Lesson 3 multi-label and segmentation
介绍吴恩达和fastai机器学习课程
Intro Andrew Ng and Fastai ML courses
Intro Andrew Ng and Fastai ML courses
- what special about fastai ML course?
- why should take both Ng and fastai ML courses?
用Zeit实现Web App
Deploy your model on Zeit
Deploy your model on Zeit
- just a page instruction
- free and easy
学员第二周项目展示
Student Projects deployed online
3:30-9:20
Student Projects deployed online 170-418
- what car is that by Edward Ross
- build the app help understand the model better
- no need to use mobile NN api
- Healthy or Not!
- [image:104C2ABE-D1CF-440B-A38B-6BE5569D516B-86291-000381CF60EFD424/26B26097-13E0-4526-95CD-64EBD0D52680.png]
- Trinidad and Tobago Hummingbird classifier
- [image:ADB4E47E-BFF5-4065-9471-E6AAE95CF2B8-86291-000381DF9FE0D786/2A47E6C9-ABAB-4FD9-B329-02DDE21DBD83.png]
- Check your mushroom
- [image:A2CAB546-E926-4BEF-B0FE-A97CA8C59C8E-86291-000381EE4799B078/0866584B-7A59-49B8-9718-CA9CC3D1881E.png]
- cousin classifier
- [image:0A3510E0-A979-43EE-A560-AFD9E5D0CD98-86291-000381F869D4F914/CFBB57C7-1ED6-4D19-9D63-2DD2A480C3BD.png]
- emotion detector and classifier
- [image:CDC2A15D-C402-4533-A51C-A572060A2AD6-86291-000382017E9B9B81/9AF78E81-7344-49B1-894A-F81033F7BFD6.png]
- sign language detector
- [image:29705796-EDB2-4EA3-B67F-34E1A272AD0B-86291-0003820E0154E0B5/3106750F-8A8D-4414-9910-780AB4DE4411.png]
- your city detector
- [image:ACB64105-9676-4D10-A7ED-A3CA094E4462-86291-0003821CB4217822/D18076AA-FA7F-4F10-A674-CA84BA810373.png]
- time series classification
- [image:877696BC-C47D-4AB7-AE0D-05205B9BCA85-86291-00038228FFA7EFC0/4738255D-E810-4830-84C7-D34109F22E69.png]
- facial emotion classification
- [image:1647B963-2CAC-406D-8EA5-B8C8E41431D8-86291-00038355D164F364/F9A95BBA-6683-4E15-8757-A798FC5258A0.png]
- tumor sequencing
- [image:D0B6EDB8-9781-4C0E-BE11-AE5E9CF49EDA-86291-0003835CAE96793E/6E587C7F-FD7C-43E8-B06F-EDE585B8007C.png]
- [Face Expression Recognition with fastai v1 – Pierre Guillou – Medium](https://medium.com/@pierre_guillou/face-expression-recognition-with-fastai-v1-dc4cf6b141a3)
介绍卫星图片集
Introduction to Satellite Imaging dataset
Introduction to Satellite Imaging dataset 9:20-11:02 418-500
9:20-11:02
- check out the image examples and labels
- what is multi-label classification?
如何下载kaggle 数据集
how to download dataset from Kaggle
11:00-14:56
How to download dataset from Kaggle
- What is Kaggle and why it is good?
- How to download dataset from Kaggle?
- How to comment, reverse comment?
- use the notebook to guide the process of downloading
- how to download with 7zip format?
- how to unzip 7zip file?
介绍data block api
Introduction to data block API
14:56-18:28
Introduction to data block API
- Note the dataset is images with multiple labels
- how to read csv with pandas?
- what data object we use for modeling?
- previously what was the trickiest step of deep learning?
- how to create more flexible ways to create your DataBunch, instead of factory method?
- What is data block api and how does it work in general?
介绍 Dataset, DataLoader, DataBunch
Introduction to Dataset, DataLoader, DataBunch
18:30-24:00
Introduction to Dataset, DataLoader, DataBunch
- What is Dataset class?
