A series of Jupyter notebooks exploring TensorFlow and Keras APIs for deep learning. Covers CNNs on CIFAR10/MNIST, subclassing models, transfer learning, data pipelines, augmentation, image loading, low-level APIs, and custom layers/functions. Demonstrates practical implementations with fine-tuning, preprocessing, and visualization techniques.

Implementation of multiple deep learning models using Keras Functional API, including a CNN on MNIST, a multi-input/multi-output example, and a toy ResNet on CIFAR-10. Demonstrates advanced model architectures, tf.data pipelines, and practical training workflows with TensorFlow Datasets.

Implementation and training of custom layers in TensorFlow/Keras using subclassing. Includes weight definition, initialization, regularization, and integration of the layer into a complete model for training and evaluation.

Collection of TensorFlow/Keras Jupyter notebooks demonstrating low-level APIs, custom training loops, callbacks, subclassed models, custom loss functions, transfer learning, and advanced deep learning architectures.

Loading, inspecting, and preprocessing datasets using TensorFlow Datasets (TFDS). Demonstrates train/test split handling, image normalization, batching, shuffling, caching, and visualization to build efficient, ready-to-train deep learning pipelines.

Hands-on deep dive into TensorFlow’s low-level API — covering tensor creation, shape manipulation, broadcasting, slicing, and math operations. Builds a strong foundation for custom deep learning workflows without relying solely on high-level abstractions.

An in-depth guide to customizing model.fit() in TensorFlow/Keras by overriding the train_step function. Covers the manual implementation of the forward pass, loss calculation, gradient application, and metric updates. Includes a basic GAN implementation as a practical example.

Implementation of a custom TensorFlow/Keras model by subclassing tf.keras.Model, including custom layers, a user-defined loss function, and full control over the forward pass. Demonstrates dataset loading, preprocessing, and training on MNIST using the Model Subclassing API for maximum flexibility

Efficient image data loading and preprocessing pipeline using TensorFlow and Keras. Includes directory-based dataset loading, normalization, resizing, batching, and performance optimization with caching, shuffling, and prefetching for high-throughput model training.

Practical guide to building high-performance data pipelines in TensorFlow using the tf.data API. Covers dataset creation, preprocessing, shuffling, batching, caching, and prefetching with AUTOTUNE to maximize training throughput and hardware utilization.

An end-to-end implementation of a custom training and validation loop for a CNN on the Fashion MNIST dataset. This project demonstrates low-level model training using tf.GradientTape and tf.keras.metrics, without relying on model.fit().

Custom TensorFlow training loops for image classification: a foundational CNN on Eurosat using tf.GradientTape for learning, and an optimized MNIST MLP with BatchNorm, Dropout, and learning rate scheduling for higher accuracy.

Implementation of Linear Regression using TensorFlow's low-level API with a custom tf.GradientTape training loop. Covers manual gradient computation, weight updates, and visualization of predictions vs actual values for educational understanding of core training mechanics.

Implementation of a custom TensorFlow/Keras model by subclassing tf.keras.Model. Includes custom layers, a user-defined loss function, and full control over the forward pass while maintaining compatibility with the Keras fit/evaluate workflow.