The Lambda
Deep Learning Blog

Published on June 3, 2020 by Chuan Li

by Chuan Li, PhD

Published on December 19, 2019 by Chuan Li

by Chuan Li, PhD

Published on October 1, 2019 by Chuan Li

TensorFlow 2 is now live! This tutorial walks you through the process of building a simple CIFAR-10 image classifier using deep learning. In this tutorial, we ...

Published on August 28, 2019 by Chuan Li

This blog will walk you through the steps of setting up a Horovod + Keras environment for multi-GPU training.

Published on August 12, 2019 by Chuan Li

One of the most asked questions we get at Lambda Labs is, “how do I track resource utilization for deep learning jobs?” Resource utilization tracking can help ...

Published on June 7, 2019 by Chuan Li

Distributed training allows scaling up deep learning task so bigger models can be learned or training can be conducted at a faster pace. In a previous ...

Published on June 6, 2019 by Chuan Li

During training, weights in the neural networks are updated so that the model performs better on the training data. For a while, improvements on the training ...

Published on June 6, 2019 by Chuan Li

This tutorial combines two items from previous tutorials: saving models and callbacks. Checkpoints are saved model states that occur during training. With ...

Published on June 5, 2019 by Chuan Li

This tutorial shows you how to perform transfer learning using TensorFlow 2.0. We will cover:

Published on February 11, 2019 by Chuan Li

Deep Learning requires GPUs, which are very expensive to rent in the cloud. In this post, we compare the cost of buying vs. renting a cloud GPU server. We use ...

Published on February 8, 2019 by Chuan Li

This tutorial is about making a character-based text generator using a simple two-layer LSTM. It will walk you through the data preparation and the network ...

Published on February 6, 2019 by Chuan Li

BERT is Google's pre-training language representations which obtained the state-of-the-art results on a wide range of Natural Language Processing tasks. ...

Published on January 15, 2019 by Chuan Li

Last, tyear, Fast.ai won the first ImageNet training cost challenge as part of the DAWN benchmark. Their customized ResNet50 takes 3.27 hours to reach 93% ...

Published on January 7, 2019 by Chuan Li

DAWNBench recently updated its leaderboard. Among the impressive entries from top-class research institutes and AI Startups, perhaps the biggest leap was ...

Published on January 6, 2019 by Chuan Li

Object Detection using Single Shot MultiBox Detector The problem The task of object detection is to identify "what" objects are inside of an image and "where" ...