Alireza-Akhavan/class.vision
Computer vision and Deep learning in SRU
repo name | Alireza-Akhavan/class.vision |
repo link | https://github.com/Alireza-Akhavan/class.vision |
homepage | http://fall97.class.vision/ |
language | Jupyter Notebook |
size (curr.) | 211258 kB |
stars (curr.) | 54 |
created | 2018-01-28 |
license | MIT License |
Vision Class
Introduction to Machine learning and Deep learning for Computer vision, A course from Shahid Rajaie University (SRU) of Tehran, Held in winter and fall of 2018.
Course starts with an Introduction to Computer Vision with practical approach using opencv
on python
, then, continues with an Introduction to Learning Algorithms and Neural Networks. after that, Deep Neural Networks published after 2012 are studied and are implemented using python and Tensorflow
, Keras
, and FastAI
Machine learning and deep learning frameworks.
Sessions
Tables consisting content of each semester in Persian can be found here: Winter 2018 β’ Fall 2018
Computer Vision
π― Topics
Computer vision overview
Course logistics
π‘ Slides
Introduction PDF
π NoteBooks
π― Topics
Reading Images
Color Spaces
Displaying Images
Saving Images
π NoteBooks
π Student notes
- Opencv Installation and startup
- Introduction to Opencv
- Introduction to Anaconda
- Git and getting last updates
π― Topics
Linear algebra
Transform matrices
Interpolation Methods
π‘ Slides
Image manipulations (1) PDF β’ PPT
π― Topics
Draw geometric shapes
Transform matrices
Translations
Rotation
Resizing
Image pyramids
Cropping
π NoteBooks
π Student notes
π Videos
π― Topics
Logical and Mathematical Operations in OpenCV
Image masking in OpenCV
Convolution and Correlation filters
Moving Average
Sharpening Filters in OpenCV
π‘ Slides
Image manipulations (2) PDF β’ PPT
π NoteBooks
π Student notes
π Videos
π― Topics
Images Types
Binary images, and Thresholds
Thresholds in OpenCV
Morphology (Dilation, Erosion, Opening, and Closing)
Morphology in OpenCV
π‘ Slides
Binary Images and Morphology PDF β’ PPT
π NoteBooks
π Student notes
π Videos
π― Topics
Images Derivative, and Gradient
Canny, and Sobel Edge Detections
Edge Detection in OpenCv
Perspective Transformation in OpenCv
Affine Transforms
Using Webcam in OpenCv
π‘ Slides
π NoteBooks
π Student notes
π Videos
Machine Learning
π― Topics
What is ML
Supervised Learning
Unsupervised Learning
Reinforcement Learning
ML projects Steps
Train-Test Split
Model evaluation
π‘ Slides
Introduction to Machine Learning PDF β’ PPT
π Student notes
π― Topics
Perceptron
Weights and Biases in Perceptron
Activation Function
Input Feature Array
Multilayer Perceptron (MLP)
Layers in MLP (input, hidden, and output)
π‘ Slides
Simple Classifier (KNN) PDF β’ PPT
Introduction to Neural Networks PDF β’ PPT
π NoteBooks
π Student notes
- KNN classifier in scikit-learn
- Introduction to Neural networks (part 1)
- Introduction to Neural networks (part 2)
π Videos
π― Topics
Loss Function (Coss Function)
Gradient Descent, and Back Propagation
Model Visualization
π Videos
π links
Model Visualization and observing changes in number of each layer using Tensorflow Playground
π― Topics
Recurrent, fully connected Networks in Keras
Declaring Model Architecture
Choosing Loss function, and Optimizer
Model Evaluation on Test Set
Predicting using Model
π NoteBooks
π Student notes
π Videos
Deep Learning
π― Topics
Classification Tasks in Real-Life
Invariant Object Recognition
KNN, pros and cons
Over-fitting
Dropout
Convolutional Neural Networks (CNN)
CNNs vs. Classic methods
ImageNet
π‘ Slides
Introduction to Deep Learning & Convolutional Neural Networks PDF β’ PPT
π NoteBooks
π Student notes
π Videos
π― Topics
Kernels: Convolutional Filters
Learning kernels vs. Designing Fitlers
Same and Valid Convolutions
Paddings and strides
Image Size before and after conv.
