endernewton / tf-faster-rcnn

Tensorflow Faster RCNN for Object Detection
https://arxiv.org/pdf/1702.02138.pdf
MIT License
3.65k stars 1.57k forks source link

segmentation fault and time: command not found #363

Closed jessiezi closed 6 years ago

jessiezi commented 6 years ago

first of all .thanks for your code. I change the -arch=sm_35 since my GPU is k40. but when i run the CUDA_VISIBLE_DEVICES=${GPU_ID} ./tools/demo.py it will throw that: $ GPU_ID=0 $ CUDA_VISIBLE_DEVICES=${GPU_ID} ./tools/demo.py /home/yulong/sw/Python-3.6.5/lib/python3.6/site-packages/h5py/init.py:36: FutureWarning: Conversion of the second argument of issubdtype from float to np.floating is deprecated. In future, it will be treated as np.float64 == np.dtype(float).type. from ._conv import register_converters as _register_converters Loaded network output/res101/voc_2007_trainval+voc_2012_trainval/default/res101_faster_rcnn_iter_110000.ckpt


Demo for data/demo/000456.jpg
Detection took 2.196s for 300 object proposals
Segmentation fault

when I run the command ./experiments/scripts/test_faster_rcnn.sh $GPU_ID pascal_voc_0712
the error occured like this:
$ GPU_ID=0
$ ./experiments/scripts/test_faster_rcnn.sh $GPU_ID pascal_voc_0712 res101
+ set -e
+ export PYTHONUNBUFFERED=True
+ PYTHONUNBUFFERED=True
+ GPU_ID=0
+ DATASET=pascal_voc_0712
+ NET=res101
+ array=($@)
+ len=3
+ EXTRA_ARGS=
+ EXTRA_ARGS_SLUG=
+ case ${DATASET} in
+ TRAIN_IMDB=voc_2007_trainval+voc_2012_trainval
+ TEST_IMDB=voc_2007_test
+ ITERS=110000
+ ANCHORS='[8,16,32]'
+ RATIOS='[0.5,1,2]'
++ date +%Y-%m-%d_%H-%M-%S
+ LOG=experiments/logs/test_res101_voc_2007_trainval+voc_2012_trainval_.txt.2018-07-07_11-48-31
+ exec
++ tee -a experiments/logs/test_res101_voc_2007_trainval+voc_2012_trainval_.txt.2018-07-07_11-48-31
+ echo Logging output to experiments/logs/test_res101_voc_2007_trainval+voc_2012_trainval_.txt.2018-07-07_11-48-31
Logging output to experiments/logs/test_res101_voc_2007_trainval+voc_2012_trainval_.txt.2018-07-07_11-48-31
+ set +x
+ [[ ! -z '' ]]
+ CUDA_VISIBLE_DEVICES=0
+ time python ./tools/test_net.py --imdb voc_2007_test --model output/res101/voc_2007_trainval+voc_2012_trainval/default/res101_faster_rcnn_iter_110000.ckpt --cfg experiments/cfgs/res101.yml --net res101 --set ANCHOR_SCALES '[8,16,32]' ANCHOR_RATIOS '[0.5,1,2]'
./experiments/scripts/test_faster_rcnn.sh: line 67: time: command not found

please help me
randomtutu commented 6 years ago

do u solve this problem?

i get the same error when i run this code

regards your reply

thx

ZhuoyaYang commented 6 years ago

do u solve this problem?

ZhuoyaYang commented 6 years ago

https://github.com/endernewton/tf-faster-rcnn/issues/89 remove "time"