AlexanderSvan
commented
4 years ago I seem to have the same problem and have been unable to figure out a fix. If you find a solution id be happy to hear!
Open abubakar2141731 opened 4 years ago
AlexanderSvan
commented
4 years ago I seem to have the same problem and have been unable to figure out a fix. If you find a solution id be happy to hear!
abubakar2141731
commented
4 years ago Hi, Yes, please install this pytorch version, source activate solo &&conda install pytorch==1.4.0 torchvision==0.5.0 cudatoolkit=10.1 -c pytorch solo\s setup does not get installed if you have pytorch version greater than 1.4, make sure you the cuda version matches your cuda version at /usr/local/cuda and rest it all works , let me know if you find any other problem
On Thu, Sep 10, 2020 at 7:36 PM AlexanderSvan notifications@github.com wrote:
I seem to have the same problem and have been unable to figure out a fix. If you find a solution id be happy to hear!
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-690526458, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOB73BHZ4QJ2D6MCRR3SFECCNANCNFSM4RDQJJOQ .
AlexanderSvan
commented
4 years ago I just tried it, but i didnt get it to work. I got the error: """ [1/2] /usr/bin/nvcc -DWITH_CUDA -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/TH -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/THC -I/media/data/SOLO/env/include -I/opt/anaconda/envs/solo/include/python3.7m -c -c /media/data/SOLO/mmdet/ops/nms/src/nms_kernel.cu -o /media/data/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_kernel.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14 FAILED: /media/data/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_kernel.o /usr/bin/nvcc -DWITH_CUDA -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/TH -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/THC -I/media/data/SOLO/env/include -I/opt/anaconda/envs/solo/include/python3.7m -c -c /media/data/SOLO/mmdet/ops/nms/src/nms_kernel.cu -o /media/data/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_kernel.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14 nvcc fatal : Unsupported gpu architecture 'compute_75' """
abubakar2141731
commented
4 years ago i didn't encounter this error, so i don't know the exact solution, but make sure what version of cuda has under usr/local/cuda and install the cuda runtime version similar to it, i trained it on google collab which has cuda 10.1 under usr/local/cuda
On Thu, Sep 10, 2020 at 8:52 PM AlexanderSvan notifications@github.com wrote:
I just tried it, but i didnt get it to work. I got the error: """ [1/2] /usr/bin/nvcc -DWITH_CUDA -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/TH -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/THC -I/media/data/SOLO/env/include -I/opt/anaconda/envs/solo/include/python3.7m -c -c /media/data/SOLO/mmdet/ops/nms/src/nms_kernel.cu -o /media/data/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_kernel.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14 FAILED: /media/data/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_kernel.o /usr/bin/nvcc -DWITH_CUDA -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/TH -I/media/data/SOLO/env/lib/python3.7/site-packages/torch/include/THC -I/media/data/SOLO/env/include -I/opt/anaconda/envs/solo/include/python3.7m -c -c /media/data/SOLO/mmdet/ops/nms/src/nms_kernel.cu -o /media/data/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_kernel.o -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -DCUDA_NO_HALF_OPERATORS -DCUDA_NO_HALF_CONVERSIONS -DCUDA_NO_HALF2_OPERATORS -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_75,code=sm_75 -std=c++14 nvcc fatal : Unsupported gpu architecture 'compute_75' """
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-690619155, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOBRZLOX2FFGTIP5BBLSFEOADANCNFSM4RDQJJOQ .
AlexanderSvan
commented
4 years ago The CUDA versions match up and i verified the functionality by installing and running the mmdetections demo of MaskRCNN with no issue. So im able to build the current version of mmdet but not the v1.0.0 included in this library
abubakar2141731
commented
4 years ago what pytorch version are you using?
On Fri, Sep 11, 2020 at 1:09 PM AlexanderSvan notifications@github.com wrote:
The CUDA versions match up and i verified the functionality by installing and running the mmdetections demo of MaskRCNN with no issue. So im able to build the current version of mmdet but not the v1.0.0 included in this library
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-691031640, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTODIHJIVV2JKHQ52OTDSFIAQBANCNFSM4RDQJJOQ .
