ruoqianguo / detnet_pytorch Goto Github PK

hello, is your GPU Titan 1080 Ti?
I use a single GPU of K40，and bs is set as 1, and it'll produce cuda runtime error.

I set the optimizer as adam, and lr is 1e-4 due to the small training dataset, but loss may be nan, do you know what's the problem?

I am unable to download weights from dropbox.

running build_ext
skipping 'model/utils/bbox.c' Cython extension (up-to-date)
skipping 'model/nms/cpu_nms.c' Cython extension (up-to-date)
skipping 'pycocotools/_mask.c' Cython extension (up-to-date)
Compiling nms kernels by nvcc...
make.sh: 11: make.sh: nvcc: not found
Including CUDA code.
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms
['/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda_kernel.cu.o']
generating /tmp/tmp25ghhu/_nms.c
setting the current directory to '/tmp/tmp25ghhu'
running build_ext
building '_nms' extension
creating disk1
creating disk1/g201708021059
creating disk1/g201708021059/gg
creating disk1/g201708021059/gg/DetNet_Pytorch
creating disk1/g201708021059/gg/DetNet_Pytorch/lib
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c _nms.c -o ./_nms.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda.o
x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -D_FORTIFY_SOURCE=2 -g -fstack-protector --param=ssp-buffer-size=4 -Wformat -Werror=format-security -std=c99 ./_nms.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda.o /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda_kernel.cu.o -o ./_nms.so
x86_64-linux-gnu-gcc: error: /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda_kernel.cu.o: No such file or directory
Traceback (most recent call last):
File "build.py", line 36, in
ffi.build()
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 164, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 100, in _build_extension
ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: LinkError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
Compiling roi pooling kernels by nvcc...
make.sh: 20: make.sh: nvcc: not found
Including CUDA code.
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling
generating /tmp/tmpaGCAHV/_roi_pooling.c
setting the current directory to '/tmp/tmpaGCAHV'
running build_ext
building '_roi_pooling' extension
creating disk1
creating disk1/g201708021059
creating disk1/g201708021059/gg
creating disk1/g201708021059/gg/DetNet_Pytorch
creating disk1/g201708021059/gg/DetNet_Pytorch/lib
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c _roi_pooling.c -o ./_roi_pooling.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling_cuda.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling_cuda.o
x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -D_FORTIFY_SOURCE=2 -g -fstack-protector --param=ssp-buffer-size=4 -Wformat -Werror=format-security -std=c99 ./_roi_pooling.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling_cuda.o /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.cu.o -o ./_roi_pooling.so
x86_64-linux-gnu-gcc: error: /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.cu.o: No such file or directory
Traceback (most recent call last):
File "build.py", line 34, in
ffi.build()
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 164, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 100, in _build_extension
ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: LinkError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
Compiling roi align kernels by nvcc...
make.sh: 29: make.sh: nvcc: not found
Including CUDA code.
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align
generating /tmp/tmpdKm6CH/_roi_align.c
setting the current directory to '/tmp/tmpdKm6CH'
running build_ext
building '_roi_align' extension
creating disk1
creating disk1/g201708021059
creating disk1/g201708021059/gg
creating disk1/g201708021059/gg/DetNet_Pytorch
creating disk1/g201708021059/gg/DetNet_Pytorch/lib
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c _roi_align.c -o ./_roi_align.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_cuda.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_cuda.o
x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -D_FORTIFY_SOURCE=2 -g -fstack-protector --param=ssp-buffer-size=4 -Wformat -Werror=format-security -std=c99 ./_roi_align.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_cuda.o /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_kernel.cu.o -o ./_roi_align.so
x86_64-linux-gnu-gcc: error: /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_kernel.cu.o: No such file or directory
Traceback (most recent call last):
File "build.py", line 35, in
ffi.build()
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 164, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 100, in _build_extension
ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: LinkError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
Compiling roi crop kernels by nvcc...
make.sh: 38: make.sh: nvcc: not found
Including CUDA code.
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop
generating /tmp/tmpzbFmDZ/_roi_crop.c
setting the current directory to '/tmp/tmpzbFmDZ'
running build_ext
building '_roi_crop' extension
creating disk1
creating disk1/g201708021059
creating disk1/g201708021059/gg
creating disk1/g201708021059/gg/DetNet_Pytorch
creating disk1/g201708021059/gg/DetNet_Pytorch/lib
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c _roi_crop.c -o ./_roi_crop.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.o