- what does __getitem__ and __len__ do?
- How to use DataLoader to handle mini-batch?
- How to validate model with DataBunch?
- How to link all the above together through data block api?
用api Nb学习data block 用法
Explore data block api notebook
Explore data block api notebook
24:00-30:20
- use data block api notebook to play with the functions and tiny version of dataset
- a lot of skills to dig into (a lot of questions can be further created)
如何做transformation
How to do transforms
30:11-33:50
How to do transforms
- when and how to pick on flip_vert?
- how to experiment to find out the best values for other parameters?
- what does max_warp do?
- when and how to use it for different dataset?
- building a model procedure is the same as usual
如何设计你的metrics
How to create your own version of metrics
How to create your own version of metrics
30:11-41:08
* what does we use metrics for?
* how to create the accuracy required by Kaggle?
* how does accuracy in fastai source code?
* what does data.c mean?
* why a threshold is needed for satellite dataset accuracy?
* how to create a special version of an accuracy function with specific arg values using partial?
问答：纠错数据，api风格，视频截取
QA on corrected data, data api style, video frames
QA on corrected data, data api style, video frames
42-48:56
* should we record the error from app?
* how to do finetuning with the corrected dataset?
* how we set the learning rate with the corrected dataset?
* should data block api be in certain order?
* where does the idea of data block come from?
* how to dig into the details of data block source code?
* what software to pull frames? (web api, opencv)
如何读取学习率作图
How to pick learning rate carefully?
48:37-50:27
How to pick learning rate carefully
* How to read the lr for fine-tuning?
* How to read the lr for full training?
* What is discriminative learning rate?
如何改进卫星图模型
How to further improve Satellite Imaging model performance
How to further improve CamVid model performance
50:27-56:32
why use smaller images than Kaggle provided for training?
why then larger images to train the model again can avoid overfitting and improve model?
How do we make use the larger images and train model?
- how to change the data with large images?
- how to put the new data into the learner previously trained?
- how to freeze most of the layers of the model and only train the last few layers?
- how to find the best learning rate?
- how to train the model 5 times?
- evetually we move up to top 10%
- How to further improve the performance?
- how to unfreeze to train all the layers?
- how to pick the learning rate to train properly?
- to get into top 20
How to actually do Kaggle competition?
介绍camvid数据集
Introducing Camvid dataset
56:24-60:25
Introducing Camvid dataset
* what kind of problem is segmentation?
* What kind of dataset needed for segmentation?
* What industries have such segmentation problems?
* How to cite the datasets to get them credits?
问答：如何解读合适的学习率
QA How to find a specific lr number or range
60:23-63:06
QA How to find a specific lr number or range
- still a bit more artisanal than expected
- require certain experiment
- bottom point value not good
- try numbers x10 smaller and a few more around
- maybe someone will create an auto learning rate finder
如何做图片区域隔离
How to do segmentation modeling
63:06-69:50
How to do segmentation modeling
- How to get data?
- How to take a look at the data?
- how to extract labels for the data?
- How to open image and segmentation image?
- how to create DataBunch and how to set validation dataset?
- how to pick and use classes names?
- how to do transformation for Camvid dataset?
- how to choose batch size?
- how convenient to do show batch for Camvid dataset?
- How to create a learner
- how to find the learning rate
- how to start training, unfreeze and train more
问答：无监督学习和不同图片尺寸训练
QA unsupervised learning and different sized dataset training
69:55-72:32
QA unsupervised learning and different sized dataset training
* can we do unsupervised learning do segmentation?
* cons of unsupervised learning for segmentation
* should we make smaller size dataset to do training?
* great idea and great trick to improve you model
问答：像素隔离所需的准确度算法
QA what kind of accuracy do we use for pixel segmentation?
72:35-75:03
what kind of accuracy do we use for pixel segmentation
why we use acc_camvid rather than accuracy?
what are void pixels?
what are the basic skills you need to create such metrics?
