TensorFlow is a machine learning library that was open-sourced by Google. Beyond the ability to work on problems with traditional machine learning, TensorFlow is most popularly used for Deep Learning. It provides an extensive library of tools for research in deep learning to the deployment of such models.
This competency includes implementation of complex neural network architectures, distributed training, tensorflow in production using TFX, using tensorboard to visualize states of the machine learning workflow, and usage of TFRecord.
- Neural Network Architectures - Ability to use TensorFlow Keras to solve more complex problems on unstructured data such as: image classification, segmentation, object detection, text summarization, video/audio classification. such as images, videos,visual, language, audio, etc using different neural network architectures using convolution layers, recurrent layers, etc.
- Using Pre-trained models - Ability to load and fine tune pre-trained models for different tasks.
- Distributed Training - Ability to setup distributed training using tensorflow.distribute for models across multiple GPUs, TPUs, or even machines.
- Production and TFX - Usage of TFX for serving models and building APIs for models. A good understanding of how TensorFlow can be used for large-scale machine learning.
- TensorBoard - Usage for TensorBoard for measuring and visualizing different states of a machine learning workflow.
- TFRecord - Usage of TFRecords for saving and loading data. TFRecord is a way to store structured data in a sequence of binary strings that can be used efficiently across platforms.