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c: In function ‘BilinearSamplerBHWD_updateGradInput’:
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:190:14: warning: unused variable ‘inBottomRight’ [-Wunused-variable]
real inBottomRight=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:189:14: warning: unused variable ‘inBottomLeft’ [-Wunused-variable]
real inBottomLeft=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:188:14: warning: unused variable ‘inTopRight’ [-Wunused-variable]
real inTopRight=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:187:14: warning: unused variable ‘inTopLeft’ [-Wunused-variable]
real inTopLeft=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:186:14: warning: unused variable ‘v’ [-Wunused-variable]
real v=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c: In function ‘BilinearSamplerBCHW_updateGradInput’:
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:441:14: warning: unused variable ‘inBottomRight’ [-Wunused-variable]
real inBottomRight=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:440:14: warning: unused variable ‘inBottomLeft’ [-Wunused-variable]
real inBottomLeft=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:439:14: warning: unused variable ‘inTopRight’ [-Wunused-variable]
real inTopRight=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:438:14: warning: unused variable ‘inTopLeft’ [-Wunused-variable]
real inTopLeft=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:437:14: warning: unused variable ‘v’ [-Wunused-variable]
real v=0;
^
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda.o
x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -D_FORTIFY_SOURCE=2 -g -fstack-protector --param=ssp-buffer-size=4 -Wformat -Werror=format-security -std=c99 ./_roi_crop.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda.o /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda_kernel.cu.o -o ./_roi_crop.so
x86_64-linux-gnu-gcc: error: /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda_kernel.cu.o: No such file or directory
Traceback (most recent call last):
File "build.py", line 35, in
ffi.build()
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 164, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 100, in _build_extension
ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: LinkError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
g201708021059@scw4750:/gg/DetNet_Pytorch/lib$ sudo apt-get install python2.7-dev
Reading package lists... Done
Building dependency tree
Reading state information... Done
python2.7-dev is already the newest version.
python2.7-dev set to manually installed.
0 upgraded, 0 newly installed, 0 to remove and 59 not upgraded.
g201708021059@scw4750:/gg/DetNet_Pytorch/lib$ sh make.sh
running build_ext
skipping 'model/utils/bbox.c' Cython extension (up-to-date)
skipping 'model/nms/cpu_nms.c' Cython extension (up-to-date)
skipping 'pycocotools/_mask.c' Cython extension (up-to-date)
Compiling nms kernels by nvcc...
make.sh: 11: make.sh: nvcc: not found
Including CUDA code.
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms
['/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda_kernel.cu.o']
generating /tmp/tmphykfmz/_nms.c
setting the current directory to '/tmp/tmphykfmz'
running build_ext
building '_nms' extension
creating disk1
creating disk1/g201708021059
creating disk1/g201708021059/gg
creating disk1/g201708021059/gg/DetNet_Pytorch
creating disk1/g201708021059/gg/DetNet_Pytorch/lib
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c _nms.c -o ./_nms.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda.o
x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -D_FORTIFY_SOURCE=2 -g -fstack-protector --param=ssp-buffer-size=4 -Wformat -Werror=format-security -std=c99 ./_nms.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda.o /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda_kernel.cu.o -o ./_nms.so
x86_64-linux-gnu-gcc: error: /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/nms/src/nms_cuda_kernel.cu.o: No such file or directory
Traceback (most recent call last):
File "build.py", line 36, in
ffi.build()
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 164, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 100, in _build_extension
ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: LinkError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
Compiling roi pooling kernels by nvcc...
make.sh: 20: make.sh: nvcc: not found
Including CUDA code.
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling
generating /tmp/tmprX3Cci/_roi_pooling.c
setting the current directory to '/tmp/tmprX3Cci'
running build_ext
building '_roi_pooling' extension
creating disk1
creating disk1/g201708021059
creating disk1/g201708021059/gg
creating disk1/g201708021059/gg/DetNet_Pytorch
creating disk1/g201708021059/gg/DetNet_Pytorch/lib
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c _roi_pooling.c -o ./_roi_pooling.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling_cuda.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling_cuda.o
x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -D_FORTIFY_SOURCE=2 -g -fstack-protector --param=ssp-buffer-size=4 -Wformat -Werror=format-security -std=c99 ./_roi_pooling.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling_cuda.o /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.cu.o -o ./_roi_pooling.so
