Deep Learning Tutorial 2019 installations

Instructions

---

Participants needs to complete the 3 following instructions before the tutorial kick off date:

• Installations
• Download resources
• Configurations

---

Installations

---

There are 2 options:

1. Using personal computer
2. Using Google Colab (alternative)

Using personal computer

A. Download and install Anaconda

Follow the underlisted steps to install Anaconda distribution in Linux (Ubuntu):

1. cd /tmp
2. curl -O https://repo.anaconda.com/archive/Anaconda3-2019.03-Linux-x86_64.sh
3. sha256sum Anaconda3-2019.03-Linux-x86_64.sh
4. bash Anaconda3-2019.03-Linux-x86_64.sh
5. source ~/.bashrc
6. conda list

Follow the underlisted steps to install Anaconda distribution in Windows:

1. coming soon ...

B. Create virtual environment

We will use the name `dsai` for thi purpose (if you choose a different name, remember to be consistent.:

1. conda create --name dsai
2. source activate dsai

C. Install packages

Install PyTorch and Tensorflow packages. Depending on your system, you can install either the cpu or gpu version: Do not install both.

1. conda install pytorch torchvision cpuonly -c pytorch # for cpu
2. conda install -c aaronzs tensorflow-gpu=1.10

Or;

1. conda install pytorch torchvision cudatoolkit=9.2 -c pytorch # for gpu with cuda 9.2
2. conda install -c aaronzs tensorflow-gpu=1.10

1. conda install numpy matplotlib
2. conda install -c anaconda scipy==1.1.0
3. conda install -c conda-forge opencv tqdm
4. install jupyter notebook or jupyter lab

conda install -c anaconda jupyter conda install -c conda-forge jupyterlab pip install torchsummary

Install PyTorch and Tensorflow packages. Depending on your system, you can install either the cpu or gpu version: Do not install both.

1. conda install pytorch torchvision cpuonly -c pytorch # for cpu
2. conda install -c aaronzs tensorflow-gpu=1.10

Or;

1. conda install pytorch torchvision cudatoolkit=9.2 -c pytorch # for gpu with cuda 9.2
2. conda install -c aaronzs tensorflow-gpu=1.10

1. conda install numpy matplotlib
2. conda install -c anaconda scipy==1.1.0
3. conda install -c conda-forge opencv tqdm
4. install jupyter notebook or jupyter lab

conda install -c anaconda jupyter conda install -c conda-forge jupyterlab pip install torchsummary

Downloads

Configurations

• Installation guide

  ---

Open a terminal and type and execute the following commands:

Anaconda

Follow the following steps to install Anaconda distribution in Ubuntu:

1. cd /tmp
2. curl -O https://repo.anaconda.com/archive/Anaconda3-2019.03-Linux-x86_64.sh
3. sha256sum Anaconda3-2019.03-Linux-x86_64.sh
4. bash Anaconda3-2019.03-Linux-x86_64.sh
5. source ~/.bashrc
6. conda list

Python 3 virtual environment

Follow the following steps to install:

1. conda create --name dsai python=3
2. conda activate dsai

TensorFlow

Follow the following steps to install:

1. conda install -c aaronzs tensorflow-gpu=1.10
2. conda update conda

Jupyter Notebook

Follow the following steps to install:

1. conda install -c anaconda jupyter

Other Libraries

Follow the following steps to install:

1. conda install -c anaconda opencv3
2. conda install -c anaconda matplotlib
3. conda install -c anaconda pillow
4. conda install -c anaconda scikit-learn
5. conda install -c anaconda scikit-image

• Tutorial dataset

  ---

Object Recognition

Follow the following steps to install

Pose Estimation

Follow the following steps to install

• Git repository

  ---

• Reference materials

  ---

Lecture Notes and Slides

Follow the following steps to install

Reference papers and web resources

Follow the following steps to install

• Survey

  ---

• Exercises

  ---