94% on CIFAR-10 in 3.29 Seconds on a Single GPU
CIFAR-10 is among the most widely used datasets in machine learning, facilitating thousands of research projects per year. To accelerate research and reduce the cost of experiments, we introduce training methods for CIFAR-10 which reach 94% accuracy in 3.29 seconds, 95% in 10.4 seconds, and 96% in 46.3 seconds, when run on a single NVIDIA A100 GPU. As one factor contributing to these training speeds, we propose a derandomized variant of horizontal flipping augmentation, which we show improves over the standard method in every case where flipping is beneficial over no flipping at all. Our code is released at https://github.com/KellerJordan/cifar10-airbench.
Code (1)
Tasks
GPUSimilar Papers 제목 키워드 기반
PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networks
Deep learning has become a cornerstone of modern machine learning. It relies heavily on vast datasets and significant computational resources for high performance. This data often contains sensitive information, making p…
Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUs
Deep Learning as a Service (DLaaS) stands as a promising solution for cloud-based inference applications. In this setting, the cloud has a pre-learned model whereas the user has samples on which she wants to run the mode…
Privacy PreservingTAPAS: Train-less Accuracy Predictor for Architecture Search
In recent years an increasing number of researchers and practitioners have been suggesting algorithms for large-scale neural network architecture search: genetic algorithms, reinforcement learning, learning curve extrapo…
GPUNeural Architecture SearchReinforcement LearningEfficient Certified Defenses Against Patch Attacks on Image Classifiers
Adversarial patches pose a realistic threat model for physical world attacks on autonomous systems via their perception component. Autonomous systems in safety-critical domains such as automated driving should thus conta…
GPUFTSO: Effective NAS via First Topology Second Operator
Existing one-shot neural architecture search (NAS) methods have to conduct a search over a giant super-net, which leads to the huge computational cost. To reduce such cost, in this paper, we propose a method, called FTSO…
Neural Architecture Search