-
in yolo3, you use concept from feature pyramid networks, can you explain why 'feature pyramid' likes dssd, retinanet outperform 'feature pyramid' likes ssd for object detection (not segmentation)? tha…
ghost updated
5 years ago
-
Thanks for sharing your TAA-PG project.
running train.py (and test.py) I get this error message which I've not been able to solve:
Traceback (most recent call last):
File "./train.py", line 3…
-
Traceback (most recent call last):
File "train.py", line 156, in
voc07_metric=args.use_voc07_metric)
File "/home/zsl/qjx/mxnet-dssd/train/train_net.py", line 188, in train_net
label_p…
-
-
Hi, Wei.
I have implemented your DSSD on VOC and ILSVRC16.
I implemented PM(Prediction Module) + DM(Deconvolution Module) based on SSD-VGG-512 model and achieve mAP 80.87 on VOC07test (trained …
-
前言：最近在跑这个代码。发现demo部分有一些小的问题，如果直接把程序download下来根本跑不了，花时间排查了一下错误，特地在此列出来，希望作者有时间的时候更正一下。也在此列出来，让大家少采坑。
正文：我觉得问题主要出在作者好像没有用这个demo跑过演示程序，导致这个demo基本上就是照搬ssd的demo结构，参数设置也和ssd的demo设置差不多，这是错误的源泉所在。
但好像还是会有…
-
-
Just to put a context: I was asked to find a paper and reproduce some results from scratch (it weights the 50% of the subject), I've my deadline around the 10 of June of 2022.
---
While rewritin…
-
Warning messages appear when running the case study from the examples.distancesampling.org page and from the multi-strata vignette in the package.
http://examples.distancesampling.org/dssd-multi-st…
-
@liufei2016 @rohrch
unfolding via dssz_util (either gecode or IDD) doesn't work, but gecode/generic (intern) do, and the unfolding result seems to be correct (as far as I can see).
[garden.colp…