x86_64-linux-gnu-gcc: error: /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_pooling/src/roi_pooling.cu.o: No such file or directory
Traceback (most recent call last):
File "build.py", line 34, in
ffi.build()
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 164, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 100, in _build_extension
ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: LinkError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
Compiling roi align kernels by nvcc...
make.sh: 29: make.sh: nvcc: not found
Including CUDA code.
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align
generating /tmp/tmpc_KAbR/_roi_align.c
setting the current directory to '/tmp/tmpc_KAbR'
running build_ext
building '_roi_align' extension
creating disk1
creating disk1/g201708021059
creating disk1/g201708021059/gg
creating disk1/g201708021059/gg/DetNet_Pytorch
creating disk1/g201708021059/gg/DetNet_Pytorch/lib
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c _roi_align.c -o ./_roi_align.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_cuda.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_cuda.o
x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -D_FORTIFY_SOURCE=2 -g -fstack-protector --param=ssp-buffer-size=4 -Wformat -Werror=format-security -std=c99 ./_roi_align.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_cuda.o /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_kernel.cu.o -o ./_roi_align.so
x86_64-linux-gnu-gcc: error: /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_align/src/roi_align_kernel.cu.o: No such file or directory
Traceback (most recent call last):
File "build.py", line 35, in
ffi.build()
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 164, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 100, in _build_extension
ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: LinkError: command 'x86_64-linux-gnu-gcc' failed with exit status 1
Compiling roi crop kernels by nvcc...
make.sh: 38: make.sh: nvcc: not found
Including CUDA code.
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop
generating /tmp/tmpsXcAr7/_roi_crop.c
setting the current directory to '/tmp/tmpsXcAr7'
running build_ext
building '_roi_crop' extension
creating disk1
creating disk1/g201708021059
creating disk1/g201708021059/gg
creating disk1/g201708021059/gg/DetNet_Pytorch
creating disk1/g201708021059/gg/DetNet_Pytorch/lib
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop
creating disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c _roi_crop.c -o ./_roi_crop.o
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.o
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c: In function ‘BilinearSamplerBHWD_updateGradInput’:
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:190:14: warning: unused variable ‘inBottomRight’ [-Wunused-variable]
real inBottomRight=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:189:14: warning: unused variable ‘inBottomLeft’ [-Wunused-variable]
real inBottomLeft=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:188:14: warning: unused variable ‘inTopRight’ [-Wunused-variable]
real inTopRight=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:187:14: warning: unused variable ‘inTopLeft’ [-Wunused-variable]
real inTopLeft=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:186:14: warning: unused variable ‘v’ [-Wunused-variable]
real v=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c: In function ‘BilinearSamplerBCHW_updateGradInput’:
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:441:14: warning: unused variable ‘inBottomRight’ [-Wunused-variable]
real inBottomRight=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:440:14: warning: unused variable ‘inBottomLeft’ [-Wunused-variable]
real inBottomLeft=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:439:14: warning: unused variable ‘inTopRight’ [-Wunused-variable]
real inTopRight=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:438:14: warning: unused variable ‘inTopLeft’ [-Wunused-variable]
real inTopLeft=0;
^
/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.c:437:14: warning: unused variable ‘v’ [-Wunused-variable]
real v=0;
^
x86_64-linux-gnu-gcc -pthread -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python2.7 -c /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda.c -o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda.o
x86_64-linux-gnu-gcc -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -fno-strict-aliasing -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -D_FORTIFY_SOURCE=2 -g -fstack-protector --param=ssp-buffer-size=4 -Wformat -Werror=format-security -std=c99 ./_roi_crop.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop.o ./disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda.o /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda_kernel.cu.o -o ./_roi_crop.so
x86_64-linux-gnu-gcc: error: /disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/src/roi_crop_cuda_kernel.cu.o: No such file or directory
Traceback (most recent call last):
File "build.py", line 35, in
ffi.build()
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 164, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python2.7/dist-packages/torch/utils/ffi/init.py", line 100, in _build_extension
ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/disk1/g201708021059/.local/lib/python2.7/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: LinkError: command 'x86_64-linux-gnu-gcc' failed with exit status 1

