System and method for training image classification model and method for classifying images

Abstract

The present application discloses a computer-implemented method for training an image classification model, a system for training the image classification model, and a computer-implemented method for classifying images. In one or more embodiments, a compact deep learning model comprises fewer layers, which require fewer floating-point operations (FLOPs). Presented herein are also embodiments of a new learning rate function, which can adaptively change the learning rate between two linear functions. In one or more embodiments, combinations of half-precision floating point format training together with larger batch size in the training process may also be employed to aid the training process.

Description

technical field [0001] The present disclosure generally relates to systems and methods for computer learning that can provide improved computer performance, features, and use. More specifically, the present disclosure relates to systems and methods for improved deep learning models and improved training of deep learning networks. Background technique [0002] Deep learning (DL) has been widely used in many different fields such as computer vision, natural language processing, medical image processing, etc. Gradually, deep learning has become the basis of the recent artificial intelligence / machine learning (AI / ML) revolution, which has impacted numerous industries and spawned many more. In most cases, the training process for DL ​​tasks is very long, even on modern advanced graphics processing unit (GPU) machines such as the one made by Nvidia in Sunnyvale, CA. The same is true on the V100 Tensor Core, or Tensor Processing Unit (TPU) made by Google in Mountain View, Califo...

AI Technical Summary

Problems solved by technology

Due to their complexity, developing TTS systems can be very labor intensive and difficult

Images