- $49
Deep Learning for Computer Vision
- Course
- 116 Lessons
Learn the basics of Machine Learning. Dive deep into Deep Learning for Computer Vision Using TensorFlow 2. Master how to build, train, evaluate, test and Deploy Deep Learning Models. Understanding Key MLOps concepts. Going from beginner to solving real world problems efficiently!
Testimonials
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
Blake Sciutto
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
Sam Draper
Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua.
Dallas Sommers
Contents
introduction
intro
Welcome
General introduction
Course Material
Link to COde
Tensors and Variables in Tensorflow
Master tensor manipulation in Tensorflow 2
Link to Code
Basics
Initialization and Casting
Indexing
Maths Operations
Linear Algebra Operations
Common Methods
Ragged Tensors
Sparse Tensors
String Tensors
Variables
Building Neural Networks with Tensorflow
Master the basics of Tensorflow by creating and training a simple linear regression model
Link to Code
Link to Dataset
Task Understanding
Data Preparation
Linear regression Model
Error sanctioning
Training and optimization
Performance Measurement
Validation and testing
Corrective Measures
TensorFlow Datasets
Building Convolutional Neural Networks with Tensorflow [Malaria Diagnosis]
Creating a simple malaria diagnosis system with convnets
Link to Code
Task Understanding
Data Preparation
Data Visualization
Data Processing
How and Why Convolutional Neural Networks work
Building convnets with Tensorflow
Binary Crossentropy loss
Convnet training
Model evaluation and testing
Loading and saving Tensorflow model to Google drive
Building more advanced TensorFlow Models with Functional API, Subclassing and Custom Layers
Link to Code
Functional API
Model Subclassing
Custom Layers
Evaluating classification models
Exploring different ways of evaluating classification models
Link to Code
Precision, Recall, Accuracy
Confusion Matrix
ROC Plots
Improving model performance
Link to Code
Callbacks with Tensorflow
Learning rate scheduling
Model checkpointing
Mitigating overfitting and underfitting
Data augmentation
Link to Code
Data augmentation with TensorFlow using tf.image and Keras Layers
Mixup data augmentation
Cutmix data augmentation
Albumentations with Tensorflow and Pytorch for data augmentation
Advanced Tensorflow concepts
Link to Code
Eager and graph models in Tensorflow
Custom Loss and Metrics
Custom training loops in Tensorflow
Tensorboard integration
Link to Code
Data logging
View model graphs
Hyperparameter tuning
Profiling and visualizations with Tensorboard
Human emotions detection
Link to Code
Data preparation
Modeling and training
Data augmentation
Tensorflow records
Modern convolutional neural networks
Alexnet
Vggnet
Resnet
Coding Resnet
Mobilenet
Efficientnet
Transfer learning
Pretrained models
Finetuning
Dive into the blackbox
Visualizing intermediate layers
Grad-cam method
Link to Code
Class imbalance and ensembling
Ensembling
Class imbalance
Transformers in Vision
Understanding VITs
Building VITs from scratch
Image Classification with Huggingface Transformers
Link to Code
Introduction to Image Classification and Data Preparation
Modeling and training
Evaluation and Testing with Gradio
Model Deployment
Link to Code
Running Model with ONNX Runtime
Creating API with FastAPI
Object detection from scratch with YOLO
Understanding Object detection
Understanding the YOLO algorithm
Dataset Preparation
Building the YOLO Resnet Model
Data augmentation for object detection
Testing the object detection model
Data generators
Link to Code
Image Segmentation with UNET
Link to Code
Data Downloading
Data Splitting
Data Processing
Data Visualization with Matplotlib
Understanding Segformer
Model Creation
Image generation with VAEs and GANs
Link to Code Vae
Introduction to Image generation
Understanding Variational Autoencoders
VAE training and Digit Generation
Latent Space Visualizations
Link to Code GAN
How GANs work
The GAN Loss
Improving GAN training
Face Generation with GANs