per Pytorch 0.2.0 or higher（not support pytorch version >=0.4.0）, I try to install pytorch by conda install pytorch=0.2.0 cuda80 -c pytorch
But I got this error:

Collecting package metadata: done
Solving environment: failed

PackagesNotFoundError: The following packages are not available from current channels:

• pytorch=0.2.0

Current channels:

• https://conda.anaconda.org/pytorch/win-64
• https://conda.anaconda.org/pytorch/noarch
• https://repo.anaconda.com/pkgs/main/win-64
• https://repo.anaconda.com/pkgs/main/noarch
• https://repo.anaconda.com/pkgs/free/win-64
• https://repo.anaconda.com/pkgs/free/noarch
• https://repo.anaconda.com/pkgs/r/win-64
• https://repo.anaconda.com/pkgs/r/noarch
• https://repo.anaconda.com/pkgs/msys2/win-64
• https://repo.anaconda.com/pkgs/msys2/noarch
• https://conda.anaconda.org/conda-forge/win-64
• https://conda.anaconda.org/conda-forge/noarch
• https://conda.anaconda.org/anaconda/win-64
• https://conda.anaconda.org/anaconda/noarch

To search for alternate channels that may provide the conda package you're
looking for, navigate to

https://anaconda.org

and use the search bar at the top of the page.

It seems the old pytorch version is nowhere to be downloaded.
Please help. My whole life depends on this:)

the links which you have given to download pre-trained model detnet59.pth are not working. how can i download detnet59 pre-trained model?

I want to use your code to train your own dataset. There are many gt boxes in it, and there are probably hundreds of them.MAX_NUM_GT_BOXES=20, can I change this parameter a lot? I see the default in Pascal VOC is 20.

hello,I want to test any image with trained model ,how should I modify the code,thks

(py27) guowei@iitlab-cat:~/gg/DetNet_Pytorch$ CUDA_VISIBLE_DEVICES=1 python test_dota.py exp_name --dataset pascal_voc --net detnet59 --checksession 1 --checkepoch 11 --checkpoint 315 --cuda --load_dir weights --soft_nms

load checkpoint weights-dota/detnet59/pascal_voc/exp_name/fpn_1_11_315.pth
load model successfully!
/home/disk2/gg/DetNet_Pytorch/lib/model/rpn/rpn_fpn.py:79: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
rpn_cls_prob_reshape = F.softmax(rpn_cls_score_reshape)
/home/disk2/gg/DetNet_Pytorch/lib/model/fpn/fpn.py:259: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
cls_prob = F.softmax(cls_score)
Traceback (most recent call last):
File "test_aiia.py", line 232, in
data = data_iter.next()
File "/home/disk2/anaconda3/envs/py27/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 210, in next
return self._process_next_batch(batch)
File "/home/disk2/anaconda3/envs/py27/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 230, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
ValueError: Traceback (most recent call last):
File "/home/disk2/anaconda3/envs/py27/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 42, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/disk2/gg/DetNet_Pytorch/lib/roi_data_layer/roibatchLoader.py", line 67, in getitem
blobs = get_minibatch(minibatch_db, self._num_classes)
File "/home/disk2/gg/DetNet_Pytorch/lib/roi_data_layer/minibatch.py", line 30, in get_minibatch
im_blob, im_scales = _get_image_blob(roidb, random_scale_inds)
File "/home/disk2/gg/DetNet_Pytorch/lib/roi_data_layer/minibatch.py", line 79, in _get_image_blob
cfg.TRAIN.MAX_SIZE)
File "/home/disk2/gg/DetNet_Pytorch/lib/model/utils/blob.py", line 39, in prep_im_for_blob
im -= pixel_means
ValueError: operands could not be broadcast together with shapes (3593,6335,4) (1,1,3) (3593,6335,4)

I have no idea of this error,please help me. Is the data error??

