jd730 / oicr-pytorch Goto Github PK

In my training process, I use the run.sh as below:

CUDA_VISIBLE_DEVICES=2  python trainval_net_org.py --dataset pascal_voc --net vgg16 \
   --bs 2 --nw 8 --save_dir=results/test_single_9  \
   --lr 0.001 --cuda --disp_interval 100 --vis \
	--checkpoint_interval=5000 --model='oicr' --threshold=0.1

CUDA_VISIBLE_DEVICES=2 python test_oicr.py --dataset pascal_voc --net vgg16  --checkpoint 070000 --load_dir=results/test_single_9 --cuda --output_dir="test" --model="oicr" --vis

the GPU is TiTan V, pytroch version is 0.4.0
But I get the AP result like this :

I haven't found the reason yet.

when I run trainval_net.py,It has a problem as shown in the figure above.

Hi,

I'm trying to compile the lib. I have already installed pytorch==0.4.0, and all other required packages. I'm using conda virtual environment and using "module load cuda-toolkit-9.0 cudnn-7.0.5 gcc-5.5.0" to load corresponding cuda and gcc. However I got the error as:

: /zf18/zy3cx/OICR-pytorch/lib ; sh make.sh
running build_ext
skipping 'model/utils/bbox.c' Cython extension (up-to-date)
skipping 'pycocotools/_mask.c' Cython extension (up-to-date)
Compiling nms kernels by nvcc...
Including CUDA code.
/net/zf18/zy3cx/OICR-pytorch/lib/model/nms
['/net/zf18/zy3cx/OICR-pytorch/lib/model/nms/src/nms_cuda_kernel.cu.o']
generating /tmp/tmpel2zqnk8/_nms.c
setting the current directory to '/tmp/tmpel2zqnk8'
running build_ext
building '_nms' extension
creating net
creating net/zf18
creating net/zf18/zy3cx
creating net/zf18/zy3cx/OICR-pytorch
creating net/zf18/zy3cx/OICR-pytorch/lib
creating net/zf18/zy3cx/OICR-pytorch/lib/model
creating net/zf18/zy3cx/OICR-pytorch/lib/model/nms
creating net/zf18/zy3cx/OICR-pytorch/lib/model/nms/src
/sw/centos/gcc/5.5.0/bin/gcc -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/zf18/zy3cx/ENTER/envs/py3pt0.3/include/python3.6m -c _nms.c -o ./_nms.o
In file included from /zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THC.h:4:0,
from _nms.c:570:
/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THCGeneral.h:12:18: fatal error: cuda.h: No such file or directory
compilation terminated.
Traceback (most recent call last):
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/unixccompiler.py", line 118, in _compile
extra_postargs)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 533, in build_extension
depends=ext.depends)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/ccompiler.py", line 574, in compile
self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/unixccompiler.py", line 120, in _compile
raise CompileError(msg)
distutils.errors.CompileError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "build.py", line 37, in
ffi.build()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 184, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 108, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/api.py", line 727, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/recompiler.py", line 1565, in recompile
compiler_verbose, debug)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.VerificationError: CompileError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1
Compiling roi pooling kernels by nvcc...
/net/zf18/zy3cx/OICR-pytorch/lib/model/roi_pooling
Including CUDA code.
generating /tmp/tmp2ownhn6a/_roi_pooling.c
setting the current directory to '/tmp/tmp2ownhn6a'
running build_ext
building '_roi_pooling' extension
creating net
creating net/zf18
creating net/zf18/zy3cx
creating net/zf18/zy3cx/OICR-pytorch
creating net/zf18/zy3cx/OICR-pytorch/lib
creating net/zf18/zy3cx/OICR-pytorch/lib/model
creating net/zf18/zy3cx/OICR-pytorch/lib/model/roi_pooling
creating net/zf18/zy3cx/OICR-pytorch/lib/model/roi_pooling/src
/sw/centos/gcc/5.5.0/bin/gcc -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/zf18/zy3cx/ENTER/envs/py3pt0.3/include/python3.6m -c _roi_pooling.c -o ./_roi_pooling.o
In file included from /zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THC.h:4:0,
from _roi_pooling.c:570:
/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THCGeneral.h:12:18: fatal error: cuda.h: No such file or directory
compilation terminated.
Traceback (most recent call last):
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/unixccompiler.py", line 118, in _compile
extra_postargs)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 533, in build_extension
depends=ext.depends)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/ccompiler.py", line 574, in compile
self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/unixccompiler.py", line 120, in _compile
raise CompileError(msg)
distutils.errors.CompileError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "build.py", line 36, in
ffi.build()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 184, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 108, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/api.py", line 727, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/recompiler.py", line 1565, in recompile
