Solving Machine Learning Problems in TensorFlow/Keras (Image Processing using Deep Learning

Cui i se adresează?

Acest curs se adresează Machine Learning Engineers – image processing

Ce vei învăța?

În cadrul acestui curs cursanții vor învăța despre clasificarea și localizarea imaginilor împreună cu cele mai bune practici în Computer Vision.

Cerințe preliminare:

Pentru a putea participa în cadrul acestui curs, studenții trebuie să fi parcurs modulul Basic Machine Learning în Tensorflow/Keras.

Este recomandat ca studenții să aibă următoarele cunoștințe:

Basic Deep Learning

● Neurons
● Types of Layers
● Networks
● Loss Functions
● Optimizers
● Overfitting
● Tensorflow

Basic Image Processing/Computer Vision

● Encoding
● Color Spaces
● Convolutions
● OpenCV/PIL

Agenda cursului:

Materialele de curs sunt în limba Engleză. Predarea se face în limba Română.

Module 1: Introduction to Deep Learning in Image Processing

  • Machine Learning and Deep Learning
  • Neural Network Anatomy
  • Types of Convolutions
  • Keras Workflow

 Module 2: Basic Image Processing and Computer Vision

  • Pixels and Images
  • Coordinate System
  • Channels
  • OpenCV
  • Channel Ordering
  • Blur and Sharpen kernels

Hands-on Lab: Learn basic Image Processing using OpenCV, learn to apply different filter kernels on images for blur generation or basic edge detection.

Module 3: Supervised Neural Networks and Regularization

  • Underfitting
  • Overfitting
  • Reducing the networks size
  • Weight Regularization: L1, L2, Elastic
  • Dropout
  • Batch Normalization

Hands-on Lab: Implement your first basic neural network, learn how to benchmark it and learn how to avoid overfitting on a Computer Vision classification task.

 Module 4: Convolutional Neural Networks

  • Convolutional Layers
  • Depthwise Convolutions
  • Building Convolutional Neural Networks in Keras
  • 1×1 Convolutions
  • Data Augmentation

Hands-on Lab: Improve your previous neural network by adding Convolutional Layers, benchmark them and compare them with the Fully Connected ones.

 Module 5: Common Convolutional Neural Networks Architectures

  • ImageNet
  • AlexNet
  • VGGNet
  • ResNet
  • MobileNet

Hands-on Lab:  Learn how to use already state of the art models from the Keras Hub.

Module 6: Reusing Convolutional Neural Networks

  • Object Localization
  • Object Segmentation
  • Reusing VGG
  • Fine-tuning

Hands-on Lab: Learn how to fine parameter tune your already trained Convolutional Neural Network to fit your task.

 Module 7: Explainable AI

  • Visualizing intermediate activations
  • Visualizing convnet
  • Visualizing heatmaps

Module 8: Unsupervised Generative Models for Image Processing

  • Autoencoders for Images
  • Deblurring
  • Image generation

Hands-on Lab: Generate a new image similar to the ones from the dataset by using a random seed. Face generation techniques

Module 9: Real World Machine Learning

  • Tensorboard
  • Deploying Deep Learning Models
  • Choosing the algorithm

Recomandăm să continui cu:

Programe de certificare

Solving Machine Learning Problems in TensorFlow/Keras (Image Processing using Deep Learning)

Oferte personalizate pentru grupuri de minim 2 persoane

Detalii curs

Durată:

2
zile

Preț:

840 EUR

Livrare:

Clasă virtuală

Nivel:

3. Advanced

Oferte personalizate pentru grupuri de minim 2 persoane