Hello!
Thank you for your implemetaion of DetNet.I training the model on PASCAL VOC07 dataset. I use three GPUs and set bs=16, lr = 1e-2, lr_decay_step=8, but the mAP is 73 on PASCAL VOC07 test.

Is there any example that I could follow? Thx

Does scale(600) mean the input image size?
600?

I want use the detnet to do some work, but the detnet59 is large for me, can you provide some pretrained detnet model smaller as resnet18?

I have a copy in my repo:
https://github.com/Morris-Chen007/deep_learning_models

Feel free to get it!

I want to finetune the model,but the link is not available.
such as https://www.dropbox.com/home/DetNet/PASCAL%20VOC%2007%2B12?preview=fpn_1_7_33101.pth
my email is [email protected]

hi,I was wondering Can it be applied to the faster rcnn model instead of resnet101?

In your implementation, the feat stride is set to [4, 8, 16, 16, 16] in line 187 of trainval.py
FPN_FEAT_STRIDES', '[4, 8, 16, 16, 16]
it worked, and it's indeed the case in the original paper,
because the feature maps are downsampled 4x, 8x, 16x, 16x, 16x (only dilated, no pooling).

However, from my understanding, as we are using dilated conv, the receptive field of the 3rd, 4 and 5 th layers are enlarged, so I think the stride should be set to
[4, 8, 16, 32, 64]
ie, one point in the 4th layer represents 2x more information than the 3rd layer. (so 32x?)

Maybe I'm not understanding dilated conv in the right way..? Correct me if I'm wrong.

In the paper it says "our stage 5 and 6 keeps the same input channels as stage 4(256 input channels for bottleneck block)". However in your code the way you create those two stages is take an input of c=1024.
I'm actually stuck by this for quite a while. We know that the # of output channels for stage 4 is 1024, then how is it possible that stage 5 takes an input channels of 256?

I use cuda90/cudnn7.pytorch 0.3.1.Someone adding env.close() or env.env.close() at the end of programs wokes. but i adding it the end of trainval_net.py doesn't work. Can anyone tell me why?

Traceback (most recent call last):
File "trainval_aiia.py", line 362, in
roi_labels = FPN(im_data, im_info, gt_boxes, num_boxes)
File "/home/disk2/anaconda3/envs/tf/lib/python3.6/site-packages/torch/nn/modules/module.py", line 357, in call
result = self.forward(*input, **kwargs)
File "/home/disk2/gg/DetNet_Pytorch/lib/model/fpn/fpn.py", line 254, in forward
bbox_pred_select = torch.gather(bbox_pred_view, 1, rois_label.long().view(rois_label.size(0), 1, 1).expand(rois_label.size(0), 1, 4))
RuntimeError: invalid argument 2: Input tensor must have same size as output tensor apart from the specified dimension at /pytorch/torch/lib/THC/generic/THCTensorScatterGather.cu:29
Exception ignored in: <bound method DataLoaderIter.del of <torch.utils.data.dataloader.DataLoaderIter object at 0x7fbe91f657f0>>
Traceback (most recent call last):
File "/home/disk2/anaconda3/envs/tf/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 333, in del
File "/home/disk2/anaconda3/envs/tf/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 319, in _shutdown_workers
File "/home/disk2/anaconda3/envs/tf/lib/python3.6/multiprocessing/queues.py", line 344, in get
ImportError: sys.meta_path is None, Python is likely shutting down

When i run trainval_net.py by my data like voc the other error arised as blow.....please help me....