compiler_verbose, debug)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.VerificationError: CompileError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1
Compiling roi align kernels by nvcc...
/net/zf18/zy3cx/OICR-pytorch/lib/model/roi_align
Including CUDA code.
generating /tmp/tmpts8wp1dm/_roi_align.c
setting the current directory to '/tmp/tmpts8wp1dm'
running build_ext
building '_roi_align' extension
creating net
creating net/zf18
creating net/zf18/zy3cx
creating net/zf18/zy3cx/OICR-pytorch
creating net/zf18/zy3cx/OICR-pytorch/lib
creating net/zf18/zy3cx/OICR-pytorch/lib/model
creating net/zf18/zy3cx/OICR-pytorch/lib/model/roi_align
creating net/zf18/zy3cx/OICR-pytorch/lib/model/roi_align/src
/sw/centos/gcc/5.5.0/bin/gcc -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/zf18/zy3cx/ENTER/envs/py3pt0.3/include/python3.6m -c _roi_align.c -o ./_roi_align.o
In file included from /zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THC.h:4:0,
from _roi_align.c:570:
/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THCGeneral.h:12:18: fatal error: cuda.h: No such file or directory
compilation terminated.
Traceback (most recent call last):
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/unixccompiler.py", line 118, in _compile
extra_postargs)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 533, in build_extension
depends=ext.depends)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/ccompiler.py", line 574, in compile
self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/unixccompiler.py", line 120, in _compile
raise CompileError(msg)
distutils.errors.CompileError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "build.py", line 38, in
ffi.build()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 184, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 108, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/api.py", line 727, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/recompiler.py", line 1565, in recompile
compiler_verbose, debug)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.VerificationError: CompileError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1
Compiling roi crop kernels by nvcc...
Including CUDA code.
/net/zf18/zy3cx/OICR-pytorch/lib/model/roi_crop
generating /tmp/tmpzgp95at6/_roi_crop.c
setting the current directory to '/tmp/tmpzgp95at6'
running build_ext
building '_roi_crop' extension
creating net
creating net/zf18
creating net/zf18/zy3cx
creating net/zf18/zy3cx/OICR-pytorch
creating net/zf18/zy3cx/OICR-pytorch/lib
creating net/zf18/zy3cx/OICR-pytorch/lib/model
creating net/zf18/zy3cx/OICR-pytorch/lib/model/roi_crop
creating net/zf18/zy3cx/OICR-pytorch/lib/model/roi_crop/src
/sw/centos/gcc/5.5.0/bin/gcc -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -std=c99 -fPIC -DWITH_CUDA -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/zf18/zy3cx/ENTER/envs/py3pt0.3/include/python3.6m -c _roi_crop.c -o ./_roi_crop.o
In file included from /zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THC.h:4:0,
from _roi_crop.c:570:
/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC/THCGeneral.h:12:18: fatal error: cuda.h: No such file or directory
compilation terminated.
Traceback (most recent call last):
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/unixccompiler.py", line 118, in _compile
extra_postargs)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 339, in run
self.build_extensions()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 448, in build_extensions
self._build_extensions_serial()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 473, in _build_extensions_serial
self.build_extension(ext)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/command/build_ext.py", line 533, in build_extension
depends=ext.depends)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/ccompiler.py", line 574, in compile
self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/distutils/unixccompiler.py", line 120, in _compile
raise CompileError(msg)
distutils.errors.CompileError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "build.py", line 36, in
ffi.build()
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 184, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 108, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/api.py", line 727, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/recompiler.py", line 1565, in recompile
compiler_verbose, debug)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/zf18/zy3cx/ENTER/envs/py3pt0.3/lib/python3.6/site-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.VerificationError: CompileError: command '/sw/centos/gcc/5.5.0/bin/gcc' failed with exit status 1

I'm not sure how to fix it. Could you help me with it? Is it necessary to compile these libraries? Thanks!