AlexanderSvan
commented
4 years ago 1.6, but i tried 1.4 as you mentioned as well
abubakar2141731
commented
4 years ago install pytorch 1.4, cuda toolkit 10.1
On Fri, Sep 11, 2020 at 3:02 PM AlexanderSvan notifications@github.com wrote:
1.6
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-691081152, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOABPFU5ZCXCGORAS6LSFINU3ANCNFSM4RDQJJOQ .
LiangYong1216
commented
4 years ago ImportError: /home/liangyong/anaconda3/envs/solov2/lib/python3.7/site-packages/mmdet-1.0.0+0b0dfb3-py3.7-linux-x86_64.egg/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E can you help me??
LiangYong1216
commented
4 years ago First: ImportError: /home/liangyong/anaconda3/envs/solov2/lib/python3.7/site-packages/mmdet-1.0.0+0b0dfb3-py3.7-linux-x86_64.egg/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E
My environment: cuda10.1 pytorch1.4 torchvision0.5
second:
Traceback (most recent call last):
File "/home/liangyong/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in
abubakar2141731
commented
4 years ago import os os.chdir('your d2det directory') !rm -r build !python setup.py develop
On Tue, Nov 17, 2020 at 9:14 AM LiangYong1216 notifications@github.com wrote:
First: ImportError: /home/liangyong/anaconda3/envs/solov2/lib/python3.7/site-packages/mmdet-1.0.0+0b0dfb3-py3.7-linux-x86_64.egg/mmdet/ops/sigmoid_focal_loss/ sigmoid_focal_loss_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E
My environment: cuda10.1 pytorch1.4 torchvision0.5
second: Traceback (most recent call last): File "/home/liangyong/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in from . import sigmoid_focal_loss_cuda ImportError: attempted relative import with no known parent package This ERROR occured in some place. can you help me
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-728764331, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOCRFQ4JW5G57BLCSMTSQIWGVANCNFSM4RDQJJOQ .
LiangYong1216
commented
3 years ago import os os.chdir('your d2det directory') !rm -r build !python setup.py develop … On Tue, Nov 17, 2020 at 9:14 AM LiangYong1216 @.***> wrote: First: ImportError: /home/liangyong/anaconda3/envs/solov2/lib/python3.7/site-packages/mmdet-1.0.0+0b0dfb3-py3.7-linux-x86_64.egg/mmdet/ops/sigmoid_focal_loss/ sigmoid_focal_loss_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E My environment: cuda10.1 pytorch1.4 torchvision0.5 second: Traceback (most recent call last): File "/home/liangyong/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in from . import sigmoid_focal_loss_cuda ImportError: attempted relative import with no known parent package This ERROR occured in some place. can you help me — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#98 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOCRFQ4JW5G57BLCSMTSQIWGVANCNFSM4RDQJJOQ .
thank you very much.i got it
LiangYong1216
commented
3 years ago UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details. "See the documentation of nn.Upsample for details.".format(mode)) when i training my dataset, this userwarning occured,hou should i handle this???? thank you very much!!!!!
gcg0210
commented
3 years ago First: ImportError: /home/liangyong/anaconda3/envs/solov2/lib/python3.7/site-packages/mmdet-1.0.0+0b0dfb3-py3.7-linux-x86_64.egg/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E
My environment: cuda10.1 pytorch1.4 torchvision0.5
second: Traceback (most recent call last): File "/home/liangyong/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in from . import sigmoid_focal_loss_cuda ImportError: attempted relative import with no known parent package This ERROR occured in some place. can you help me
same problem, how do you slove it ?thank you
abubakar2141731
commented
3 years ago use pytorch==1.4 , !rm -r build !python setup.py develop
On Sun, Dec 20, 2020 at 11:22 AM gcg0210 notifications@github.com wrote:
First: ImportError: /home/liangyong/anaconda3/envs/solov2/lib/python3.7/site-packages/mmdet-1.0.0+0b0dfb3-py3.7-linux-x86_64.egg/mmdet/ops/sigmoid_focal_loss/ sigmoid_focal_loss_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E
My environment: cuda10.1 pytorch1.4 torchvision0.5
second: Traceback (most recent call last): File "/home/liangyong/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in from . import sigmoid_focal_loss_cuda ImportError: attempted relative import with no known parent package This ERROR occured in some place. can you help me
same problem, how do you slove it ?thank you
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-748588754, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOHKNV4H4IU7MWSVCX3SVXGADANCNFSM4RDQJJOQ .
