it occurs when train fpn
I trian own data when I use voc data format. I use config which is resnet_v1_101_coco_trainval_fpn_dcn_end2end_ohem.yaml
Log:
append flipped images to roidb
filtered 0 roidb entries: 33134 -> 33134
infer_shape error. Arguments:
data: (1, 3, 400, 500)
Traceback (most recent call last):
File "experiments/fpn/fpn_end2end_train_test.py", line 20, in
Stack trace returned 10 entries: [bt] (0) /vol/home/alex/mxnet_alex/local/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x306d1a) [0x7fc4e5933d1a] [bt] (1) /vol/home/alex/mxnet_alex/local/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x307341) [0x7fc4e5934341] [bt] (2) /vol/home/alex/mxnet_alex/local/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x4d4f65) [0x7fc4e5b01f65] [bt] (3) /vol/home/alex/mxnet_alex/local/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x14896e6) [0x7fc4e6ab66e6] [bt] (4) /vol/home/alex/mxnet_alex/local/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x24c574a) [0x7fc4e7af274a] [bt] (5) /vol/home/alex/mxnet_alex/local/lib/python2.7/site-packages/mxnet/libmxnet.so(+0x24c8084) [0x7fc4e7af5084] [bt] (6) /vol/home/alex/mxnet_alex/local/lib/python2.7/site-packages/mxnet/libmxnet.so(MXSymbolInferShape+0x15aa) [0x7fc4e7a6edba] [bt] (7) /usr/lib/x86_64-linux-gnu/libffi.so.6(ffi_call_unix64+0x4c) [0x7fc53136ae40] [bt] (8) /usr/lib/x86_64-linux-gnu/libffi.so.6(ffi_call+0x2eb) [0x7fc53136a8ab] [bt] (9) /vol/home/alex/mxnet_alex/lib/python2.7/lib-dynload/_ctypes.x86_64-linux-gnu.so(_ctypes_callproc+0x48f) [0x7fc53157a3df]
Hi,have you solved this problem ?
For Windows users, run cmd .\init.bat. For Linux user, run sh ./init.sh. The scripts will build cython module automatically and create some folders.Are you sure you read the installation instructions carefully?
Hi @liveway6 , @chanyixialex @weiiLu did you solve this issue?