Ziyan

My result of map is 0.2356，dataset is VOC2007，I didn't change the code，this is why？help.
sofa ap: 0.12975247981011617
cat ap: 0.01879150012978754
pottedplant ap: 0.20625525393691832
train ap: 0.5004305709273787
aeroplane ap: 0.2474352381104394
dog ap: 0.0289142347889386
bicycle ap: 0.3126646265085514
tvmonitor ap: 0.5629137748687733
person ap: 0.02026650342161751
car ap: 0.44308816282035074
sheep ap: 0.32254964068156194
bus ap: 0.5162746762903689
bird ap: 0.13202707092855498
motorbike ap: 0.5910886389691948
bottle ap: 0.05152223720911757
horse ap: 0.05455088120480837
cow ap: 0.2397996902710858
diningtable ap: 0.004031905442788624
boat ap: 0.14813410699849647
chair ap: 0.18177460452319866
I guess I have the same problem with @fregulationn.

hi bor ,thank you for sharing your code!
when i read your code,i have a question:
on line 124 of the /OICR-pytorch/lib/model/oicr/oicr.py , according to the paper, "self.ic_prob" should denote the proposal score matrices, but in your code, it seem like denote the classification score matrices. I don’t understand it,hope for your reply

Hi,
thanks for sharing your OICR implementation. I have some code issues about the flip test.

Hello, sorry to disturb you.I replaced the data of voc2007 with my own data, and the following problems occurred.

Traceback (most recent call last):
File "trainval_net.py", line 418, in
data = next(data_iter)
File "trainval_net.py", line 382, in cycle
for x in it :
File "/home/summer/anaconda3/envs/oicr/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 286, in next
return self._process_next_batch(batch)
File "/home/summer/anaconda3/envs/oicr/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 307, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
ValueError: Traceback (most recent call last):
File "/home/summer/anaconda3/envs/oicr/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/summer/anaconda3/envs/oicr/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 57, in
samples = collate_fn([dataset[i] for i in batch_indices])
File "/home/summer/zkdcd/OICR-pytorch-master/lib/roi_data_layer/roibatchLoader.py", line 44, in getitem
blobs = get_minibatch(minibatch_db, self._num_classes)
File "/home/summer/zkdcd/OICR-pytorch-master/lib/roi_data_layer/minibatch.py", line 58, in get_minibatch
labels_blob = np.vstack((labels_blob, labels))
File "<array_function internals>", line 6, in vstack
File "/home/summer/anaconda3/envs/oicr/lib/python3.6/site-packages/numpy/core/shape_base.py", line 283, in vstack
return _nx.concatenate(arrs, 0)
File "<array_function internals>", line 6, in concatenate
ValueError: all the input array dimensions for the concatenation axis must match exactly, but along dimension 1, the array at index 0 has size 20 and the array at index 1 has size 10

It should be because the categories are not uniform. My data category is 10 categories. But I have been looking for a reason for a long time. No place to modify the category was found. Can you give some suggestions for modification.
Thank you.

Thank you for the work of the reimplementation.

I have tried to run the code on pascal voc 2007, however got a much lower mAP 36.27 that reported.

AP list:
AP for aeroplane = 0.5698
AP for bicycle = 0.5532
AP for bird = 0.2643
AP for boat = 0.1777
AP for bottle = 0.1356
AP for bus = 0.5892
AP for car = 0.5607
AP for cat = 0.3745
AP for chair = 0.2180
AP for cow = 0.3692
AP for diningtable = 0.3320
AP for dog = 0.2192
AP for horse = 0.2363
AP for motorbike = 0.5885
AP for person = 0.1010
AP for pottedplant = 0.2027
AP for sheep = 0.3001
AP for sofa = 0.4573
AP for train = 0.4927
AP for tvmonitor = 0.5130
Mean AP = 0.3627

The script I use is:
CUDA_VISIBLE_DEVICES=0,1,2,3 python3 trainval_net.py --dataset pascal_voc \ --net vgg16 --bs 8 --nw 12 --save_dir 'results/voc_multi_train_ilabel_full' \ --lr 0.001 --epochs 7 --lr_decay_step 4 \ --cuda --disp_interval 50 \ --vis --mGPUs --checkpoint_interval 1750 \ --model 'oicr' --threshold 0.1

I changed the lr-decay iteration from 4e4 to dynamically lr_decay_step * iterations_per_epoch in trainval_net.py.

Thank you for the help in advance.

