What should I do if I just want to test the result of using my image set about fcis HOT 11 CLOSED

@lc8631058 Maybe you can refer to the demo code.

from fcis.

@liyi14 Hi, I try to run demo.py, but comes an error like this:

<ipython-input-6-ba520ac12655> in <module>()
     15 import cv2
     16 from config.config import config, update_config
---> 17 from utils.image import resize, transform
     18 import numpy as np
     19 # get config

/home/carnd/Semantic_segmentation/FCIS/fcis/../lib/utils/image.py in <module>()
      4 import random
      5 from PIL import Image
----> 6 from bbox.bbox_transform import clip_boxes
      7 
      8 

/home/carnd/Semantic_segmentation/FCIS/fcis/../lib/bbox/bbox_transform.py in <module>()
      8 
      9 import numpy as np
---> 10 from bbox import bbox_overlaps_cython
     11 
     12 

ImportError: cannot import name 'bbox_overlaps_cython'

And I back to bbox folder to see if there is a file named bbox_overlaps_cython, I've found there is no such file, and I do try sh ./init.sh several times and it shows:

skipping 'bbox.c' Cython extension (up-to-date)
running build_ext
running build_ext
skipping 'cpu_nms.c' Cython extension (up-to-date)
skipping 'gpu_nms.cpp' Cython extension (up-to-date)
running build_ext
skipping 'gpu_mv.cpp' Cython extension (up-to-date)

so where can I go to find the 'bbox_overlaps_cython' file? have you ever encountered a case like this?

from fcis.

for the error above, just amend from bbox import bbox_overlaps_cython to from bbox.bbox import bbox_overlaps_cython, and then it works until a new error:

    main()
  File "demo.py", line 43, in main
    sym = sym_instance.get_symbol(config, is_train=False)
  File "/home/carnd/Semantic_segmentation/FCIS/fcis/symbols/resnet_v1_101_fcis.py", line 799, in get_symbol
    psroipool_cls_seg = mx.contrib.sym.PSROIPooling(name='psroipool_cls_seg', data=fcis_cls_seg, rois=rois,
AttributeError: module 'mxnet.contrib.symbol' has no attribute 'PSROIPooling'

which hasn't been solved until now

from fcis.

I've done this manually: cp /fcis/operator_cxx/* to $(YOUR_MXNET_FOLDER)/src/operator/contrib, I'm not sure how to recompile mxnet, what I did was run make clean under python3.5/site-packages/mxnet and run this again: make -j $(nproc) USE_OPENCV=1 USE_BLAS=openblas USE_CUDA=1 USE_CUDA_PATH=/usr/local/cuda USE_CUDNN=1, but still doesn't work.

from fcis.

Did you copy the python operators
cp -n ${FCIS}/fcis/operator_py/* ${MXNET}/python/mxnet/contrib/fcis_ops
and build the python bindings after running make the second time
sh ./install/python.sh

from fcis.

@shortcipher3 No, I didn't do that, I don't even know that I should do that, I just copy the files in operator_cxx to $(YOUR_MXNET_FOLDER)/src/operator/contrib, let me try, thanks!

from fcis.

@shortcipher3 I didn't find fcis_ops folder under ${MXNET}/python/mxnet/contrib,

what I've found was like this: @ip-172-31-25-67:~/anaconda3/lib/python3.5/site-packages/mxnet/python/mxnet/contrib$ ls

autograd.py __init__.py ndarray.py symbol.py tensorboard.py

from fcis.

@shortcipher3 problem above has been solved, new error:
src/operator/convolution.cu:87: This convolution is not supported by cudnn, MXNET convolution is applied.

from fcis.

now I run demo.py correctly in Jupyter notebook, but the show_masks function just output the original demo images without any changes, I wonder why?

from fcis.

just found the answer in #21

from fcis.

Hi, I have similar issue! How did you solve it?

from fcis.