caffe-yolo icon indicating copy to clipboard operation
caffe-yolo copied to clipboard

Published 20 hours ago • verified publisher icon Harick1

train.sh

Open riadhayachi opened this issue 7 years ago • 5 comments

F0520 14:52:10.337806 11844 relu_layer.cu:26] Check failed: error == cudaSuccess (9 vs. 0) invalid configuration argument *** Check failure stack trace: *** @ 0x7ff5c51b65cd google::LogMessage::Fail() @ 0x7ff5c51b8433 google::LogMessage::SendToLog() @ 0x7ff5c51b615b google::LogMessage::Flush() @ 0x7ff5c51b8e1e google::LogMessageFatal::~LogMessageFatal() @ 0x7ff5c59dcdda caffe::ReLULayer<>::Forward_gpu() @ 0x7ff5c585cbe2 caffe::Net<>::ForwardFromTo() @ 0x7ff5c585cd07 caffe::Net<>::Forward() @ 0x7ff5c57e4070 caffe::Solver<>::Step() @ 0x7ff5c57e4b09 caffe::Solver<>::Solve() @ 0x40b408 train() @ 0x4075a8 main @ 0x7ff5c3c6b830 __libc_start_main @ 0x407d19 _start @ (nil) (unknown) Aborted (core dumped) can any one help find out what is the problem

riadhayachi avatar May 18 '17 17:05 riadhayachi

Can you upload your train.sh file to here?

tankienleong avatar May 22 '17 07:05 tankienleong

#!/usr/bin/env sh

CAFFE_HOME=/home/riadh/caffe-yolo

SOLVER=./gnet_solver.prototxt WEIGHTS=/home/riadh/caffe-yolo/models/bvlc_googlenet/bvlc_googlenet.caffemodel

$CAFFE_HOME/build/tools/caffe train
--solver=$SOLVER --weights=$WEIGHTS --gpu=0

riadhayachi avatar May 22 '17 16:05 riadhayachi

I never try fine tuning caffe-yolo from bvlc_googlenet.caffemodel. May be you can try train your caffe-yolo from scratch.

tankienleong avatar May 23 '17 04:05 tankienleong

ok good idea but i think the problem because of the graphique card (cuda success) i have only 2gb gpu on my machine

riadhayachi avatar May 23 '17 09:05 riadhayachi

hello,Could you tell me how to solve this problem?i am faced same problemed with you.

daixia avatar Oct 08 '19 07:10 daixia