I write a OCIR with Pytorch 1.2, recent days. Batch size of 1 is set in my implementation. It works well with ROI Pool, but it just get about 18 mAP with ROI Align. I am just wondering ROI Align works well in your OICR implementation with batch size of 2?

When I use default setting, all is ok.
But when I force to use nms_cpu, the mAP is about 37 with the same detections.pkl files.

(OICR) mickey@a208-System-Product-Name:~/OICR-pytorch$ CUDA_VISIBLE_DEVICES=0 python3 trainval_net.py
Called with args:
Namespace(batch_size=2, checkpoint=-1, checkpoint_interval=500, class_agnostic=False, cuda=False, dataset='pascal_voc', disp_interval=50, large_scale=False, load_dir=None, lr=0.001, lr_decay_gamma=0.1, lr_decay_step=5, mGPUs=False, max_epochs=20, model='oicr', net='vgg16', num_workers=4, optimizer='sgd', save_dir='output', session=1, start_epoch=1, threshold=0.01, use_tb=False, vis=False)
/home/mickey/OICR-pytorch/lib/model/utils/config.py:392: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
yaml_cfg = edict(yaml.load(f))
Using config:
{'ANCHOR_RATIOS': [0.5, 1, 2],
'ANCHOR_SCALES': [8, 16, 32],
'CROP_RESIZE_WITH_MAX_POOL': False,
'CUDA': False,
'DATA_DIR': '/home/mickey/OICR-pytorch/data',
'DEDUP_BOXES': 0.125,
'EPS': 1e-14,
'EXP_DIR': 'vgg16',
'FEAT_STRIDE': [16],
'GPU_ID': 0,
'MATLAB': 'matlab',
'MAX_NUM_GT_BOXES': 20,
'MOBILENET': {'DEPTH_MULTIPLIER': 1.0,
'FIXED_LAYERS': 5,
'REGU_DEPTH': False,
'WEIGHT_DECAY': 4e-05},
'PIXEL_MEANS': array([[[102.9801, 115.9465, 122.7717]]]),
'POOLING_MODE': 'align',
'POOLING_SIZE': 7,
'RESNET': {'FIXED_BLOCKS': 1, 'MAX_POOL': False},
'RNG_SEED': 2,
'ROOT_DIR': '/home/mickey/OICR-pytorch',
'TEST': {'BBOX_REG': True,
'HAS_RPN': True,
'MAX_SIZE': 2000,
'MODE': 'nms',
'NMS': 0.3,
'PROPOSAL_METHOD': 'gt',
'RPN_MIN_SIZE': 16,
'RPN_NMS_THRESH': 0.7,
'RPN_POST_NMS_TOP_N': 300,
'RPN_PRE_NMS_TOP_N': 6000,
'RPN_TOP_N': 5000,
'SCALES': [480, 576, 688, 864, 1200],
'SVM': False,
'USE_FLIPPED': True},
'TRAIN': {'ASPECT_GROUPING': False,
'BATCH_SIZE': 256,
'BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'BBOX_NORMALIZE_MEANS': [0.0, 0.0, 0.0, 0.0],
'BBOX_NORMALIZE_STDS': [0.1, 0.1, 0.2, 0.2],
'BBOX_NORMALIZE_TARGETS': True,
'BBOX_NORMALIZE_TARGETS_PRECOMPUTED': True,
'BBOX_REG': True,
'BBOX_THRESH': 0.5,
'BG_THRESH_HI': 0.5,
'BG_THRESH_LO': 0.0,
'BIAS_DECAY': False,
'BN_TRAIN': False,
'DISPLAY': 10,
'DOUBLE_BIAS': True,
'FG_FRACTION': 0.25,
'FG_THRESH': 0.5,
'GAMMA': 0.1,
'HAS_RPN': True,
'IMS_PER_BATCH': 2,
'LEARNING_RATE': 0.01,
'MAX_IMAGE_SIZE': 2000,
'MAX_ROIS_SIZE': 6000,
'MAX_SIZE': 2000,
'MOMENTUM': 0.9,
'PROPOSAL_LIMIT': 2000,
'PROPOSAL_METHOD': 'gt',
'RPN_BATCHSIZE': 256,
'RPN_BBOX_INSIDE_WEIGHTS': [1.0, 1.0, 1.0, 1.0],
'RPN_CLOBBER_POSITIVES': False,
'RPN_FG_FRACTION': 0.5,
'RPN_MIN_SIZE': 8,
'RPN_NEGATIVE_OVERLAP': 0.3,
'RPN_NMS_THRESH': 0.7,
'RPN_POSITIVE_OVERLAP': 0.7,
'RPN_POSITIVE_WEIGHT': -1.0,
'RPN_POST_NMS_TOP_N': 2000,
'RPN_PRE_NMS_TOP_N': 12000,
'SCALES': [480, 576, 688, 864, 1200],
'SNAPSHOT_ITERS': 5000,
'SNAPSHOT_KEPT': 3,
'SNAPSHOT_PREFIX': 'res101_faster_rcnn',
'STEPSIZE': [40000],
'SUMMARY_INTERVAL': 180,
'TRIM_HEIGHT': 600,
'TRIM_WIDTH': 600,
'TRUNCATED': False,
'USE_ALL_GT': True,
'USE_FLIPPED': True,
'USE_GT': False,
'USE_SEG': True,
'WEIGHT_DECAY': 0.0005},
'USE_GPU_NMS': True}
WARNING: You have a CUDA device, so you should probably run with --cuda
gt
Loaded dataset voc_2007_trainval for training
Set proposal method: gt
Appending horizontally-flipped training examples...
wrote gt roidb to /home/mickey/OICR-pytorch/data/cache/voc_2007_trainval_gt_roidb.pkl
Traceback (most recent call last):
File "trainval_net.py", line 231, in
imdb, roidb, ratio_list, ratio_index = combined_roidb(args.imdb_name)
File "/home/mickey/OICR-pytorch/lib/roi_data_layer/roidb.py", line 100, in combined_roidb
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "/home/mickey/OICR-pytorch/lib/roi_data_layer/roidb.py", line 100, in
roidbs = [get_roidb(s) for s in imdb_names.split('+')]
File "/home/mickey/OICR-pytorch/lib/roi_data_layer/roidb.py", line 97, in get_roidb
roidb = get_training_roidb(imdb)
File "/home/mickey/OICR-pytorch/lib/roi_data_layer/roidb.py", line 82, in get_training_roidb
imdb.append_flipped_images()
File "/home/mickey/OICR-pytorch/lib/datasets/imdb.py", line 117, in append_flipped_images
boxes = self.roidb[i]['boxes'].copy()
KeyError: 'boxes'

