English | MP4 | AVC 1280×720 | AAC 44KHz 2ch | 86 lectures (32h 28m) | 14.93 GB
Master and Deploy Image Classification solutions with Tensorflow using models like Convnets and Vision Transformers
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 Huggingface
You will learn:
- The Basics of Tensorflow (Tensors, Model building, training, and evaluation)
- Deep Learning algorithms like Convolutional neural networks and Vision Transformers
- Evaluation of Classification Models (Precision, Recall, Accuracy, F1-score, Confusion Matrix, ROC Curve)
- Mitigating overfitting with Data augmentation
- Advanced Tensorflow concepts like Custom Losses and Metrics, Eager and Graph Modes and Custom Training Loops, Tensorboard
- Machine 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 Detection
- Transfer 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!
Table of Contents
Introduction
1 Welcome
2 General Introduction
Tensors and variables
3 Basics
4 Initialization and Casting
5 Indexing
6 Maths Operations
7 Linear Algebra Operations
8 Common Methods
9 RaggedTensors
10 Sparse Tensors
11 String Tensors
12 Variables
PREREQUISCITE Building neural networks with Tensorflow
13 Understanding the Task
14 Data Preparation
15 Linear Regression Model
16 Error Sanctioning
17 Training and Optimization
18 Performance Measurement
19 Validation and Testing
20 Corrective Measures
Building convnets with tensorflow
21 Understanding the Task
22 Data Preparation
23 Data Visualization
24 Data Processing
25 How and Why Convolutional Neural Networks Work
26 Building ConvNets with TensorFlow
27 Binary Crossentropy Loss
28 Training
29 Model Evaluation and Testing
30 Loading and Saving tensorflow models to gdrive
Building more advanced TensorFlow Models with Functional API Subclassing and Cu
31 Functional API
32 Model Subclassing
33 Custom Layers
Evaluating Classification Models
34 PrecisionRecallAccuracy
35 Confusion Matrix
36 ROC curve
Improving Model Performance
37 Callbacks with TensorFlow
38 Learning Rate Scheduling
39 Model Checkpointing
40 Mitigating Overfitting and Underfitting with Dropout Regularization
Data Augmentation
41 Data augmentation with TensorFlow using tfimage and Keras Layers
42 Mixup Data augmentation with TensorFlow 2 with intergration in tfdata
43 Cutmix Data augmentation with TensorFlow 2 and intergration in tfdata
44 Albumentations with TensorFlow 2 and PyTorch for Data augmentation
Advanced Tensorflow
45 Custom Loss and Metrics in TensorFlow 2
46 Eager and Graph Modes in TensorFlow 2
47 Custom Training Loops in TensorFlow 2
Tensorboard integration with TensorFlow 2
48 Log data
49 view model graphs
50 hyperparameter tuning
51 Profiling and other visualizations with Tensorboard
MLOps with Weights and Biases
52 Experiment Tracking
53 Hyperparameter Tuning with Weights and Biases and TensorFlow 2
54 Dataset Versioning with Weights and Biases and TensorFlow 2
55 Model Versioning with Weights and Biases and TensorFlow 2
Human Emotions Detection
56 data preparation
57 Modeling and Training
58 Data augmentation
59 Tensorflow records
Modern Convolutional Neural Networks
60 Alexnet
61 vggnet
62 resnet
63 coding resnet
64 mobilenet
65 efficientnet
Transfer learning
66 Pretrained Models
67 Finetuning
Understanding the blackbox
68 visualizing intermediate layers
69 gradcam method
Class Imbalance and Ensembling
70 Ensembling
71 Class imbalance
Transformers in Vision
72 Understanding VITs
73 Building VITs from scratch
74 Finetuning Huggingface VITs
75 Model Evaluation with Wandb
76 Data efficient Transformers
77 Swin Transformers
Deploying the Image classification model
78 Conversion from tensorflow to Onnx Model
79 Understanding quantization
80 Practical quantization of Onnx Model
81 Quantization Aware training
82 Conversion to tensorflowlite model
83 How APIs work
84 Building API with Fastapi
85 Deploying API to the Cloud
86 Load testing API
Resolve the captcha to access the links!