AI-powered search & chat for Data / Computer Science Students
Uploading Models with KerasNLP
Load Model If you want to build a Causal LM based on a base model, simply call keras_nlp.models.CausalLM.from_preset and pass a built-in preset identifier. Fine-tune Model After loading the model, you...
Read more at Keras Developer guides
Segment Anything in KerasCV!
Overview The Segment Anything Model (SAM) produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been t...
Read more at Keras Developer guides
Custom Image Augmentations with BaseImageAugmentationLayer
Overview Data augmentation is an integral part of training any robust computer vision model. While KerasCV offers a plethora of prebuild high quality data augmentation techniques, you may still want t...
Read more at Keras Developer guides
Distributed training with Keras 3
Introduction The Keras distribution API is a new interface designed to facilitate distributed deep learning across a variety of backends like JAX, TensorFlow and PyTorch. This powerful API introduces ...
Read more at Keras Developer guides
Migrating Keras 2 code to multi-backend Keras 3
Setup First, lets install keras-nightly . This example uses the TensorFlow backend ( os.environ["KERAS_BACKEND"] = "tensorflow" ). After you've migrated your code, you can change the "tensorflow" stri...
Read more at Keras Developer guides
Semantic Segmentation with KerasCV
Background Semantic segmentation is a type of computer vision task that involves assigning a class label such as person, bike, or background to each individual pixel of an image, effectively dividing ...
Read more at Keras Developer guides
Multi-GPU distributed training with JAX
Introduction There are generally two ways to distribute computation across multiple devices: Data parallelism , where a single model gets replicated on multiple devices or multiple machines. Each of t...
Read more at Keras Developer guides
Multi-GPU distributed training with PyTorch
Introduction There are generally two ways to distribute computation across multiple devices: Data parallelism , where a single model gets replicated on multiple devices or multiple machines. Each of t...
Read more at Keras Developer guides
Multi-GPU distributed training with TensorFlow
Introduction There are generally two ways to distribute computation across multiple devices: Data parallelism , where a single model gets replicated on multiple devices or multiple machines. Each of t...
Read more at Keras Developer guides
Customizing what happens in
Introduction When you're doing supervised learning, you can use fit() and everything works smoothly. When you need to take control of every little detail, you can write your own training loop entirely...
Read more at Keras Developer guides
Customizing what happens in
Introduction When you're doing supervised learning, you can use fit() and everything works smoothly. When you need to take control of every little detail, you can write your own training loop entirely...
Read more at Keras Developer guides
Customizing what happens in
Introduction When you're doing supervised learning, you can use fit() and everything works smoothly. When you need to take control of every little detail, you can write your own training loop entirely...
Read more at Keras Developer guides
Writing a training loop from scratch in JAX
Setup Introduction Keras provides default training and evaluation loops, fit() and evaluate() . Their usage is covered in the guide Training & evaluation with the built-in methods . If you want to cus...
Read more at Keras Developer guides
The Functional API
Setup Introduction The Keras functional API is a way to create models that are more flexible than the keras.Sequential API. The functional API can handle models with non-linear topology, shared layers...
Read more at Keras Developer guides
The Sequential model
Setup When to use a Sequential model A Sequential model is appropriate for a plain stack of layers where each layer has exactly one input tensor and one output tensor . Schematically, the following Se...
Read more at Keras Developer guides
Transfer learning & fine-tuning
Setup Introduction Transfer learning consists of taking features learned on one problem, and leveraging them on a new, similar problem. For instance, features from a model that has learned to identify...
Read more at Keras Developer guides
Writing a training loop from scratch in PyTorch
Setup Introduction Keras provides default training and evaluation loops, fit() and evaluate() . Their usage is covered in the guide Training & evaluation with the built-in methods . If you want to cus...
Read more at Keras Developer guides
Writing a training loop from scratch in TensorFlow
Setup Introduction Keras provides default training and evaluation loops, fit() and evaluate() . Their usage is covered in the guide Training & evaluation with the built-in methods . If you want to cus...
Read more at Keras Developer guides
Training & evaluation with the built-in methods
Setup Introduction This guide covers training, evaluation, and prediction (inference) models when using built-in APIs for training & validation (such as Model.fit() , Model.evaluate() and Model.predic...
Read more at Keras Developer guides
Writing your own callbacks
Introduction A callback is a powerful tool to customize the behavior of a Keras model during training, evaluation, or inference. Examples include keras.callbacks.TensorBoard to visualize training prog...
Read more at Keras Developer guides
Object Detection with KerasCV
Object detection introduction Object detection is the process of identifying, classifying, and localizing objects within a given image. Typically, your inputs are images, and your labels are bounding ...
Read more at Keras Developer guides
Classification with KerasCV
Inference with a pretrained classifier Let's get started with the simplest KerasCV API: a pretrained classifier. In this example, we will construct a classifier that was pretrained on the ImageNet dat...
Read more at Keras Developer guides
Customizing Saving and Serialization
Introduction This guide covers advanced methods that can be customized in Keras saving. For most users, the methods outlined in the primary Serialize, save, and export guide are sufficient. APIs We wi...
Read more at Keras Developer guides
Handling failed trials in KerasTuner
Introduction A KerasTuner program may take a long time to run since each model may take a long time to train. We do not want the program to fail just because some trials failed randomly. In this guide...
Read more at Keras Developer guides- «
- ‹