问答：当训练损失值高于验证损失值时怎么办
QA what to do when training loss higher than validation loss?
75:03-76:21
QA what to do when training loss higher than validation loss
- what to do?
- training longer
- train the last bit with lower learning rate
- decease regularization
- data augmentation
- what to learn about regularization in coming weeks?
为什么以及如何创建U-net来做隔离问题
Why and how to create a U-net for segmentation?
76:21-78:52
Why and how to create a U-net for segmentation
* what does a U-net look like?
* how a medical DL paper contribute to DL in general?
* U-net is the best option for segmentation so far
* What is the usual factory procedure for building and training segmentation model?
什么是one-cycle-learning
What is the trick of one cycle learning?
78:52-86:22
What is the trick of one cycle learning
* How to plot the loss during training and validation?
* Why loss go up a bit and then go down?
* why it is a good idea to start low and push lr up and push it down?
* how to explain it through visualization?
* too small or large is bad
* you want lr to decrease as it is converging
* what does the loss space look like?
* what is learning rate annealing?
* what is leslie Smith’s contribution in one cycle learning?
* How Smith see the loss space in general?
* What is Smith’s learning rate strategy to explore the space much more quickly and efficiently?
* How to get yourself to be an experimentalist?
如何使用更大的图片来进一步训练模型
how to get full image size to train the previous trained model
86:22-90:56
how to get full image size to train the previous trained model
* how to get full image size to train the previous trained model?
* how to show result for segmentation model?
* how good is our model compared to the state of art?
* how big deal with U-net and one-cycle-learning from this example?
什么是mixed precision training
What is mixed precision training for memory limit?
90:56-94:01
What is mixed precision training for memory limit
* what does to_fp16 mean? and how to use it?
* what the hardware requirement is?
* why it is so fast and easy with GPU?
* how good is its performance?
介绍BIWI数据集
Introduction to BIWI dataset
94:01-97:20
Introduction to BIWI dataset
What does this dataset problem do?
How to use the provided functions and methods to calculate the coordinates for dot on the face?
what is the interesting point about the ImagePoints?
what kind of problem is it? (classification or regression)
如何将BIWI数据做成DataBunch
how to prepare BIWI data into DataBunch?
97:20-99:14
how to prepare BIWI data into DataBunch
* how to pick validation set?
* how to set the labels?
* how to do transformation?
如何用CNN做回归问题
How to train CNN for regression
99:14-101:11
How to train CNN for regression
* how to choose a model
* how to choose a loss
* how to find the lr?
* how to fit and save model
* how to check the result
介绍IMDB数据集
Introduction to IMDB dataset
101:08-106:52
Introduction to IMDB dataset
* How to classify document
* which submodule of fastai to use
* introduction to IMDB dataset
* how to create DataBunch quickly?
* how to create it step by step?
- what is tokenization?
- what is numericalization?
- how to do all these steps with data block api?
- What is a language model?
- How to train a learner and save the model
- there is a fastai paper on this model
深度学习理论有多么简单
How simple DL theory is
108:40-116:45
How simple DL theory is
* why NN is all about matrix multiplication?
* what is nonlinear activation?
* what were the popular activations?
* what is ReLU, as the current popular activation?
* how come matrix multiplication + nonlinear + stack together = deep NN?
* what is universal approximation theorem?
* BP is used to find parameter values
* people can’t accept DL theory is so simple
问答：tokenization如何处理San Francisco
QA how tokenization work on things like San Francisco?
116:45-119:10
QA how tokenization work on things like San Francisco
* what did the old way do (Bigram, N-gram)?
* what does NN do with tokens? (how words work together)
问答：4个channel的图片怎么处理？
QA how to deal with images with four channels
119:08-121:23
how to deal with images with four channels
* plan to incorporate into fastai library
* what if you only got 2 channels?
* what if you have 4 channels?
总结
summary of lesson 3
121:23-end
- a single workflow to solve different kinds of problems
- data block api is not big and you are free to add your own
summary of lesson 3