Linear Regression, Logistic Regression and Neural Networks built from scratch.
Basics of Tensorflow and training neural networks with TensorFlow 2.
Convolutional Neural Networks applied to Malaria Detection
Building more advanced Tensorflow models with Functional API, Model Subclassing and Custom Layers
Evaluating Classification Models using different metrics like: Precision,Recall,Accuracy and F1-score
Classification Model Evaluation with Confusion Matrix and ROC Curve
Tensorflow Callbacks, Learning Rate Scheduling and Model Check-pointing
Mitigating Overfitting and Underfitting with Dropout, Regularization, Data augmentation
Data augmentation with TensorFlow using TensorFlow image and Keras Layers
Advanced augmentation strategies like Cutmix and Mixup
Data augmentation with Albumentations with TensorFlow 2 and PyTorch
Custom Loss and Metrics in TensorFlow 2
Eager and Graph Modes in TensorFlow 2
Custom Training Loops in TensorFlow 2
Integrating Tensorboard with TensorFlow 2 for data logging, viewing model graphs, hyperparameter tuning and profiling
Machine Learning Operations (MLOps) with Weights and Biases
Experiment tracking with Wandb
Hyperparameter tuning with Wandb
Dataset versioning with Wandb
Model versioning with Wandb
Human emotions detection
Modern convolutional neural networks(Alexnet, Vggnet, Resnet, Mobilenet, EfficientNet)
Transfer learning
Visualizing convnet intermediate layers
Grad-cam method
Model ensembling and class imbalance
Transformers in Vision
Huggingface Transformers
Vision Transformers
Model deployment
Conversion from tensorflow to Onnx Model
Quantization Aware training
Building API with Fastapi
Deploying API to the Cloud
Requirements
Basic Knowledge of Python
Access to an internet connection, as we shall be using Google Colab (free version)
Description
Image classification models find themselves in different places today, like farms, hospitals, industries, schools, and highways,... With the creation of much more efficient deep learning models from the early 2010s, we have seen a great improvement in the state of the art in the domain of image classification.In this course, we shall take you on an amazing journey in which you'll master different concepts with a step-by-step approach. We shall start by understanding how image classification algorithms work, and deploying them to the cloud while observing best practices. We are going to be using Tensorflow 2 (the world's most popular library for deep learning, built by Google) and HuggingfaceYou will learn:The Basics of Tensorflow (Tensors, Model building, training, and evaluation)Deep Learning algorithms like Convolutional neural networks and Vision TransformersEvaluation of Classification Models (Precision, Recall, Accuracy, F1-score, Confusion Matrix, ROC Curve)Mitigating overfitting with Data augmentationAdvanced Tensorflow concepts like Custom Losses and Metrics, Eager and Graph Modes and Custom Training Loops, TensorboardMachine Learning Operations (MLOps) with Weights and Biases (Experiment Tracking, Hyperparameter Tuning, Dataset Versioning, Model Versioning)Binary Classification with Malaria detection Multi-class Classification with Human Emotions DetectionTransfer learning with modern Convnets (Vggnet, Resnet, Mobilenet, Efficientnet)Model Deployment (Onnx format, Quantization, Fastapi, Heroku Cloud)If you are willing to move a step further in your career, this course is destined for you and we are super excited to help achieve your goals!This course is offered to you by Neuralearn. And just like every other course by Neuralearn, we lay much emphasis on feedback. Your reviews and questions in the forum will help us better this course. Feel free to ask as many questions as possible on the forum. We do our very best to reply in the shortest possible time.Enjoy!!!
