CUDA_LAUNCH_BLOCKING=1 python train.py --name nyuv2_VGGdeeplab_depthconv --dataset_mode nyuv2 --flip --scale --crop --colorjitter --depthconv --list dataset/sunrgbd_training.lst
------------ Options -------------
batchSize: 1
beta1: 0.5
checkpoints_dir: ./checkpoints
colorjitter: True
continue_train: False
crop: True
dataroot:
dataset_mode: nyuv2
debug: False
decoder: psp_bilinear
depthconv: True
depthglobalpool: False
display_freq: 100
display_winsize: 512
encoder: resnet50_dilated8
fineSize: [480, 640]
flip: True
gpu_ids: [0]
inputmode: bgr-mean
isTrain: True
iterSize: 10
label_nc: 40
list: dataset/sunrgbd_training.lst
loadfroms: False
lr: 0.00025
lr_power: 0.9
max_dataset_size: inf
maxbatchsize: -1
model: DeeplabVGG
momentum: 0.9
nThreads: 1
name: nyuv2_VGGdeeplab_depthconv
nepochs: 100
no_html: False
phase: train
pretrained_model:
pretrained_model_HHA:
pretrained_model_rgb:
print_freq: 100
save_epoch_freq: 10
save_latest_freq: 1000
scale: True
serial_batches: False
tf_log: False
use_softmax: False
vallist:
verbose: False
warmup_iters: 500
wd: 0.0004
which_epoch: latest
which_epoch_HHA: latest
which_epoch_rgb: latest
-------------- End ----------------
CustomDatasetDataLoader
dataset [NYUDataset] was created
#training images = 795
model [BaseModel] was created
create web directory ./checkpoints/nyuv2_VGGdeeplab_depthconv/web...
/home/cgl/miniconda3/envs/torch0.40/lib/python3.6/site-packages/torch/nn/functional.py:1749: 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))
/home/cgl/code/Git/DepthAwareCNN/models/Deeplab.py:106: UserWarning: invalid index of a 0-dim tensor. This will be an error in PyTorch 0.5. Use tensor.item() to convert a 0-dim tensor to a Python number
self.averageloss += [self.loss.data[0]]
error in depthconv_col2im: an illegal memory access was encountered
THCudaCheck FAIL file=/pytorch/aten/src/THC/generic/THCTensorMath.cu line=26 error=77 : an illegal memory access was encountered
Traceback (most recent call last):
File "train.py", line 55, in
model.backward(total_steps, opt.nepochs * dataset.len() * opt.batchSize + 1)
File "/home/cgl/code/Git/DepthAwareCNN/models/Deeplab.py", line 112, in backward
self.loss.backward()
File "/home/cgl/miniconda3/envs/torch0.40/lib/python3.6/site-packages/torch/tensor.py", line 93, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/cgl/miniconda3/envs/torch0.40/lib/python3.6/site-packages/torch/autograd/init.py", line 89, in backward
allow_unreachable=True) # allow_unreachable flag
File "/home/cgl/code/Git/DepthAwareCNN/models/ops/depthconv/functions/depthconv.py", line 91, in backward
grad_weight = weight.new(*weight.size()).zero_()
RuntimeError: cuda runtime error (77) : an illegal memory access was encountered at /pytorch/aten/src/THC/generic/THCTensorMath.cu:26

Hi. You reported the best performance with \alpha set to 8.3. My question is how to set the \alpha coefficient in Depth Similarity Function? I didn't find the corresponding code in your repo.

Thanks for your code sharing.
In my data preprocessing with NYU-v2, the number of class of NYU-v2 is 41 containing background.
But your code is scripted 40 class. Is this model does not contain background class?

@laughtervv I use the model you upload 4 days ago, and the val
result color is different from the lable, they can't match.


the first picture is gt, and the second is the pred
I just make the label [ label > 39 ] = 0,
I don't know the method is right or not, could you help me

Hello,
thanks a lot for sharing code. Could you provide methods that allow us to prepare datasets to run learning (lst and hha files)?
This will make it easier to reproduce the results. Thank you in advance.
Best regards.