gcg0210
commented
3 years ago use pytorch==1.4 , !rm -r build !python setup.py develop … On Sun, Dec 20, 2020 at 11:22 AM gcg0210 @.***> wrote: First: ImportError: /home/liangyong/anaconda3/envs/solov2/lib/python3.7/site-packages/mmdet-1.0.0+0b0dfb3-py3.7-linux-x86_64.egg/mmdet/ops/sigmoid_focal_loss/ sigmoid_focal_loss_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E My environment: cuda10.1 pytorch1.4 torchvision0.5 second: Traceback (most recent call last): File "/home/liangyong/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in from . import sigmoid_focal_loss_cuda ImportError: attempted relative import with no known parent package This ERROR occured in some place. can you help me same problem, how do you slove it ?thank you — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#98 (comment)>, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOHKNV4H4IU7MWSVCX3SVXGADANCNFSM4RDQJJOQ .
I tried this.But it didn't work.
Traceback (most recent call last):
File "/home/pc001/e/gcg_new_new/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in
my env are as follows:
_libgcc_mutex 0.1 main https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
addict 2.4.0 pypi_0 pypi
albumentations 0.5.2 pypi_0 pypi
asynctest 0.13.0 pypi_0 pypi
attrs 20.3.0 pypi_0 pypi
blas 1.0 mkl https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
ca-certificates 2020.12.8 h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
certifi 2020.12.5 py37h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
chardet 4.0.0 pypi_0 pypi
codecov 2.1.11 pypi_0 pypi
coverage 5.3.1 pypi_0 pypi
cudatoolkit 10.1.243 h6bb024c_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
cycler 0.10.0 pypi_0 pypi
cython 0.29.21 pypi_0 pypi
decorator 4.4.2 pypi_0 pypi
flake8 3.8.4 pypi_0 pypi
freetype 2.10.4 h5ab3b9f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
idna 2.10 pypi_0 pypi
imagecorruptions 1.1.2 pypi_0 pypi
imageio 2.9.0 pypi_0 pypi
imgaug 0.4.0 pypi_0 pypi
importlib-metadata 3.3.0 pypi_0 pypi
iniconfig 1.1.1 pypi_0 pypi
intel-openmp 2020.2 254 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
isort 5.6.4 pypi_0 pypi
jpeg 9b h024ee3a_2 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
kiwisolver 1.3.1 pypi_0 pypi
kwarray 0.5.12 pypi_0 pypi
lcms2 2.11 h396b838_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
ld_impl_linux-64 2.33.1 h53a641e_7 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
libedit 3.1.20191231 h14c3975_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
libffi 3.3 he6710b0_2 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
libgcc-ng 9.1.0 hdf63c60_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
libpng 1.6.37 hbc83047_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
libstdcxx-ng 9.1.0 hdf63c60_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
libtiff 4.1.0 h2733197_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
lz4-c 1.9.2 heb0550a_3 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
matplotlib 3.3.3 pypi_0 pypi
mccabe 0.6.1 pypi_0 pypi
mkl 2020.2 256 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
mkl-service 2.3.0 py37he8ac12f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
mkl_fft 1.2.0 py37h23d657b_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
mkl_random 1.1.1 py37h0573a6f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
mmcv 0.2.16 pypi_0 pypi
mmdet 1.0.0+b00170f dev_0
abubakar2141731
commented
3 years ago this notebook might help you , i used it to train solo on google colab
On Sun, Dec 20, 2020 at 3:26 PM gcg0210 notifications@github.com wrote:
use pytorch==1.4 , !rm -r build !python setup.py develop … <#m-6311481873565249691> On Sun, Dec 20, 2020 at 11:22 AM gcg0210 @.***> wrote: First: ImportError: /home/liangyong/anaconda3/envs/solov2/lib/python3.7/site-packages/mmdet-1.0.0+0b0dfb3-py3.7-linux-x86_64.egg/mmdet/ops/sigmoid_focal_loss/ sigmoid_focal_loss_cuda.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E My environment: cuda10.1 pytorch1.4 torchvision0.5 second: Traceback (most recent call last): File "/home/liangyong/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in from . import sigmoid_focal_loss_cuda ImportError: attempted relative import with no known parent package This ERROR occured in some place. can you help me same problem, how do you slove it ?thank you — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub <#98 (comment) https://github.com/WXinlong/SOLO/issues/98#issuecomment-748588754>, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOHKNV4H4IU7MWSVCX3SVXGADANCNFSM4RDQJJOQ .
