EIEIOTECHNOVATION
← Training programmes

EIEIO / ARTIFICIAL INTELLIGENCE

Advanced Deep Learning for Practical Computer Vision (4 days)

Course outline

4 days
Discuss this programme →

Duration

Advanced Deep Learning for Practical Computer Vision

4 days

Overview

The area of ​​Natural Language Processing (NLP) is a subarea of ​​Artificial Intelligence that aims to make computers capable of understanding human language, both written and spoken. Some examples of practical applications are: translators between languages, translation from text to speech or speech to text, chatbots, automatic question and answer systems (Q&A), automatic generation of descriptions for images, generation of subtitles in videos, classification of sentiments in sentences, among many others! Learning this area can be the key to bringing real solutions to present and future needs!

Equip yourself and your team with the knowledge needed to thrive in this AI-driven era.

Outline

Tensors and Variables

  • Tensor Basics
  • Tensor Initialization and Casting
  • Indexing
  • Maths Operations in Tensorflow
  • Linear Algebra Operations in Tensorflow
  • Common Tensorflow Methods
  • Ragged Tensors
  • Sparse Tensors
  • String Tensors
  • Tensorflow Variables

Building a Simple Neural Network in Tensorflow

  • Link to Dataset
  • Task Understanding
  • Data Preparation
  • Linear Regression Model
  • Error Sanctioning
  • Training and Optimization
  • Performance Measurement
  • Validation and Testing
  • Corrective Measures

Building Convolutional Neural Networks

  • Task Understanding
  • Data Preparation
  • Data Visualization
  • Data Processing
  • How and Why Convolutional Neural Networks work
  • Building Convnets in Tensorflow

Binary Crossentropy Loss

  • Convnet Training
  • Model Evaluation and Testing
  • Loading and Saving Tensorflow Models to Google Drive

Building more advanced Models with Functional API, Subclassing and Custom Layers

  • Functional API
  • Model Subclassing
  • Custom Layers

Evaluating Classification Models

  • Precision,Recall and Accuracy
  • Confusion Matrix
  • ROC Curve

Improving Model Performance

  • Tensorflow Callbacks
  • Learning rate scheduling
  • Model checkpointing
  • Mitigating Overfitting and Underfitting with Dropout, Regularization

Data Augmentation

  • Data augmentation with TensorFlow using tf.image and Keras Layers
  • Mixup Data augmentation with TensorFlow 2 with intergration in tf.data
  • Cutmix Data augmentation with TensorFlow 2 and intergration in tf.data
  • Albumentations with TensorFlow 2 and PyTorch for Data augmentation

Advanced Tensorflow Concepts

  • Custom Loss and Metrics
  • Eager and Graph Modes

Custom Training Loops

  • Tensorboard Integration
  • Data Logging
  • Viewing Model Graphs
  • Hyperparameter tuning
  • Profiling and other visualizations with Tensorboard

MLOps with Weights and Biases

  • Experiment Tracking
  • Hyperparameter Tuning with Weights and Biases and TensorFlow 2
  • Dataset Versioning with Weights and Biases and TensorFlow 2
  • Data Versioning with Wandb
  • Model Versioning with Weights and Biases and TensorFlow 2

Human Emotions Detection

  • Data Preparation
  • Modeling and Training
  • Data augmentation
  • Tensorflow Records

Modern Convolutional Neural Networks

  • Alexnet
  • Vggnet
  • Resnet
  • Coding Resnet
  • Mobilenet
  • Efficientnet

Transfer Learning

  • Leveraging Pretrained Models
  • Finetuning

Diving into the blackbox

  • Visualizing intermediate layers
  • Grad-cam Method
  • Ensembling and class imbalance
  • Ensembling
  • Class Imbalance

Transformers in Vision

  • Understanding VITs
  • Building VITs from scratch
  • Finetuning Huggingface Transformers
  • Model Evaluation with Wandb
  • Data efficient transformers
  • Swin Transformers

Model Deployment

  • Model Conversion from Tensorflow to Onnx
  • Understanding quantization
  • Practical quantization of Onnx model
  • Quantization Aware training
  • Conversion to Tensorflow lite model

What is an API

  • Building the Emotions Detection API with Fastapi
  • Deploy the Emotions Detection API to the Cloud
  • Load tesing the Emotions Detection API with Locust

Object Detection with YOLO algorithm

  • Understanding object detection
  • YOLO Paper
  • Dataset Preparation
  • YOLO Resnet
  • YOLO Loss
  • Data augmentation
  • Testing
  • Data generators

Image segmentation

  • Image Segmentation - Oxford IIIT Pet Dataset
  • UNET model
  • Training and Optimization
  • Data Augmentation and Dropout
  • Class weighting and reduced network

People Counting

  • People Counting - Shangai Tech Dataset
  • Dataset Preparation
  • CSRNET
  • Training and Optimization
  • Data Augmentation

Image Generation

  • Introduction to Image generation
  • Understanding Variational autoencoders
  • VAE training and digit generation
  • Latent space visualizations

How GANs work

  • The GAN Loss
  • Improving GAN training
  • Face generation with GANs

Programme scope, delivery arrangements and suitability are confirmed during enquiry.