Adam Algorithm

1. Adam Algorithm

2. Parameters

Convolution Layer

1. The idea of convolution layer

# of parameter dimensions:

# dimension reduction by 1 convolution operation:

2. The idea of ConvNet

some notes:

1. the shape of the layers go smaller and smaller.

2. the number of channels go larger and larger.

3. the final results of ConvNet will be flatten and then feed into a NN layer. 

3. The idea of Pooling Layer (Max Pooling)

4. Putting it together

Neural Network Forward and Backward Compute (N layers)

1. Forward Propagation

2. Backward Propagation

3. Put it together

Neural Network Forward and Backward Compute (2 layers)

1: Forward Compute with One Example

2: Forward Compute with Vectorizing across multiple examples

3. Gradient for Backward Compute

4. Formula for Backward Compute

5. To understand why the partial derivatives are calculated, check out the book here: http://www.deeplearningbook.org/  

or check the video here:

https://www.coursera.org/learn/neural-networks-deep-learning/lecture/6dDj7/backpropagation-intuition-optional

ImageNet

1. What it is?

More than 14 million[1][2] images have been hand-annotated by the project to indicate what objects are pictured and in at least one million of the images, bounding boxes are also provided.[3] ImageNet contains more than 20,000 categories[2] with a typical category, such as "balloon" or "strawberry", consisting of several hundred images.

2. History

AI researcher Fei-Fei Li presented their database for the first time as a poster at the 2009 CVPR.

3. ImageNet Large Scale Visual Recognition Challenge (ILSVRC)

GoogleLeNet-v4 is the winner until now: https://www.google.com/search?q=imagenet+accuracy+over+time&tbm=isch&source=univ&sa=X&ved=2ahUKEwiI_7yQ3tLmAhVFSX0KHdjICC8QsAR6BAgFEAE&biw=1920&bih=897#   

https://machinelearningmastery.com/introduction-to-the-imagenet-large-scale-visual-recognition-challenge-ilsvrc/

Google Spreadsheet API

https://medium.com/@ashokyogi5/a-beginners-guide-to-google-oauth-and-google-apis-450f36389184

Docker Notes

1. What is a Dockerfile?

• Docker can build images automatically by reading the instructions from a Dockerfile. A Dockerfile is a text document that contains all the commands a user could call on the command line to assemble an image. 

2. What are the most common Docker command? 

Build commands:

• docker build -t name:version:
  Build an image from the Dockerfile in the current directory and tag the image
• docker images:
  List all images that are locally stored with the Docker engine
• docker rmi imagename (REPOSITORY:TAG)
  remove an image from local

Ship commands:

• docker pull
• docker push

Run commands:

• docker run 

--rm remove container automatically after it exits 

--it connect the container to terminal

--name name the container 

-p 5000:80 expose port 5000 externally and map to port 80 

-v create a host mapped volume inside the container the image from which the container is instantiated the command to run inside the container

• docker stop
• docker kill 
• docker ps
  List all containers
• docker exec --it container bash
  create a process inside a container and connect to the terminal

https://www.docker.com/sites/default/files/Docker_CheatSheet_08.09.2016_0.pdf

3. Image vs Container 

Image vs Container is like Class vs Object

4. Where to check out some example Dockerfile?

https://github.com/docker-library/python/blob/8601079d1f70b03c01408377716a3243ce75cec9/3.7/stretch/Dockerfile

https://github.com/Quantisan/docker-clojure/blob/e04878d311653b89714e15d8fa8d6081f2c2d773/debian/lein/Dockerfile

5. How to clean local docker file? images, contains and volumes? 

docker system prune - removing dangling images
docker rmi
docker rm
docker run --rm


https://www.digitalocean.com/community/tutorials/how-to-remove-docker-images-containers-and-volumes

6. What are most common dockerfile command?

• FROM
  The FROM instruction initializes a new build stage and sets the Base Image for subsequent instructions. As such, a valid Dockerfile must start with a FROM instruction
• RUN
  RUN <command>
  
  • RUN lein test && \
  • lein uberjar
  RUN ["executable", "param1", "param2"]
• CMD
• ENTRYPOINT
• EXPOSE
  
  • EXPOSE 80/tcp
  • Regardless of the EXPOSE settings, you can override them at runtime by using the -p flag. 
• ENV
• ENV myName="John Doe"  \
•     myCat=fluffy
• ADD
• The ADD instruction copies new files, directories or remote file URLs from <src> and adds them to the filesystem of the image at the path <dest>
• ADD files* /somedir/
• COPY
• WORKDIR
• ARG
• LABEL
• The LABEL instruction adds metadata to an image. A LABEL is a key-value pair. To include spaces within a LABEL value, use quotes and backslashes as you would in command-line parsing. 

7. The Process:

Find the Docker Base Image
Build my own Docker Image
Run the docker image