root@ceeb91162089:/test/code/oicr/OICR-pytorch# ./run.sh
Traceback (most recent call last):
File "trainval_net.py", line 28, in
from roi_data_layer.roidb import combined_roidb
File "/test/code/oicr/OICR-pytorch/lib/roi_data_layer/roidb.py", line 15, in
import model.utils.cython_bbox
ModuleNotFoundError: No module named 'model.utils.cython_bbox'

selective_search
Loaded dataset voc_2007_trainval for training
Set proposal method: selective_search
Preparing training data...
voc_2007_trainval ss roidb loaded from /test/data/PASCAL/data/cache/voc_2007_trainval_selective_search_roidb.pkl
done
before filtering, there are 5011 images...
after filtering, there are 5011 images...
voc_2007_trainval ss roidb loaded from /test/data/PASCAL/data/cache/voc_2007_trainval_selective_search_roidb.pkl
5236 71
5011 roidb entries
results/test_single/log/log.txt file already exists
results/test_single/log/log_6.txt
results/test_single/log/progress.csv file already exists
Logging to results/test_single/log
oicr
Loading pretrained weights from data/pretrained_model/vgg16_caffe.pth
Learning rate 0.001
cudaCheckError() failed : no kernel image is available for execution on the device

I'm a beginner. I want to ask what the function of this function is.、
camp.py
Thank you!

Traceback (most recent call last):
File "/home/spp/OICR-pytorch/lib/model/oicr/oicr.py", line 68, in forward
nb = int(num_boxes[:,0].item())
ValueError: only one element tensors can be converted to Python scalars.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "trainval_net.py", line 423, in
rois, midn_loss, oc1, oc2, oc3, cls_prob= OICR(im_data, im_rois, labels, num_boxes)
File "/home/spp/anaconda3/envs/pytorch0.4/lib/python3.6/site-packages/torch/nn/modules/module.py", line 491, in call
result = self.forward(*input, **kwargs)
File "/home/spp/OICR-pytorch/lib/model/oicr/oicr.py", line 70, in forward
nb = int(num_boxes.item())
ValueError: only one element tensors can be converted to Python scalars.

