search

rbgirshick / py-faster-rcnn

Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
Other
8.13k stars 4.11k forks source link

TypeError: 'numpy.float64' object cannot be interpreted as an index #625

Open nanzhixiong opened 7 years ago

nanzhixiong commented 7 years ago

I am training voc 2007 and already finished stage 1, I have zf_rpn_stage1_iter_80000.caffemodel and zf_rpn_stage1_iter_80000_proposals.pkl in my output/faster_rcnn_alt_opt/train/ folder. But then I encountered this error:

File "/home/Documents/py-faster-rcnn/tools/../lib/roi_data_layer/minibatch.py", line 100, in _sample_rois fg_inds, size=fg_rois_per_this_image, replace=False) File "mtrand.pyx", line 1070, in mtrand.RandomState.choice (numpy/random/mtrand/mtrand.c:8044)

I find that the error " TypeError: 'numpy.float64' object cannot be interpreted as an index " can be solved by "sudo pip install -U numpy==1.11.0". However, then another error appears as "ImportError: numpy.core.multiarray failed to import", to sovle this, "pip install -U numpy" works.

then I train the model one more time, and again I find the error of "TypeError: 'numpy.float64' object cannot be interpreted as an index"

mattdingmeng commented 7 years ago

I have the same problem.

zhenni commented 7 years ago

It seems that you use float object as the index, which may sometimes cause errors. Try to use pdb.set_trace() to stop and check where you use float objects as index and convert the float index to int.

wangtaofree commented 7 years ago

@nanzhixiong This problem have solved in this issue:"https://github.com/rbgirshick/py-faster-rcnn/issues/481", it's really works, you can refer to the PentaHiggs's answer.

ujsyehao commented 6 years ago

you can delete the problem, it has been solved https://github.com/rbgirshick/py-faster-rcnn/issues/481