Did you run make in the lib directory?

Oh, I'm sorry.
I haven't run "make" yet.

I really enjoy using your 'fast-rcnn'.
My ultimate goal is to run 'fast-rcnn' or 'faster-rcnn' with pretrained ImageNet model.
So, perheps I may ask some questions again.
Thank you.

Hi,
when I run faster-rcnn demo.py, I got this error.
r\tools..\lib\fast_rcnn\nms_wrapper.py", line 9, in
from nms.gpu_nms import gpu_nms
ImportError: No module named gpu_nms

I already run python setup.py file (Lib folder)

without using Make file is there any problem with that??

Thank you

I'm also facing the same issue even though I have done make already. Please help

I faced the same problem too ?anyone solved it ?

Traceback (most recent call last):
File "test_net.py", line 13, in
from fast_rcnn.test import test_net
File "/home/joyian/py-faster-rcnn/tools/../lib/fast_rcnn/test.py", line 17, in
from fast_rcnn.nms_wrapper import nms
File "/home/joyian/py-faster-rcnn/tools/../lib/fast_rcnn/nms_wrapper.py", line 9, in
from nms.gpu_nms import gpu_nms
ImportError: No module named gpu_nms

I was facing the same error while trying to use RCNN in CPU-only mode.

I fixed it by going to /FRCNN/py-faster-rcnn/lib/fast_rcnn/nms_wrapper.py and changing the code as follows:

from fast_rcnn.config import cfg
#from nms.gpu_nms import gpu_nms
from nms.cpu_nms import cpu_nms

def nms(dets, thresh, force_cpu=False):
    """Dispatch to either CPU or GPU NMS implementations."""

    if dets.shape[0] == 0:
        return []
    #if cfg.USE_GPU_NMS and not force_cpu:
    #    return gpu_nms(dets, thresh, device_id=cfg.GPU_ID)
    else:
        return cpu_nms(dets, thresh)

Commented out GPU-specific lines.

This holds also for py-R-FCN if run in CPU mode.

So GPU mode is still not solved? I want to run on GPU, but can't go over the "ImportError: No module named nms.gpu_nms " I have run make all over, and i think my caffe has all the paths set right (python and all) because it builds right. :(

same here for gpu. Is there any solution?

how can detect multiple object on same image using demo.py ????????????

The issue most likely is that the setup.py file did not locate your cuda directory, so make sure that CUDAHOME env variable is pointing to the right directory, and make again.

I face the error " image not found",anyone knows how to solve it. thanks!
the detail error as follows:
zhongzunfadeMacBook-Air:tools zhongzunfa$ python demo.py
Traceback (most recent call last):
File "demo.py", line 17, in
from fast_rcnn.test import im_detect
File "/Users/zhongzunfa/fjl/py-faster-rcnn/tools/../lib/fast_rcnn/test.py", line 16, in
import caffe
File "/Users/zhongzunfa/fjl/py-faster-rcnn/tools/../caffe-fast-rcnn/python/caffe/init.py", line 1, in
from .pycaffe import Net, SGDSolver, NesterovSolver, AdaGradSolver, RMSPropSolver, AdaDeltaSolver, AdamSolver
File "/Users/zhongzunfa/fjl/py-faster-rcnn/tools/../caffe-fast-rcnn/python/caffe/pycaffe.py", line 13, in
from ._caffe import Net, SGDSolver, NesterovSolver, AdaGradSolver,
ImportError: dlopen(/Users/zhongzunfa/fjl/py-faster-rcnn/tools/../caffe-fast-rcnn/python/caffe/_caffe.so, 2): Library not loaded: libcaffe.so.1.0.0-rc3
Referenced from: /Users/zhongzunfa/fjl/py-faster-rcnn/caffe-fast-rcnn/python/caffe/_caffe.so
Reason: image not found

@deshanadesai : or a cleaner solution when the folloxing problem occurs: 'ImportError: No module named gpu_nms'

from fast_rcnn.config import cfg
if cfg.USE_GPU_NMS:
        from nms.gpu_nms import gpu_nms
from nms.cpu_nms import cpu_nms

Anyone solved the problem yet?

try this
import pyximport
pyximport.install()

@msha096
I tried your method, but there was a mistake.
"CompileError: command 'gcc' failed with exit status 1\n"

@msha096 cuda:8.0,gcc:4.9.3,I succeeded in another way.

@msha096 cuda:8.0,gcc:4.9.3,I succeeded in another way.

How do you deal with it? I also face the problem!

@Chida15 You can switch to the Lib file, make

hello all
thanks for the great efforts

i am beginner in this field and i want to run the code

when i ran it i got this error

ModuleNotFoundError Traceback (most recent call last)
in
1 import _init_paths
2 import tensorflow as tf
----> 3 from fast_rcnn.config import cfg
4 from fast_rcnn.test import im_detect
5 from fast_rcnn.nms_wrapper import nms

ModuleNotFoundError: No module named 'fast_rcnn'

what should i do to fix it,
and where i can get the right steps?

Same Problem with
ModuleNotFoundError: No module named 'nms.cpu_nms'

Any one who have solved this problem yet?

I am also facing same issue :
(tf_gpu) C:\Projects\new_caffe_fasterRCNN\py-faster-rcnn>python tools\demo.py
Traceback (most recent call last):
File "tools\demo.py", line 18, in
from fast_rcnn.test import im_detect
File "C:\Projects\new_caffe_fasterRCNN\py-faster-rcnn\tools..\lib\fast_rcnn\test.py", line 17, in
from fast_rcnn.nms_wrapper import nms
File "C:\Projects\new_caffe_fasterRCNN\py-faster-rcnn\tools..\lib\fast_rcnn\nms_wrapper.py", line 10, in
from nms.cpu_nms import cpu_nms
ImportError: DLL load failed: The specified module could not be found.

please use python 3.7.5, 3.7.4 python gpu_nms run failed.

I'm having the same problem :D

File "/root/plasticbag-faster-rcnn/tools/../lib/model/nms_wrapper.py", line 12, in <module>
from nms.gpu_nms import gpu_nms
ImportError: No module named gpu_nms

This is what my nms folder looks like:

ls lib/nms
__init__.py  __init__.pyc  cpu_nms.c  cpu_nms.cpython-35m-x86_64-linux-gnu.so  cpu_nms.pyx  gpu_nms.cpp  gpu_nms.cpython-35m-x86_64-linux-gnu.so  gpu_nms.hpp  gpu_nms.pyx  nms_kernel.cu  py_cpu_nms.py