I printed num_boxes:
tensor([[ 2185., 480., 640.],
[ 1006., 1200., 1846.]], device='cuda:0')

What should i do？

Hi author, after I see your code, I think the number of iteration per epoch is decided by the number of image. Therefore, the program will cope with 5011 images per epoch in your code.
But in that paper, that author sets 70k iterations and batch size also equal to 2. So each epoch should deal with 3500 iterations and that means each epoch should process 7000 images rather that 5011.
I do not sure whether my thinking is right...

When I run the file about OICR-pytorch-master/lib/model/nms/build.py

/usr/bin/python3.5 /home/chen/OICR-pytorch-master/lib/model/nms/build.py
Including CUDA code.
/home/chen/OICR-pytorch-master/lib/model/nms
['/home/chen/OICR-pytorch-master/lib/model/nms/src/nms_cuda_kernel.cu.o']
generating /tmp/tmpdfjv8b_w/_nms.c
setting the current directory to '/tmp/tmpdfjv8b_w'
running build_ext
building '_nms' extension
creating home
creating home/chen
creating home/chen/OICR-pytorch-master
creating home/chen/OICR-pytorch-master/lib
creating home/chen/OICR-pytorch-master/lib/model
creating home/chen/OICR-pytorch-master/lib/model/nms
creating home/chen/OICR-pytorch-master/lib/model/nms/src
x86_64-linux-gnu-gcc -pthread -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -DWITH_CUDA -I/usr/local/lib/python3.5/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python3.5/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python3.5/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python3.5m -c _nms.c -o ./_nms.o
x86_64-linux-gnu-gcc -pthread -DNDEBUG -g -fwrapv -O2 -Wall -Wstrict-prototypes -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 -fPIC -DWITH_CUDA -I/usr/local/lib/python3.5/dist-packages/torch/utils/ffi/../../lib/include -I/usr/local/lib/python3.5/dist-packages/torch/utils/ffi/../../lib/include/TH -I/usr/local/lib/python3.5/dist-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/usr/include/python3.5m -c /home/chen/OICR-pytorch-master/lib/model/nms/src/nms_cuda.c -o ./home/chen/OICR-pytorch-master/lib/model/nms/src/nms_cuda.o
x86_64-linux-gnu-gcc: error: /home/chen/OICR-pytorch-master/lib/model/nms/src/nms_cuda.c: 没有那个文件或目录
x86_64-linux-gnu-gcc: fatal error: no input files
compilation terminated.
Traceback (most recent call last):
File "/usr/lib/python3.5/distutils/unixccompiler.py", line 118, in _compile
extra_postargs)
File "/usr/lib/python3.5/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/usr/lib/python3.5/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/usr/lib/python3.5/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command 'x86_64-linux-gnu-gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/cffi/ffiplatform.py", line 51, in _build
dist.run_command('build_ext')
File "/usr/lib/python3.5/distutils/dist.py", line 974, in run_command
cmd_obj.run()
File "/usr/lib/python3.5/distutils/command/build_ext.py", line 338, in run
self.build_extensions()
File "/usr/lib/python3.5/distutils/command/build_ext.py", line 447, in build_extensions
self._build_extensions_serial()
File "/usr/lib/python3.5/distutils/command/build_ext.py", line 472, in _build_extensions_serial
self.build_extension(ext)
File "/usr/lib/python3.5/distutils/command/build_ext.py", line 532, in build_extension
depends=ext.depends)
File "/usr/lib/python3.5/distutils/ccompiler.py", line 574, in compile
self._compile(obj, src, ext, cc_args, extra_postargs, pp_opts)
File "/usr/lib/python3.5/distutils/unixccompiler.py", line 120, in _compile
raise CompileError(msg)
distutils.errors.CompileError: command 'x86_64-linux-gnu-gcc' failed with exit status 1

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/chen/OICR-pytorch-master/lib/model/nms/build.py", line 37, in
ffi.build()
File "/usr/local/lib/python3.5/dist-packages/torch/utils/ffi/init.py", line 184, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)
File "/usr/local/lib/python3.5/dist-packages/torch/utils/ffi/init.py", line 108, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)
File "/usr/local/lib/python3.5/dist-packages/cffi/api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)
File "/usr/local/lib/python3.5/dist-packages/cffi/recompiler.py", line 1520, in recompile
compiler_verbose, debug)
File "/usr/local/lib/python3.5/dist-packages/cffi/ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)
File "/usr/local/lib/python3.5/dist-packages/cffi/ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))
cffi.error.VerificationError: CompileError: command 'x86_64-linux-gnu-gcc' failed with exit status 1

Is this a missing nms_cuda.c file in the OICR-pytorch-master/lib/model/nms/src ?