Overview
Section 1: Introduction
Lecture 1 Welcome
Lecture 2 General Introduction
Section 2: Tensors and variables
Lecture 3 Basics
Lecture 4 Initialization and Casting
Lecture 5 Indexing
Lecture 6 Maths Operations
Lecture 7 Linear Algebra Operations
Lecture 8 Common Methods
Lecture 9 RaggedTensors
Lecture 10 Sparse Tensors
Lecture 11 String Tensors
Lecture 12 Variables
Section 3:[PRE-REQUISCITE] Building neural networks with Tensorflow
Lecture 13 Understanding the Task
Lecture 14 Data Preparation
Lecture 15 Linear Regression Model
Lecture 16 Error Sanctioning
Lecture 17 Training and Optimization
Lecture 18 Performance Measurement
Lecture 19 Validation and Testing
Lecture 20 Corrective Measures
Section 4: Building convnets with tensorflow
Lecture 21 Understanding the Task
Lecture 22 Data Preparation
Lecture 23 Data Visualization
Lecture 24 Data Processing
Lecture 25 How and Why Convolutional Neural Networks Work
Lecture 26 Building ConvNets with TensorFlow
Lecture 27 Binary Crossentropy Loss
Lecture 28 Training
Lecture 29 Model Evaluation and Testing
Lecture 30 Loading and Saving tensorflow models to gdrive
Section 5: Building more advanced TensorFlow Models with Functional API, Subclassing and Cu
Lecture 31 Functional API
Lecture 32 Model Subclassing
Lecture 33 Custom Layers
Section 6: Evaluating Classification Models
Lecture 34 Precision,Recall,Accuracy
Lecture 35 Confusion Matrix
Lecture 36 ROC curve
Section 7: Improving Model Performance
Lecture 37 Callbacks with TensorFlow,
Lecture 38 Learning Rate Scheduling,
Lecture 39 Model Checkpointing
Lecture 40 Mitigating Overfitting and Underfitting with Dropout, Regularization
Section 8: Data Augmentation
Lecture 41 Data augmentation with TensorFlow using tf.image and Keras Layers
Lecture 42 Mixup Data augmentation with TensorFlow 2 with intergration in tf.data
Lecture 43 Cutmix Data augmentation with TensorFlow 2 and intergration in tf.data
Lecture 44 Albumentations with TensorFlow 2 and PyTorch for Data augmentation
Section 9: Advanced Tensorflow
Lecture 45 Custom Loss and Metrics in TensorFlow 2
Lecture 46 Eager and Graph Modes in TensorFlow 2
Lecture 47 Custom Training Loops in TensorFlow 2
Section 10: Tensorboard integration with TensorFlow 2
Lecture 48 Log data
Lecture 49 view model graphs
Lecture 50 hyperparameter tuning
Lecture 51 Profiling and other visualizations with Tensorboard
Section 11: MLOps with Weights and Biases
Lecture 52 Experiment Tracking
Lecture 53 Hyperparameter Tuning with Weights and Biases and TensorFlow 2
Lecture 54 Dataset Versioning with Weights and Biases and TensorFlow 2
Lecture 55 Model Versioning with Weights and Biases and TensorFlow 2
Section 12: Human Emotions Detection
Lecture 56 data preparation
Lecture 57 Modeling and Training
Lecture 58 Data augmentation
Lecture 59 Tensorflow records
Section 13: Modern Convolutional Neural Networks
Lecture 60 Alexnet
Lecture 61 vggnet
Lecture 62 resnet
Lecture 63 coding resnet
Lecture 64 mobilenet
Lecture 65 efficientnet
Section 14: Transfer learning
Lecture 66 Pretrained Models
Lecture 67 Finetuning
Section 15: Understanding the blackbox
Lecture 68 visualizing intermediate layers
Lecture 69 grad-cam method
Section 16: Class Imbalance and Ensembling
Lecture 70 Ensembling
Lecture 71 Class imbalance
Section 17: Transformers in Vision
Lecture 72 Understanding VITs
Lecture 73 Building VITs from scratch
Lecture 74 Finetuning Huggingface VITs
Lecture 75 Model Evaluation with Wandb
Lecture 76 Data efficient Transformers
Lecture 77 Swin Transformers
Section 18: Deploying the Image classification model
Lecture 78 Conversion from tensorflow to Onnx Model
Lecture 79 Understanding quantization
Lecture 80 Practical quantization of Onnx Model
Lecture 81 Quantization Aware training
Lecture 82 Conversion to tensorflowlite model
Lecture 83 How APIs work
Lecture 84 Building API with Fastapi
Lecture 85 Deploying API to the Cloud
Lecture 86 Load testing API
Beginner Python Developers curious about Applying Deep Learning for Computer vision,Deep Learning for Computer vision Practitioners who want gain a mastery of how things work under the hood,Anyone who wants to master deep learning fundamentals and also practice deep learning for image classification using best practices in TensorFlow.,Computer Vision practitioners who want to learn how state of art image classification models are built and trained using deep learning.,Anyone wanting to deploy image classification Models,Learners who want a practical approach to Deep learning for image classification

Homepage

https://www.udemy.com/course/deep-learning-image-classification-with-tensorflow-in-2023/