Transferred from: http://lanbing510.info/2017/08/28/YOLO-SSD.html
Prior to the emergence of deep learning, the traditional target detection method is probably divided into regional selection (sliding window), feature extraction (SIFT, hog, etc.), classifier (SVM, adaboost, etc.) three parts, the main problems have two aspects: on the one hand, sliding window selection strategy is not targeted, time complexity, window redundancy On the other hand, the characteristics of manual design are poor. S
In a variety of test mix scenarios, the combination of 10 (combination 10:SSD * 2, RAID 0, Xfs,wb,nobarrier,noop) has the highest overall performance, so it is the benchmark, and the comparison of other schemes, the following table is the comparison of the combinations and combinations 10:650) this.width=650; "Src=" http://dp.imysql.com:8080/files/upload_yejr_imysql/SAS_VS_SSD_MySQL_OLTP%E5%AF%B9%E6% Af%94%e6%b5%8b%e8%af%95%e8%a1%a8-20120907.png "styl
does not mean that the hard disk can not be used, but performance will be reduced, there is noise, such as driving a car, the mechanical structure will appear aging, so need maintenance, but mechanical hard disk use for 5-10 years completely no problem, or even more.
Solid-state hard disk life standard is generally written or written capacity, the calculation of capacity units are not intuitive, including 4 K, 8K of random write capacity, usually in TB, PB units to calculate, the general profe
SSD predictive bbox is essentially the same as RPN, except that it predicts on multiple layers to better detect objects on multiple scales. predicting bbox on multiple layers
The original SSD300 is predicted on the following layer:
Conv4 ==> x conv7 ==> x conv8 ==>
5 x
5
conv9 ==> 3 3
CONV11 ==> 1 x 1
The number that follows is the size of the feature map for this layer output.SSD512:
Conv4 ==> x conv7 ==> x conv8
The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion;
products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the
content of the page makes you feel confusing, please write us an email, we will handle the problem
within 5 days after receiving your email.
If you find any instances of plagiarism from the community, please send an email to:
info-contact@alibabacloud.com
and provide relevant evidence. A staff member will contact you within 5 working days.