Traceback (most recent call last):
File "trainval_aiia.py", line 362, in
roi_labels = FPN(im_data, im_info, gt_boxes, num_boxes)
File "/home/disk2/anaconda3/envs/tf/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/disk2/gg/DetNet_Pytorch/lib/model/fpn/fpn.py", line 192, in forward
rois, rpn_loss_cls, rpn_loss_bbox = self.RCNN_rpn(rpn_feature_maps, im_info, gt_boxes, num_boxes)
File "/home/disk2/anaconda3/envs/tf/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/disk2/gg/DetNet_Pytorch/lib/model/rpn/rpn_fpn.py", line 109, in forward
rpn_data = self.RPN_anchor_target((rpn_cls_score_alls.data, gt_boxes, im_info, num_boxes, rpn_shapes))
File "/home/disk2/anaconda3/envs/tf/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/disk2/gg/DetNet_Pytorch/lib/model/rpn/anchor_target_layer_fpn.py", line 141, in forward
positive_weights = 1.0 / num_examples
File "/home/disk2/anaconda3/envs/tf/lib/python3.6/site-packages/torch/tensor.py", line 320, in rdiv
return self.reciprocal() * other
RuntimeError: reciprocal is not implemented for type torch.cuda.LongTensor

With using the version of pytorch0.3.1 and pytorch0.4.0 both with python3.6, I met the error as blow:

Traceback (most recent call last):
File "trainval_aiia.py", line 29, in
from model.utils.net_utils import vis_detections
File "/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/utils/net_utils.py", line 11, in
from model.roi_crop.functions.roi_crop import RoICropFunction
File "/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/functions/roi_crop.py", line 4, in
from .._ext import roi_crop
File "/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/roi_crop/_ext/roi_crop/init.py", line 3, in
from ._roi_crop import lib as _lib, ffi as _ffi
ImportError: dynamic module does not define module export function (PyInit__roi_crop)

When I change to use python2.7,pytorch0.3.1,other error arised as blow:

(py27-pytorch) g201708021059@scw4750:~/gg/DetNet_Pytorch$ CUDA_VISIBLE_DEVICES=0 python3 trainval_aiia.py exp_name --dataset pascal_voc --net detnet59 --bs 1 --nw 1 --lr 1e-3 --epochs 12 --save_dir weights --cuda --use_tfboard True
Traceback (most recent call last):
File "trainval_aiia.py", line 29, in
from model.utils.net_utils import vis_detections
File "/disk1/g201708021059/gg/DetNet_Pytorch/lib/model/utils/net_utils.py", line 9, in
import torchvision.models as models
ModuleNotFoundError: No module named 'torchvision.models'

and I have done the complilation process, with using the cuda80/cudnn6.0

when
/DetNet_Pytorch$ CUDA_VISIBLE_DEVICES=1 python3 trainval_aiia.py exp_name --dataset pascal_voc --net detnet59 --bs 1 --nw 1 --lr 1e-3 --epochs 12 --save_dir weights --cuda --use_tfboard True

I got the error ''Segmentation fault (core dumped)‘’

Please help me.
the data in DetNet_Pytorch/data/VOCdevkit2007 is ok?

How did you get a score of resnet?

which -arch is for Tesla V100 ?

Hi，thanks for your code.
I am having a weird problem about GPU memory.
I have four Titanx GPU, but when I use your code for training Pascal data set , even if I have reduced the batch size to 1 and use mGPUs, it still gives feed back about

RuntimeError: cuda runtime error (2) : out of memory at /opt/conda/conda-bld/pytorch_1513363039688/work/torch/lib/THC/generic/THCStorage.cu:58

Would you mind tell me why? I am not sure if that's because some part of the code has some problem>
And my cuda version is 8.0, pytorch 0.3.0,

@baolinhu
@KevinQian97

same problem with u.
can u solve the problem??many many thanks!!!

