B3. Implement Image Captioning with Recurrent Neural Networks (Abdul Rehman Yousaf, 2022)

1. Course Overview: 1. Course Overview 00:00:00 2. Introducing Image Captioning: 1. Overview 00:01:49 2. What Is Image Captioning and Why Is It Important 00:04:48 3. Introducing the Business Case Study for Image-captioning 00:08:14 4. Proposed Solutions for Image Captioning Case Study 00:10:33 5. Summary 00:16:47 3. Preparing Data for Image Captioning Models: 1. Module and Project Overview 00:17:48 2. Demo - Load and Explore the Dataset 00:25:28 3. Demo - Pre-processing the Images Data 00:35:50 4. Demo - Pre-processing the Captions Data 00:43:34 5. Demo - Prepare Training Data Using Pre-processed Data 00:50:06 6. Summary 00:53:57 4. Building the Model for Image Captioning Using Tensorflow: 1. Overview 00:54:48 2. Demo - Build the Attention Model for Image-captioning Using TensorFlow 00:55:59 3. Demo - Implement CNN Encoder in TensorFlow 01:01:19 4. Demo - Implement RNN Decoder with Attention & Sentence Generator 01:02:36 5. Demo - Define the Loss Function and Model Checkpoints 01:05:00 6. Demo - Perform Model Training 01:07:47 7. Demo - Making Predictions out of the Trained Model 01:11:13 8. Summary 01:12:49 5. Evaluating Deep Learning Models for Image Captioning: 1. Overview 01:13:38 2. Meshed Memory Transformer for Image Captioning 01:14:37 3. Evaluation Metrics for Image Captioning 01:18:21 4. Bottom-up and Top-down Attention for Image Captioning 01:28:37 5. Summary 01:31:12