py-R-FCN

py-R-FCN copied to clipboard

hello， This project implements end to end training with minibatch = 1，it takes up about 4G~5G GPU resources .but my single GPU resources is 24G, and my dataset is about...

ygren

what's the difference between class-aware and agnostic?

6

Hello, I found that the classification is also work for agnostic method, so what's the difference between class-aware and agnostic? Are they produce the same mAP result? Thanks for your...

scut-salmon

bbox_loss is always zero when I train R-FCN with OHEM

1

when i train a R-FCN t with OHEM----rfcn_end2end_ohem.sh, I get loss_bbox = 0 (* 1 = 0 loss) from the very beginning. However, when i train the verision without OHEM,...

starxhong

Can you update pretrained R-FCN model of COCO？

2

Can you update pretrained R-FCN model of COCO？Thanks！

brantbzhang

Segmentation fault in cpu mode.

12

I have successfully train the rfcn model and test in gpu model. But when i run the demo in cpu model the program will core dump with "Segmentation fault". Can...

misery0424

psroi_pooling_layer.cu:108 invalid configuration argument

9

Hi, I met the issue during ResNet-50 training: psroi_pooling_layer.cu:108] Check failed: error == cudaSuccess (9 vs. 0) invalid configuration argument Ubuntu 14.04 + one 1080 GPU card. Any idea on...

harrycrossincode

Hi, current the model is trained with class agnostic box, how to train the model with class aware box?

panovr

Can't parse message of type "caffe.NetParameter"

1

Hi, sorry for the bother, but I have this issue and I really don't know why: ``` [libprotobuf ERROR google/protobuf/message_lite.cc:123] Can't parse message of type "caffe.NetParameter" because it is missing...

lucasjinreal

train error

1

when use ./experiments/scripts/rfcn_end2end_ohem.sh 0 ResNet-50 pascal_voc get the error Traceback (most recent call last): File "./tools/train_net.py", line 104, in imdb, roidb = combined_roidb(args.imdb_name) File "./tools/train_net.py", line 69, in combined_roidb roidbs...

wjwstate

MissLikeWind