训练的时候出现问题

[Xassassinator]

Solving... /home/xbb/Documents/FPN/tools/../lib/rpn/proposal_target_layer.py:241: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future bbox_targets[ind, start:end] = bbox_target_data[ind, 1:] /home/xbb/Documents/FPN/tools/../lib/rpn/proposal_target_layer.py:242: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future bbox_inside_weights[ind, start:end] = cfg.TRAIN.BBOX_INSIDE_WEIGHTS F0415 15:33:55.383641 1399 math_functions.cu:375] Check failed: status == CURAND_STATUS_SUCCESS (201 vs. 0) CURAND_STATUS_LAUNCH_FAILURE *** Check failure stack trace: *** ./experiments/scripts/FP_Net_end2end.sh: line 57: 1399 Aborted (core dumped) ./tools/train_net.py --gpu ${GPU_ID} --solver models/${PT_DIR}/${NET}/FP_Net_end2end/solver.prototxt --weights data/pretrained_model/ResNet50.v2.caffemodel --imdb ${TRAIN_IMDB} --iters ${ITERS} --cfg experiments/cfgs/FP_Net_end2end.yml ${EXTRA_ARGS}

This problem has troubled me for a long time ,I think it is the pretrain model problem ?,not sure, and your resnet model address has expired , can you help me to slove this problem ,thanks ! @unsky

[unsky]

https://github.com/BVLC/caffe/issues/4324

[Xassassinator]

@unsky thank you for your help, I have solved this problem by replace makefile.config in caffe

[yin19961202]

@Xassassinator how do you solve the problem?I met the same problem, can you help me ? Thank you very much!