FasterR-CNN,R-FCN,SSD,FPN,RetinaNet,YOLOv3速度和准确性比较
很难在不同的目标检测器之间进行公平的比较。对于哪个模型是最好的?这个问题是没有直接的答案。对于现实生活中的应用,我们选择平衡准确性和速度。除了检测器类型外,我们还需要了解影响性能的其他选择:
Feature extractors (VGG16, ResNet, Inception, MobileNet).
Output strides for the extractor.
Input image resolutions.
Matching strategy and IoU threshold (how predictions are excluded in calculating loss).
Non-max suppression IoU threshold.
Hard example mining ratio (positive v.s. negative anchor ratio).
The number of proposals or predictions.
Boundary box encoding.
Data augmentation.
Training dataset.
Use of multi-scale images in training or testing (with cropping).
Which feature map layer(s) for object detection.
Localization loss function.
Deep learning software platform used.
Training configurations including batch size, input image resize, learning rate, and learning rate decay.
最糟糕的是,技术发展如此之快,以至于任何比较都很快变得过时。在这里,我们总结了各个论文的结果,因此您可以完整分析和对比它们。然后,我们根据Google Research中总结得出一篇综述。通过在一种情况下提出多种观点,我们希望我们可以更好地了解性能指标。
详细内容参考此链接:http://47.115.23.213/?p=107