I tried this.But it didn't work.
Traceback (most recent call last): File "/home/pc001/e/gcg_new_new/SOLO/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss.py", line 5, in from . import sigmoid_focal_loss_cuda ImportError: attempted relative import with no known parent package
my env are as follows: Name Version Build Channel
_libgcc_mutex 0.1 main https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main addict 2.4.0 pypi_0 pypi albumentations 0.5.2 pypi_0 pypi asynctest 0.13.0 pypi_0 pypi attrs 20.3.0 pypi_0 pypi blas 1.0 mkl https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main ca-certificates 2020.12.8 h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main certifi 2020.12.5 py37h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main chardet 4.0.0 pypi_0 pypi codecov 2.1.11 pypi_0 pypi coverage 5.3.1 pypi_0 pypi cudatoolkit 10.1.243 h6bb024c_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main cycler 0.10.0 pypi_0 pypi cython 0.29.21 pypi_0 pypi decorator 4.4.2 pypi_0 pypi flake8 3.8.4 pypi_0 pypi freetype 2.10.4 h5ab3b9f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main idna 2.10 pypi_0 pypi imagecorruptions 1.1.2 pypi_0 pypi imageio 2.9.0 pypi_0 pypi imgaug 0.4.0 pypi_0 pypi importlib-metadata 3.3.0 pypi_0 pypi iniconfig 1.1.1 pypi_0 pypi intel-openmp 2020.2 254 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main isort 5.6.4 pypi_0 pypi jpeg 9b h024ee3a_2 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main kiwisolver 1.3.1 pypi_0 pypi kwarray 0.5.12 pypi_0 pypi lcms2 2.11 h396b838_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main ld_impl_linux-64 2.33.1 h53a641e_7 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libedit 3.1.20191231 h14c3975_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libffi 3.3 he6710b0_2 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libgcc-ng 9.1.0 hdf63c60_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libpng 1.6.37 hbc83047_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libstdcxx-ng 9.1.0 hdf63c60_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main libtiff 4.1.0 h2733197_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main lz4-c 1.9.2 heb0550a_3 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main matplotlib 3.3.3 pypi_0 pypi mccabe 0.6.1 pypi_0 pypi mkl 2020.2 256 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main mkl-service 2.3.0 py37he8ac12f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main mkl_fft 1.2.0 py37h23d657b_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main mkl_random 1.1.1 py37h0573a6f_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main mmcv 0.2.16 pypi_0 pypi mmdet 1.0.0+b00170f dev_0 ncurses 6.2 he6710b0_1 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main networkx 2.5 pypi_0 pypi ninja 1.10.2 py37hff7bd54_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main numpy 1.19.2 py37h54aff64_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main numpy-base 1.19.2 py37hfa32c7d_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main olefile 0.46 py37_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main opencv-python 4.4.0.46 pypi_0 pypi opencv-python-headless 4.4.0.46 pypi_0 pypi openssl 1.1.1i h27cfd23_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main ordered-set 4.0.2 pypi_0 pypi packaging 20.8 pypi_0 pypi pillow 6.2.2 pypi_0 pypi pip 20.3.3 py37h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main pluggy 0.13.1 pypi_0 pypi py 1.10.0 pypi_0 pypi pycocotools 2.0 pypi_0 pypi pycodestyle 2.6.0 pypi_0 pypi pyflakes 2.2.0 pypi_0 pypi pyparsing 2.4.7 pypi_0 pypi pytest 6.2.1 pypi_0 pypi pytest-cov 2.10.1 pypi_0 pypi pytest-runner 5.2 pypi_0 pypi python 3.7.9 h7579374_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main python-dateutil 2.8.1 pypi_0 pypi pytorch 1.4.0 py3.7_cuda10.1.243_cudnn7.6.3_0 pytorch pywavelets 1.1.1 pypi_0 pypi pyyaml 5.3.1 pypi_0 pypi readline 8.0 h7b6447c_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main requests 2.25.1 pypi_0 pypi scikit-image 0.18.0 pypi_0 pypi scipy 1.5.4 pypi_0 pypi setuptools 51.0.0 py37h06a4308_2 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main shapely 1.7.1 pypi_0 pypi six 1.15.0 py37h06a4308_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main sqlite 3.33.0 h62c20be_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main terminaltables 3.1.0 pypi_0 pypi tifffile 2020.12.8 pypi_0 pypi tk 8.6.10 hbc83047_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main toml 0.10.2 pypi_0 pypi torchvision 0.5.0 py37_cu101 pytorch typing-extensions 3.7.4.3 pypi_0 pypi ubelt 0.9.3 pypi_0 pypi urllib3 1.26.2 pypi_0 pypi wheel 0.36.2 pyhd3eb1b0_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main xdoctest 0.15.0 pypi_0 pypi xz 5.2.5 h7b6447c_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main yapf 0.30.0 pypi_0 pypi zipp 3.4.0 pypi_0 pypi zlib 1.2.11 h7b6447c_3 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main zstd 1.4.5 h9ceee32_0 https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-748614773, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOCJWO7V572WUQHL5ELSVYCSDANCNFSM4RDQJJOQ .
