Shypd.aiThe largest open index of AI toolsGradient-Centralization is an open-source optimization technique for deep neural networks that centralizes gradient vectors to have zero mean. It speeds up training and improves generalization performance.
Trending
About
Gradient Centralization (GC) is an open-source optimization technique designed to enhance the training and generalization performance of Deep Neural Networks (DNNs). It works by centralizing gradient vectors to have zero mean, a simple yet effective modification that can be easily integrated into existing gradient-based DNN optimizers. GC can accelerate the training process and improve the final generalization performance across various applications, including general image classification, fine-grained image classification, object detection and segmentation, and Person ReID. The technique is implemented in optimizers like SGD_GC, Adam_GC, and Adagrad_GCC, with options for applying GC to both convolutional and fully connected layers, or only convolutional layers for adaptive learning rate methods. It is available as a PyTorch implementation and has also been adapted for TensorFlow and Ranger optimizer.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending
