yousongzhu / couplenet Goto Github PK

The paper says the global FCN collects the surrounding information by concating the original and 2 times lager proposals together then feding into the later roi-wise subnet. But I dont find that in your code..How you guys do that?

I'd like to train CoupleNet on a custom dataset. Could you tell me how to go about it?

hi @tshizys,

why do you try to add 1x1 conv to norm them before sum them together?

Did you use the context prior to the global branch when you get 33.1 mAP result on coco dataset without multi-scale training

I'm training CoupleNet on a custom dataset. I have a few questions and I'd greatly appreciate it if you could respond to my queries. First off, How do I run train.py?

How does concat context information and another feature in goal FCN?
Is it the 0 connection of the concat layer or the 1 connection?

I have no way to download it from baidu pan (do not have a baidu account and it is hard to even register one). Is there any other way I can download the file (dropbox, onedrive?)
Thx

@tshizys HI

In Table4，for Global FCN, it can be regarded as a Faster R-CNN.
But the depth of roI-wise subnetwork is only two, why did it work out so well( 78.5 )?? In our common sense, roi-wise subnetwork should be very deep to be correct.

Hi,
I follow the procedure to prepare and I can train py-rfcn. But when I train couple net it occured

F0504 10:19:44.208268 4032 net.cpp:777] Check failed: target_blobs.size() == source_layer.blobs_size() (1 vs. 2) Incompatible number of blobs for layer conv1
*** Check failure stack trace: ***
./experiments/scripts/couplenet_end2end_ohem.sh: line 58: 4032 Aborted (core dumped) ./tools/train_net.py --gpu ${GPU_ID} --solver models/${PT_DIR}/${NET}/couplenet_end2end/solver_ohem.prototxt --weights data/imagenet_models/${NET}-model.caffemodel --imdb ${TRAIN_IMDB} --iters ${ITERS} --cfg experiments/cfgs/couplenet_end2end_ohem.yml ${EXTRA_ARGS}

what's wrong ?