gcg0210
commented
3 years ago hello! my dataset is little special .some data has no foreground ,and some data has no background. I don't konw if it would work when facing these dataset.thank you .
cyrilzakka
commented
3 years ago @abubakar2141731 Mind sharing your colab notebook with SOLO setup?
abubakar2141731
commented
3 years ago Here it is.
On Sun, Apr 11, 2021 at 9:06 AM Cyril Zakka @.***> wrote:
@abubakar2141731 https://github.com/abubakar2141731 Mind sharing your colab notebook with SOLO setup?
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-817261101, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOHUV6XIGL7OS4QNBXDTIFC73ANCNFSM4RDQJJOQ .
cyrilzakka
commented
3 years ago @abubakar2141731 I'm sorry but I'm not seeing a link
abubakar2141731
commented
3 years ago Hello, I sent as an attachment previously, please find the link here : https://colab.research.google.com/drive/1F67zmJ71Ff9Hzh8AEpCboLKhzIko7CTh?usp=sharing
There are three notebooks, please check the notebooks with names Untitled, I haven't renamed them. I hope you will figure it out, open all of them .
On Mon, Apr 12, 2021 at 9:42 AM Cyril Zakka @.***> wrote:
@abubakar2141731 https://github.com/abubakar2141731 I'm sorry but I'm not seeing a link
— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/WXinlong/SOLO/issues/98#issuecomment-817569388, or unsubscribe https://github.com/notifications/unsubscribe-auth/APDXTOECGKVNM7XWP656G4LTIKP4ZANCNFSM4RDQJJOQ .
Hi, while installing the setup for solov2, i got the following wrror, i installed mmdetection from mmlab repositiory and it installed perfectly fine, my cuda version is 10.1, and pytorch is 1.6, can you please help me to diagnose this error running develop running egg_info writing mmdet.egg-info/PKG-INFO writing dependency_links to mmdet.egg-info/dependency_links.txt writing requirements to mmdet.egg-info/requires.txt writing top-level names to mmdet.egg-info/top_level.txt reading manifest file 'mmdet.egg-info/SOURCES.txt' writing manifest file 'mmdet.egg-info/SOURCES.txt' running build_ext building 'mmdet.ops.utils.compiling_info' extension creating /content/SOLO/build/temp.linux-x86_64-3.7 creating /content/SOLO/build/temp.linux-x86_64-3.7/mmdet creating /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops creating /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/utils creating /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/utils/src Emitting ninja build file /content/SOLO/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) [1/1] c++ -MMD -MF /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/utils/src/compiling_info.o.d -pthread -B /usr/local/envs/solo/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/usr/local/envs/solo/lib/python3.7/site-packages/torch/include -I/usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/usr/local/envs/solo/lib/python3.7/site-packages/torch/include/TH -I/usr/local/envs/solo/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/local/envs/solo/include/python3.7m -c -c /content/SOLO/mmdet/ops/utils/src/compiling_info.cpp -o /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/utils/src/compiling_info.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=compiling_info -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:149:0, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:7, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from /content/SOLO/mmdet/ops/utils/src/compiling_info.cpp:4: /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:84:0: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]
pragma omp parallel for if ((end - begin) >= grain_size)