3D convolutions
Multi-filter convolutions
Convolutional Layers Parameters
Pooling Layers
LeNet
π‘ Slides
Convolutional Neural Networks PDF β’ PPT
π Videos
π― Topics
CNN Layers
CNN pros and cons
CNNs in Keras
Conv2D and MaxPooling2D functions
Flatten Method
Models Summery
π NoteBooks
π Videos
π― Topics
Train-Test-Validation Split
Data Generators in Keras
Sigmoid and Softmax
Step per Epoch
Over-fitting
π NoteBooks
π Student notes
π Videos
π― Topics
Brain Architecture
AlexNet
VGGNet
GoogLeNet
ResNet
π‘ Slides
π Student notes
π Videos
π Reading Materials
π― Topics
Preventing Over-fitting
Data Augmentation in Keras
π‘ Slides
Data Augmentation & Transfer Learning PDF β’ PPT
π NoteBooks
π― Topics
Loading Pre-trained Models
Transfer Learning in Keras
π‘ Slides
Data Augmentation & Transfer Learning PDF β’ PPT
π NoteBooks
π Student notes
π― Topics
Implementing classification in keras
conv. layers as Feature extraction
Fine-tuning
π NoteBooks
π― Topics
One-shot Learning
Siamese Networks
Triplet Loss
π‘ Slides
π― Topics
Center Loss
A-softmax Loss
π NoteBooks
π Reading Materials
A Discriminative Feature Learning Approach for Deep Face Recognition PDF SphereFace: Deep Hypersphere Embedding for Face Recognition PDF
π― Topics
Face Detection
HAAR Cascade
Wider Challenge
MTCNN
Face Detection Project Instructions
π NoteBooks
π Reading Materials
Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks (MTCNN) PDF
π links
π― Topics
Batch-Norm
Learning-Rate Decay
Multi-Label Classification in Keras
π‘ Slides
Batch-Norm, Learning-Rate Decay, and Multi-Label Classification PDF β’ PPT
π NoteBooks
π Student notes
π Videos
Multi-Label Classification (Continued)
Tensorflow Low-level API
Graphs, Constant Tensors, and Sessions in Tensorflow
π‘ Slides
A Gentle Introduction to Tensorflow PDF β’ PPT
π NoteBooks
π Videos
π― Topics
Placeholders and Variables
Feeding and Fetching Graphs
π‘ Slides
Batch-Norm, Learning-Rate Decay, and Multi-Label Classification PDF β’ PPT
π NoteBooks
π Videos
π― Topics
MNIST Dataset
Fully-connected Layers
CNN Layers
π NoteBooks
π Videos
π― Topics
Finding Efficient Learning Rate
Stochastic Gradient Descent with Restarts
π‘ Slides
An even more Gentle Introduction to FastAI (1) PDF β’ PPT
π NoteBooks
π Videos
π― Topics
Global Pooling
Adaptive Pooling
Change Image Size Between Epochs
π‘ Slides
An even more Gentle Introduction to FastAI (2) PDF β’ PPT
π NoteBooks
π Videos
π― Topics
Multi-Label Classification in FastAI
RNNs
π‘ Slides
An Introduction to RNNs PDF β’ PPT
π NoteBooks
π Videos
π― Topics
Forward Propagation
Back Propagation
Language Models
LSTM
Vanishing Gradient
π‘ Slides
Recurrent Neural Networks PDF β’ PPT
π NoteBooks
π Videos
π― Topics
Vanishing Gradient
LSTM
Bidirectional RNNs
GRU
Deep RNNs
Character Level Language Models in Keras
π‘ Slides
RNNs, LSTM, and GRU PDF β’ PPT
π NoteBooks
π Videos
π― Topics
Word Embedding
Analogy
π‘ Slides
Recurrent Neural Networks PDF β’ PPT
π Videos
π― Topics
Word2Vec
Word Embedding
Skip-grams
Softmax Classification issues
Negative Sampling
π‘ Slides
Recurrent Neural Networks PDF β’ PPT
π Videos
π― Topics
Glove
Gender and Race Biases
Using Embedding Vectors in Keras
π‘ Slides
Recurrent Neural Networks PDF β’ PPT
π NoteBooks
π Videos
π― Topics
Word Analogy
Removing Biases
Word Embedding
Emoji Dataset
π‘ Slides
Recurrent Neural Networks PDF β’ PPT
π NoteBooks
π Videos
π― Topics
RNN
Character Level Embedding
Eager Execution in Tensorflow
π NoteBooks
π Videos
π― Topics
Image Captioning
Keras
π NoteBooks
π Videos
π¦ Files
Required files for training model
π― Topics
Seq2Seq Models
Machine Translation
π‘ Slides
Sequence to Sequence Models PDF β’ PPT
π Videos
π― Topics
NLP
Machine Translation
Attention Layer
Keras
π‘ Slides
Attention and Memory PDF β’ PPT
π NoteBooks
π― Topics
Spectrogram
Attention
CTC
Trigger Word Detection
RNNs
π‘ Slides
Speech Recognition and Trigger Word Detection using RNNs PDF β’ PPT
π NoteBooks
- [Trigger Word Detection](51-Trigger-word-detection/Trigger word detection - v1.ipynb)
π Videos
π― Topics
Trigger Word Detection
Collaborative Filtering
Recommendation systems
RNNs
π NoteBooks
π¦ Files
Excel used for Collaborative Filtering
π― Topics
Recommendation Systems
GANs
π‘ Slides
Neural Style Transfer PDF β’ PPT
π NoteBooks
Practices
- P1 - Basics
- P2 - Binary images and Morphology
- P3 - Edge detection, perspective transform, and using Webcam
- P4 - KNN classifier, and Intro to Neural Networks in datacamp
- P5 - Introduction to Neural Networks
- P6 - Implement and train classifiers, and using Google Colab
- P7 - Objects Recognition using webcam
- P8 - Intro to Tensorflow
- P9 - LSTM, GRU, and Word Embedding
quizzes
Guests
- Dr. Reza Ebrahimpour on Business and Graduate Studies
- Mohammad Chanarin Nakhaie on FastAI Introduction
- Mohammad Ghodoosi on Spiky Neural Networks
- Abolfazl Mehdizadeh on Image Captioning