Deep learning models for computer vision in remote sensing such as Convolutional Neural Network (CNN) has benefitted acceleration from the usage of multiple CPUs and GPUs. There are several ways to make the training s...
详细信息
ISBN:
(纸本)9781510666184;9781510666191
Deep learning models for computer vision in remote sensing such as Convolutional Neural Network (CNN) has benefitted acceleration from the usage of multiple CPUs and GPUs. There are several ways to make the training stage more effective in terms of utilizing multiple cores at the same time by processing different image mini-batches with a duplicated model called Distributed Data Parallelization (DDP) and computing the parameters in a lower precision floating-point number called Automatic Mixed Precision (AMP). We would like to investigate the impact of DDP and AMP training modes on the overall utilization and memory consumption of CPU and GPU, as well as the accuracy of a CNN model. The study is performed on the EuroSAT dataset, a Sentinel-2-based benchmark satellite image dataset for image classification of land covers. We compare training using 1 CPU, using DDP, and using both DDP and AMP over 100 epochs using ResNet-18 architecture. The hardware that we used are Intel Xeon Silver 4116 CPU with 24 cores and an NvIDIA v100 GPU. We find that although parallelization of CPUs or DDP takes less time to train on the images, it can take 50 MB more memory than using only a single CPU. The combination of DDP and AMP can release memory up to 160 MB and reduce computation time by 20 seconds. The test accuracy is slightly higher for both DDP and DDP-AMP at 90.61% and 90.77% respectively than without DDP and AMP at 89.84%. Hence, training using Distributed Data Parallelization (DDP) and Automatic Mixed Precision (AMP) has more benefits in terms of lower GPU memory consumption, faster training execution time, faster convergence towards solutions, and finally, higher accuracy.
The agricultural landscape is evolving, demanding innovative solutions to enhance productivity while ensuring the welfare of livestock. Farmguard introduces an advanced Automated Animal Detection and Monitoring System...
详细信息
Automatic restoration of damaged or missing pixels is a key problem in image reconstruction for various applications such as retouching, image restoration, image coding, and computer vision. This paper presents a nove...
详细信息
Stereo vision systems are used in various applications, such as industrial automation. This study used a fuzzy logic-based design to control the vergence of the binocular stereo-vision system in order to mimic the eye...
详细信息
In India, where 70% of the population is involved in agriculture, accurate recognition of botanical disorders is crucial to minimize crop losses. Manual monitoring of these diseases requires significant labor, experti...
详细信息
The automation scenario in the current industrial as well as domestic applications has seen an exponential growth over the decade. Robot plays an important role in industrial automation but in some cases, it needs som...
详细信息
Despite its popularity as a one-shot Neural Architecture Search (NAS) approach, the applicability of differentiable architecture search (DARTS) on complex vision tasks is still limited by the high computation and memo...
详细信息
Despite its popularity as a one-shot Neural Architecture Search (NAS) approach, the applicability of differentiable architecture search (DARTS) on complex vision tasks is still limited by the high computation and memory costs incurred by the over-parameterized supernet. We propose a new architecture search method called EasyNAS, whose memory and computational efficiency is achieved via our devised operator merging technique which shares and merges the weights of candidate convolution operations into a single convolution, and a dynamic channel refinement strategy. We also introduce a configurable search space-to-supernet conversion tool, leveraging the concept of atomic search components, to enable its application from classification to more complex vision tasks: detection and semantic segmentation. In classification, EasyNAS achieves state-of-the-art performance on the NAS-Bench-201 benchmark, attaining an impressive 76.2% accuracy on imageNet. For detection, it achieves a mean average precision (mAP) of 40.1 with 120 frames per second (FPS) on MS-COCO test-dev. Additionally, we transfer the discovered architecture to the rotation detection task, where EasyNAS achieves a remarkable 77.05 mAP$_{50}$50 on the DOTA-v1.0 test set, using only 21.1 M parameters. In semantic segmentation, it achieves a competitive mean intersection over union (mIoU) of 72.6% at 173 FPS on Cityscape, after searching for only 0.7 GPU-day.
The article describes the results of assessing the possibility of using machine learning models as part of robotic complexes for navigational transcranial stimulation (nTMS). It is assumed that they will be used to ma...
详细信息
The electrocardiogram signal of the heart is used to monitor the health status and function of the human heart and to a doctor in diagnosing the type of disease. For this purpose, first, the scalogram of the different...
详细信息
The papers in this special section focus on deep learning for high-dimensional sensing. People live in a high-dimensional world and sensing is the first step to perceive and understand the environment for both human b...
详细信息
The papers in this special section focus on deep learning for high-dimensional sensing. People live in a high-dimensional world and sensing is the first step to perceive and understand the environment for both human beings and machines. Therefore, high-dimensional sensing (HDS) plays a pivotal role in many fields such as robotics, signal processing, computer vision and surveillance. The recent explosive growth of artificial intelligence has provided new opportunities and tools for HDS, especially for machinevision. In many emerging real applications such as advanced driver assistance systems/autonomous driving systems, large-scale, high-dimensional and diverse types of data need to be captured and processed with high accuracy and in a real-time manner. Bearing this in mind, now is the time to develop new sensing and processing techniques with high performance to capture high-dimensional data by leveraging recent advances in deep learning (DL).
暂无评论