Comments (11)
@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.
Related Issues (20)
- TypeError: _update_params_on_kvstore() takes exactly 4 arguments (3 given) HOT 1
- there is an error when trained on ResNet-50 model HOT 1
- Index out of bounds error in line 143 of proposal_annotator.py HOT 1
- Some problems encountered when using deconvolution
- mxnet.base.MXNetError: [15:20:32] src/engine/threaded_engine.cc:320: Check failed: device_count_ > 0 (-1 vs. 0) GPU usage requires at least 1 GPU HOT 1
- The result finetune with cityscapes is very poor
- Network structure
- When I train my own coco-like datasets,I successfully train and test the model,but the result of all AP is 0. HOT 5
- If my data is small,such as 6000 images,is it difficult to train the model? HOT 3
- my own data set ,test map is 0
- 有哪位遇到过训练成功,测试map=0的情况吗 HOT 3
- mxnet.base.MXNetError: [16:31:18] src/operator/nn/./cudnn/cudnn_convolution-inl.h:449: Check failed: e == CUDNN_STATUS_SUCCESS (3 vs. 0) cuDNN: CUDNN_STATUS_BAD_PARAM HOT 1
- pip install -r requirements.txt HOT 3
- unable to install ./init.sh error HOT 4
- Problems when launching demo.py
- Is it possible to run FCIS on AMD?
- Trouble building on Windows 10 (TypeError: expected str, bytes or os.PathLike object, not NoneType) HOT 2
- In-depth guide to getting FCIS working on Windows 10 HOT 3
- [HELP] problem with cpu_nms HOT 1
- Result file for COCO test-dev instance segmentation
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fcis.