Decoupled-Classification-Refinement

Decoupled-Classification-Refinement copied to clipboard

So is the whole DCR setup similar to setting up Faster RCNN + classifier? For DCR v1, is it just letting the classifier post-process the output from the faster RCNN...

ydixon

Thanks for your nice work, however I have some questions: 1)In the DCRV2, paepr writes that "During training, we first sample R boxes from the outputs of the bounding box...

HuangLian126

How can I train my own data? PASCAL VOC2007 format.

3

dby2017

During testing DCR-v1, I have problem in getting the document **'_detections_all.pkl'**. I get it by run `python experiments/faster_rcnn/rcnn_test.py --cfg experiments/faster_rcnn/cfgs/resnet_v1_101_coco_train2017_rcnn_end2end.yaml --thresh 0 --disable-nms` and make some modifications according to my...

wirevoid

Could this code run on the envirornment of CUDA Version 9.0.176?

1

than you in advance

ShihuaiXu

How to combine scores of stage1 and stage2

1

What if their prediction class is different? Like stage1 predict the box as cat, while stage2 predict the box as dog. Thank you

emergencyd

Question about technical details

1

Hi, thanks for sharing your great work. I have a question regarding technical details of your works. 1. In Table.1 in your paper(ECCV2018), you compare 'sampling methods' to choose training...

hdjang

Any suggestion about model ensemble for faster rcnn?

1

I have trained several faster rcnn models with different backbones, then I want to ensemble these models for a better performance, but I am totally confused about how to do...

BasisPoint

Can you give a detailed explaination about DCR-v1 ? Especially the two .py codes in ./dcr_v1/.

15

KimSoybean

How can I add a new batchnorm layer?

4

I want to add extra conv + bn+relu layers after dcr, but I donot konw how to init bn layer both in train and use in test, can you give...

EyreEyre