简体   繁体   English

不使用预训练的模型和权重的最佳对象定位策略。

[英]Best strategy for Object localisation without using pretrained model and weights.?

我想从头开始训练模型,而无需使用任何预先训练的模型和权重以及20k图像数据集和4个对象坐标。您能建议我解决此问题的最佳方法吗?

Why won't you try any of the existing architectures - YOLO, SSD, Faster-RCNN to name a few (or their next-gens) and see what is the performance? 您为什么不尝试任何现有架构-YOLO,SSD,Faster-RCNN等(或它们的下一代),看看它们的性能如何?
Of course, if you know in advance the properties of the objects in your data set this can be useful - eg for smaller objects, Faster-RCNN would probably yield better performance that SSD and YOLO. 当然,如果您事先知道数据集中对象的属性,这将很有用-例如,对于较小的对象,Faster-RCNN可能会产生比SSD和YOLO更好的性能。
Each one of them has available open source implementations in all leading DNN frameworks. 他们每个人在所有领先的DNN框架中都有可用的开源实现。

声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.

相关问题 Mask RCNN 的权重初始化,不使用来自 Imagenet / COCO 的预训练权重 - Weight Initialization for Mask RCNN without using pretrained weights from Imagenet / COCO 如何使用 model 的预训练权重在下一次迭代中初始化权重? - How to use pretrained weights of a model for initializing the weights in next iteration? 如何使用 keras 保存最佳权重和最佳模型 - how to save best weights and best model using keras 迁移学习后如何查看预训练模型的权重? - How to view weights of a pretrained model after transfer learning? Caffe:使用相同的预训练权重初始化两个频道的连体网络,但在训练期间没有共享权重 - Caffe: Initializing two channels of siamese networks with the same pretrained weights , but without sharing weights during training 在Keras中保存最佳权重和模型 - Saving the best weights and model in Keras 使用来自 Keras 应用程序的模型,无需预训练权重 - Use models from Keras Applications without pretrained weights caffe中预训练imagenet模型的对象类别 - Object categories of pretrained imagenet model in caffe 预训练的 model 或从头开始训练以进行 object 检测? - Pretrained model or training from scratch for object detection? 更改预训练模型的默认权重 - Change default weights on pretrained models
 
粤ICP备18138465号  © 2020-2024 STACKOOM.COM