Tag: tensorflow
Posts of Tag: tensorflow
  1. Understanding TensorFlow's @tf.function Decorator

    .lazyload-placeholder { display: none; } Introduction Improving the performance of a training loop can save hours of computing time when training machine learning models. One of the ways of improving the perfor...Learn More
    PythonFunctionMachine LearningDeep Learningtensorflow
  2. RandAugment for Image Classification with Keras/TensorFlow

    .lazyload-placeholder { display: none; } Data augmentation has, for a long while, been serving as a means of replacing a "static" dataset with transformed variants, bolstering the invariance of Convolutional Ne...Learn More
    PythonMachine LearningImageDeep Learningkerastensorflowcomputer vision
  3. What is 'from_logits=True' in Keras/TensorFlow Loss Functions?

    .lazyload-placeholder { display: none; } Deep Learning frameworks like Keras lower the barrier to entry for the masses and democratize the development of DL models to unexperienced folk, who can rely on reasona...Learn More
    PythonFunctionMachine LearningDeep Learningkerastensorflow
  4. Don't Use Flatten() - Global Pooling for CNNs with TensorFlow and Keras

    .lazyload-placeholder { display: none; } Most practitioners, while first learning about Convolutional Neural Network (CNN) architectures - learn that it's comprised of three basic segments: Convolutional Layer...Learn More
    PythonMachine LearningDeep Learningkerastensorflowcomputer vision
  5. 5-Line GPT-Style Text Generation in Python with TensorFlow/Keras

    .lazyload-placeholder { display: none; } Transformers, even though released in 2017, have only started gaining significant traction in the last couple of years. With the proliferation of the technology through ...Learn More
    PythonMachine LearningDeep Learningkerastensorflownlp
  6. Transformer Token and Position Embedding with Keras

    .lazyload-placeholder { display: none; } Introduction There are plenty of guides explaining how transformers work, and for building an intuition on a key element of them - token and position embedding. Position...Learn More
    PythonMachine LearningDeep Learningkerastensorflownlp
  7. Split Train, Test and Validation Sets with Tensorflow Datasets - tfds

    Introduction Tensorflow Datasets, also known as tfds is is a library that serves as a wrapper to a wide selection of datasets, with proprietary functions to load, split and prepare datasets for Machine and Deep...Learn More
    PythonMachine LearningDeep LearningValidationdata sciencetensorflow
  8. Image Classification with Transfer Learning in Keras - Create Cutting Edge CNN Models

    Introduction Deep Learning models are very versatile and powerful - they're routinely outperforming humans in narrow tasks, and their generalization power is increasing at a rapid rate. New models are being rel...Learn More
    PythonMachine LearningImageDeep Learningartificial intelligencekerastensorflow
  9. Machine Learning: Overfitting Is Your Friend, Not Your Foe

    Note: These are the musings of a man - flawed and prone to misjudgement. The point of writing this is to promote a discussion on the topic, not to be right or contrarian. If an...Learn More
    PythonMachine Learningartificial intelligencekerastensorflow
  10. Keras Callbacks: Save and Visualize Prediction on Each Training Epoch

    Introduction Keras is a high-level API, typically used with the Tensorflow library, and has lowered the barrier to entry for many and democratized the creation of Deep Learning models and systems. When just sta...Learn More
    PythonMachine Learningdata scienceartificial intelligencekerastensorflow
  11. Hands-On House Price Prediction - Deep Learning in Python with Keras

    In this short series of guides, we'll be taking a look at a hands-on house price prediction. We'll be using Keras, the deep learning API built on top of TensorFlow to train a neural network to predict the price...Learn More
    PythonMachine Learningdata scienceartificial intelligencekerastensorflow
  12. Installing TensorFlow on Windows

    Installing TensorFlow on Windows Introduction to TensorFlow TensorFlow is a deep learning framework that provides an easy interface to a variety of functionalities, required to perform state of the art deep lea...Learn More