (DLIB)

8. Natural Language Processing

  • 8.0: Word embeddings Introduction
  • 8.1: Use jieba to divide Chinese words
  • 8.2: Basic concepts for Word2vec word embeddings
  • 8.3: Use jieba to analyze lyrics
  • 8.4: Using Gensim to train Chinese word vector (WORD2vec)

3. Official sample of Keras

Resource address: \

Github.com/keras-team/…

Resources:

Github is the official example of Keras. It contains CV, NLP, build model, and some general function code. It is textbook and can be used to modify the input and output.

4. Keras’ pre-training model \

Resource address: \

Github.com/fchollet/de…

This repository was built by keras’s authors and contains pre-trained KerAS models:

  • VGG16

  • VGG19

  • ResNet50

  • Inception v3

  • CRNN for music tagging

    Example description:

Image classification code

from resnet50 import ResNet50
from keras.preprocessing import image
from imagenet_utils import preprocess_input, decode_predictions

model = ResNet50(weights='imagenet')

img_path = 'elephant.jpg'
img = image.load_img(img_path, target_size=(224.224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

preds = model.predict(x)
print('Predicted:', decode_predictions(preds))
# print: [[u'n02504458', u'African_elephant']]
Copy the code

conclusion

After reading these materials, Keras basic introduction, then encountered problems can be solved by their own information!

On this site

The public account “Beginner machine Learning” was founded by Dr. Huang Haiguang. Huang Bo has more than 22,000 followers on Zhihu and ranks among the top 110 in github (32,000). This public number is committed to the direction of artificial intelligence science articles, for beginners to provide learning routes and basic information. Original works include: Personal Notes on Machine learning, notes on deep learning, etc.

Highlights from the past

  • All those years of academic philanthropy. – You’re not alone

  • Suitable for beginners to enter the artificial intelligence route and information download

  • Ng machine learning course notes and resources (Github star 12000+, provide Baidu cloud image) \

  • Ng deep learning notes, videos and other resources (Github standard star 8500+, providing Baidu cloud image)

  • Statistical Learning Methods of Python code implementation (Github 7200+) \

  • Carefully organized and translated mathematical materials related to machine learning

  • Introduction to Deep Learning – Python Deep Learning, annotated version of the original code in Chinese and ebook

Note: If you join our wechat group or QQ group, please reply”Add group“

To join Knowledge Planet (4300+ user ID: 92416895), please reply”Knowledge of the planet“