Open realwill opened 7 years ago
How did you install mxnet? I installed it according to http://mxnet.io/, but the code didn't work.
@baiyancheng20 yes, I installed the mxnet as http://mxnet.io
I debug the training, and locate the error as https://github.com/dmlc/mxnet/issues/3724
@realwill So did you fix the bug following that?
@Oh233 no.....
@Oh233 the same problem with training fcis
@Oh233 and the same after I use another mxnet: https://github.com/dmlc/mxnet/tree/62ecb60
Hello, I have same error after Epoch[0] Batch [800] (for the second try: Batch [700]):
Error in CustomOp.forward: Traceback (most recent call last): File "/usr/local/lib/python2.7/dist-packages/mxnet-0.9.5-py2.7.egg/mxnet/operator.py", line 758, in forward_entry aux=tensors[4]) File "experiments/rfcn/../../rfcn/operator_py/proposal.py", line 137, in forward keep = nms(det) File "experiments/rfcn/../../rfcn/../lib/nms/nms.py", line 20, in _nms return gpu_nms(dets, thresh, device_id) File "gpu_nms.pyx", line 29, in gpu_nms.gpu_nms (gpu_nms.cpp:1914) IndexError: Out of bounds on buffer access (axis 0)
hi @realwill @baiyancheng20
I have compile the mxnet and copy the folder mxnet/pyhton to external/mxnet,,then run the command python ./rfcn/demo.py ,the error is
File "./rfcn/demo.py", line 28, in
Thank you!
@mursalal,hello, Have you solved the problem?
same problem File "gpu_nms.pyx", line 29, in gpu_nms.gpu_nms IndexError: Out of bounds on buffer access (axis 0)
Does anybody solve this problem?
Thank you for sharing the wonderful work, it is really help. I encounter problems when training. The training suspend in epoch 0 batch 3300 (or others) and gpu-util become 0%, why?