Hello, I have a new question，I tried to solve it by myself, but I failed.
(OICR) mickey@a208-System-Product-Name:~/OICR-pytorch$ CUDA_VISIBLE_DEVICES=0 python3 trainval_net.py --dataset pascal_voc --net vgg16 \

--bs 2 --nw 6 --save_dir='results/test_single'
--lr 0.001 --cuda --disp_interval 50 --vis
--checkpoint_interval=500 --model='oicr' --threshold=0.1
Traceback (most recent call last):
File "trainval_net.py", line 28, in
from roi_data_layer.roidb import combined_roidb
File "/home/mickey/OICR-pytorch/lib/roi_data_layer/roidb.py", line 15, in
import model.utils.cython_bbox
ModuleNotFoundError: No module named 'model.utils.cython_bbox'

CUDA_VISIBLE_DEVICES=1,2 python3 trainval_net.py --dataset pascal_voc --net vgg16 --bs 2 --nw 4 --save_dir='output' --model='oicr' --lr 0.001 --cuda --disp_interval 50 --mGPUs --vis --checkpoint_interval=500

I ran this, but it seems that only one GPU ( GPU 1 ) been used ( without any errors or warnings )and it takes about 300s per 50 iterations. My environment is CUDA 8.0, Python 3.5 and Pytorch 0.4.0

My code stopped here for a long time,about 3 days， is this right？How much time does it take to train？

/home/yesenmao/shenjt/OICR-pytorch/lib/model/oicr/oicr.py(37)WeightedSoftmaxWithLoss()
-> loss = (labels_ic * torch.log(prob + eps))
(Pdb) > /home/yesenmao/shenjt/OICR-pytorch/lib/model/oicr/oicr.py(37)WeightedSoftmaxWithLoss()
-> loss = (labels_ic * torch.log(prob + eps))
(Pdb)

I simply run the trainval_net.py demo script (from GitHub) like so:

Traceback (most recent call last):
File "/home/OICR-pytorch/lib/model/oicr/oicr.py", line 71, in forward
nb = int(num_boxes[:,0].item())
ValueError: only one element tensors can be converted to Python scalars

During handling of the above exception, another exception occurred:

I met an Error when I ran the trainval_net.py, which said
ImportError: /OICR-pytorch/lib/model/roi_crop/_ext/roi_crop/_roi_crop.so: undefined symbol: __cudaPopCallConfiguration

I can't find evalutaion.py. I don't know how to use your code to get mAP.
Thank you

I met some build problems when I run the project. I think it is the env problem, thanks.

during my training, the midn loss is decreased but the oicr loss is rising especially for oicr1 and oicr2.
Is that reasonable?

I use a single card GPU, TITANX.training time spent four days, is this normal phenomenon? mAP is 40.2.
What adjustments should I make if I want to speed up my training or improve my mAP?
Thank you for your patient guidance.

As the readme said that
creat softlinks in the folder data/.
move selective_search_data folder into data folder.
But there is no folder named data. should I creat a folder and name it "data" ?

When using two GPUs, bs = 8 will report an error.
May I ask if the actual bs of your code can only be equal to 1 (in the forward and backward propagation)?
And I also notice this assert in assign labels.
Thanks

trainval_net.py: error: unrecognized arguments: --oicr ?

Sorry to bother you. I have the followed question.
Found GPU0 GeForce RTX 2080 Ti which requires CUDA_VERSION >= 9000 for optimal performance and fast startup time, but your PyTorch was compiled with CUDA_VERSION 8000. My Configuration is torch 0.4.0+cuda9.0+torchvision0.2.2.

Hi, I read the code roughly and found something strange about the training batch size. you set batch_size=4, but in line 26 of lib/oicr_layer/layer.py, you assert batch size equal to 1.
assert num_images == 1, 'batch size shoud be equal to 1
So, why you can set batch_size=4 with this assert?

Besides, have tried Resnet backbone? I use Res50 as backbone, but it doesn't work well, the VOC2007 AP only get 0.27.
Thanks very much!