g++ -pthread -shared -B /usr/local/envs/solo/compiler_compat -L/usr/local/envs/solo/lib -Wl,-rpath=/usr/local/envs/solo/lib -Wl,--no-as-needed -Wl,--sysroot=/ /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/utils/src/compiling_info.o -L/usr/local/envs/solo/lib/python3.7/site-packages/torch/lib -L/usr/local/cuda/lib64 -lc10 -ltorch -ltorch_cpu -ltorch_python -lcudart -lc10_cuda -ltorch_cuda -o build/lib.linux-x86_64-3.7/mmdet/ops/utils/compiling_info.cpython-37m-x86_64-linux-gnu.so building 'mmdet.ops.nms.soft_nms_cpu' extension creating /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms creating /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src Emitting ninja build file /content/SOLO/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) [1/1] c++ -MMD -MF /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/soft_nms_cpu.o.d -pthread -B /usr/local/envs/solo/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/usr/local/envs/solo/lib/python3.7/site-packages/numpy/core/include -I/usr/local/envs/solo/include/python3.7m -c -c /content/SOLO/mmdet/ops/nms/src/soft_nms_cpu.cpp -o /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/soft_nms_cpu.o -Wno-unused-function -Wno-write-strings -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=soft_nms_cpu -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /usr/local/envs/solo/lib/python3.7/site-packages/numpy/core/include/numpy/ndarraytypes.h:1822:0, from /usr/local/envs/solo/lib/python3.7/site-packages/numpy/core/include/numpy/ndarrayobject.h:12, from /usr/local/envs/solo/lib/python3.7/site-packages/numpy/core/include/numpy/arrayobject.h:4, from /content/SOLO/mmdet/ops/nms/src/soft_nms_cpu.cpp:650: /usr/local/envs/solo/lib/python3.7/site-packages/numpy/core/include/numpy/npy_1_7_deprecated_api.h:17:2: warning: #warning "Using deprecated NumPy API, disable it with " "#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-Wcpp]
warning "Using deprecated NumPy API, disable it with " \
^
~~ g++ -pthread -shared -B /usr/local/envs/solo/compiler_compat -L/usr/local/envs/solo/lib -Wl,-rpath=/usr/local/envs/solo/lib -Wl,--no-as-needed -Wl,--sysroot=/ /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/soft_nms_cpu.o -o build/lib.linux-x86_64-3.7/mmdet/ops/nms/soft_nms_cpu.cpython-37m-x86_64-linux-gnu.so building 'mmdet.ops.nms.nms_cpu' extension Emitting ninja build file /content/SOLO/build/temp.linux-x86_64-3.7/build.ninja... Compiling objects... Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) [1/1] c++ -MMD -MF /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_cpu.o.d -pthread -B /usr/local/envs/solo/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/usr/local/envs/solo/lib/python3.7/site-packages/torch/include -I/usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/usr/local/envs/solo/lib/python3.7/site-packages/torch/include/TH -I/usr/local/envs/solo/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda/include -I/usr/local/envs/solo/include/python3.7m -c -c /content/SOLO/mmdet/ops/nms/src/nms_cpu.cpp -o /content/SOLO/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_cpu.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_cpu -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/ATen/Parallel.h:149:0, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/utils.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn/cloneable.h:5, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/nn.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:7, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from /content/SOLO/mmdet/ops/nms/src/nms_cpu.cpp:2: /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/ATen/ParallelOpenMP.h:84:0: warning: ignoring #pragma omp parallel [-Wunknown-pragmas]pragma omp parallel for if ((end - begin) >= grain_size)
In file included from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/c10/core/Device.h:5:0, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/c10/core/Allocator.h:6, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/ATen/ATen.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4, from /usr/local/envs/solo/lib/python3.7/site-packages/torch/include/torch/extension.h:4, from /content/SOLO/mmdet/ops/nms/src/nms_cpu.cpp:2: /content/SOLO/mmdet/ops/nms/src/nms_cpu.cpp: In instantiation of ‘at::Tensor nms_cpu_kernel(const at::Tensor&, float) [with scalar_t = double]’: /content/SOLO/mmdet/ops/nms/src/nms_cpu.cpp:63:3: required from here /content/SOLO/mmdet/ops/nms/src/nms_cpu.cpp:6:24: warning: ‘at::DeprecatedTypeProperties& at::Tensor::type() const’ is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations] AT_ASSERTM(!dets.type().is_cuda(), "dets must be a CPU tensor");