| S.No |
Topic |
Sub-Topics |
| 1 | Introduction | Install TF, CPU vs GPU, Eager mode, Tensor basics |
| 2 | Tensor Operations | Tensor creation, slicing, reshaping, broadcasting |
| 3 | Computation Graph | Graph vs Eager, tf.function, autograph |
| 4 | Matrix Operations | MatMul, transpose, reduce ops |
| 5 | Datasets Basics | tf.data, map, batch, shuffle |
| 6 | TFRecords | Create TFRecords, serialize, parse |
| 7 | Keras Basics | Sequential model, compile, fit, evaluate |
| 8 | Functional API | Custom architectures, merging layers, multi-input models |
| 9 | Layer Types | Dense, Conv, RNN, Embedding, Flatten |
| 10 | Optimizers | Adam, SGD, RMSProp, custom optimizer |
| 11 | Loss Functions | MSE, CrossEntropy, Huber loss, custom loss |
| 12 | Callbacks | ModelCheckpoint, EarlyStopping, TensorBoard |
| 13 | Computer Vision Basics | Image preprocessing, CNN, Conv2D |
| 14 | Advanced CNN | ResNet, Inception, MobileNet, Fine-tuning |
| 15 | Data Augmentation | ImageDataGenerator, tf.image operations |
| 16 | NLP Basics | Text preprocessing, Tokenizer, Embedding |
| 17 | RNN Models | LSTM, GRU, Bi-LSTM |
| 18 | Transformers | Attention, BERT, Encoder-Decoder |
| 19 | Custom Layers | Layer subclassing, call(), build() |
| 20 | Custom Training Loop | GradientTape, train_step(), metrics |
| 21 | Model Saving & Loading | SavedModel, checkpoints, export |
| 22 | Performance Optimization | Mixed precision, profiling, XLA |
| 23 | Distributed Training | MirroredStrategy, Multi-GPU training |
| 24 | TPU & Cloud Training | TPU setup, strategy, distributed datasets |
| 25 | TensorFlow Serving | REST API, Docker deployment |
| 26 | TensorFlow Lite | Quantization, TFLite conversion, mobile deployment |
| 27 | Object Detection | TFOD API, SSD, Faster R-CNN |
| 28 | Image Segmentation | U-Net, Mask R-CNN, FCN |
| 29 | AutoML + KerasTuner | Hyperparameter tuning, search strategies |
| 30 | MLOps Pipeline | CI/CD, model registry, orchestration |
| 31 | End-to-End Project | Data → Training → Evaluation → Serving deployment |