Originally posted by @foralliance in #2 (comment)

params = [] for key, value in dict(FPN.named_parameters()).items(): if value.requires_grad: if 'bias' in key: params += [{'params': [value], 'lr': lr * (cfg.TRAIN.DOUBLE_BIAS + 1), \ 'weight_decay': cfg.TRAIN.BIAS_DECAY and cfg.TRAIN.WEIGHT_DECAY or 0}] else: params += [{'params': [value], 'lr': lr, 'weight_decay': cfg.TRAIN.WEIGHT_DECAY}]
I have some incomprehension about this part of code in trainval_net.py, can you tell the meaning of this part, and we do that for the reason of frozen layers?

I downloaded it . I run the trainval_net.py which I modified , I modified the "_FPN", but it was error . so, the pretrained model is the detnet-backbone with FPN which trained on Imagenet ???

`Traceback (most recent call last):
File "trainval_net.py", line 36, in
from model.fpn.detnet_backbone import detnet
File "/home/wty/project/DetNet_pytorch/lib/model/fpn/detnet_backbone.py", line 6, in
from model.fpn.fpn import _FPN
File "/home/wty/project/DetNet_pytorch/lib/model/fpn/fpn.py", line 12, in
from model.rpn.rpn_fpn import _RPN_FPN
File "/home/wty/project/DetNet_pytorch/lib/model/rpn/rpn_fpn.py", line 7, in
from .proposal_layer_fpn import _ProposalLayer_FPN
File "/home/wty/project/DetNet_pytorch/lib/model/rpn/proposal_layer_fpn.py", line 19, in
from model.nms.nms_wrapper import nms
File "/home/wty/project/DetNet_pytorch/lib/model/nms/nms_wrapper.py", line 10, in
from model.nms.cpu_nms import cpu_soft_nms

ModuleNotFoundError: No module named 'model.nms.cpu_nms'`
I have installed the cython, I don't get why thie problem occured, anyone can help me?

Thank you for your sharing the detnet59 pretrained model. I want to know why the mAP in COCO2017 is much lower than the result reported in the original paper?

cannot download the detnet50.pth with the uploaded dropbox link. Anyone else who can download the pth with dropbox??

hello, is it provide to provide the training code of DetNet59 backbone for ImageNet? Thanks a lot

[session 1][epoch 1][iter 0/19370] loss: 2.0254, lr: 1.00e-03 fg/bg=(54/202), time cost: 2.824575 rpn_cls: 0.6977, rpn_box: 0.2524, rcnn_cls: 0.6933, rcnn_box 0.3820 Traceback (most recent call last): File "trainval_net.py", line 362, in <module> roi_labels = FPN(im_data, im_info, gt_boxes, num_boxes) File "/home/hubl/anaconda3/envs/gluon/lib/python3.6/site-packages/torch/nn/modules/module.py", line 357, in __call__ result = self.forward(*input, **kwargs) File "/home/hubl/code/DetNet_pytorch/lib/model/fpn/fpn.py", line 254, in forward bbox_pred_select = torch.gather(bbox_pred_view, 1, rois_label.long().view(rois_label.size(0), 1, 1).expand(rois_label.size(0), 1, 4)) RuntimeError: invalid argument 2: Input tensor must have same size as output tensor apart from the specified dimension at /pytorch/torch/lib/THC/generic/THCTensorScatterGather.cu:29 Exception ignored in: <bound method DataLoaderIter.__del__ of <torch.utils.data.dataloader.DataLoaderIter object at 0x7ff67f0827f0>> Traceback (most recent call last): File "/home/hubl/anaconda3/envs/gluon/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 333, in __del__ File "/home/hubl/anaconda3/envs/gluon/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 319, in _shutdown_workers File "/home/hubl/anaconda3/envs/gluon/lib/python3.6/multiprocessing/queues.py", line 337, in get ImportError: sys.meta_path is None, Python is likely shutting down
Thanks for you code.Can you help me?

hello, when i train the pascal_voc_0712, this problem comes：
cuda runtime error (38) : no CUDA-capable device is detected at /pytorch/torch/lib/THC/THCGeneral.c:70
could you tell me why? I don't sure if i need reinstall the graphics driver.thanks a lot.
And my cuda version is 8.0, pytorch 0.3.0,graphics driver 384