Hi, when I try to run train.py, this import error occurs. Any clue why this happens? Thank you.

depth = np.bitwise_or(np.right_shift(depth,3),np.left_shift(depth,16-3))
I am currently reproducing this paper, so I am studying the author's implementation method. I can't understand this code in sunrgbd_dataset.py. Could someone please give me some help?

I want to compile the package from scratch but got some problems.

@laughtervv Hello, I am trying to run the DepthAwareCNN code, when I write run the following command on
python train.py --name nyuv2_VGGdeeplab_depthconv --dataset_mode nyuv2 --flip --scale --crop --colorjitter --depthconv --list ./lists/train.lst --vallist ./lists/val.lst --continue_train
yet the following error popped out:

I tried to search on the Internet yet nothing valuable were acquired.
What is the meaning of the following line:
from .Deeplab import Deeplab_Solver
and why using . before Deeplab.

RuntimeError: cuda runtime error (77) : an illegal memory access was encountered at /pytorch/aten/src/THC/generic/THCTensorCopy.c:20

RT, when training

User crmauceri's rewriting of this repo provides a more up-to date version of this paper's code that is compatible with the rewriting of PyTorch's extension interface with versions >1.0.0

I trained the network with the pre-trained weights in deeplab, but got poor results(mAcc 48, mIoU 35). Any different training strategy for model initialized with pre-trained weights?

Due to the mismatch of each input size, 4ad69f7 does not support training with BatchSize > 1.

When trying to compile C extension in depthconv Folder, I got error( VerificationError: CompileError: command 'C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe' failed with exit status 2), and tried all the methods mentioned, but all can't fix it. Is there anyone know how to fix it?
OS: Windows 10
PyTorch version: 0.4.1
How you installed PyTorch (conda, pip, source): conda
Python version: Python 3.5.6 |Anaconda, Inc.| (default, Aug 26 2018, 16:05:27) [MSC v.1900 64 bit (AMD64)] on win32
CUDA/cuDNN version: CUDA-9.0
GPU models and configuration: VS 2015

generating C:\Users\liyang\AppData\Local\Temp\tmp65k1yok8_my_lib.c
setting the current directory to 'C:\Users\liyang\AppData\Local\Temp\tmp65k1yok8'
running build_ext
building '_my_lib' extension
creating Release
creating Release\models
creating Release\models\ops
creating Release\models\ops\learn
creating Release\models\ops\learn\11
creating Release\models\ops\learn\11\src
C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe /c /nologo /Ox /W3 /GL /DNDEBUG /MD -IC:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\torch\utils\ffi....\lib\include -IC:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\torch\utils\ffi....\lib\include\TH -IC:\Users\liyang\Anaconda3\pkgs\pytorch-cpu-0.4.1-py35_cpuhe774522_1\Lib\site-packages\torch\lib\include -IC:\Users\liyang\Anaconda3\envs\pytorch41\include -IC:\Users\liyang\Anaconda3\envs\pytorch41\include "-IC:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\INCLUDE" "-IC:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\ATLMFC\INCLUDE" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.10240.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.6.1\include\um" "-IC:\Program Files (x86)\Windows Kits\8.1\include\shared" "-IC:\Program Files (x86)\Windows Kits\8.1\include\um" "-IC:\Program Files (x86)\Windows Kits\8.1\include\winrt" /Tc_my_lib.c /Fo.\Release_my_lib.obj -std=c99
C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe /c /nologo /Ox /W3 /GL /DNDEBUG /MD -IC:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\torch\utils\ffi....\lib\include -IC:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\torch\utils\ffi....\lib\include\TH -IC:\Users\liyang\Anaconda3\pkgs\pytorch-cpu-0.4.1-py35_cpuhe774522_1\Lib\site-packages\torch\lib\include -IC:\Users\liyang\Anaconda3\envs\pytorch41\include -IC:\Users\liyang\Anaconda3\envs\pytorch41\include "-IC:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\INCLUDE" "-IC:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\ATLMFC\INCLUDE" "-IC:\Program Files (x86)\Windows Kits\10\include\10.0.10240.0\ucrt" "-IC:\Program Files (x86)\Windows Kits\NETFXSDK\4.6.1\include\um" "-IC:\Program Files (x86)\Windows Kits\8.1\include\shared" "-IC:\Program Files (x86)\Windows Kits\8.1\include\um" "-IC:\Program Files (x86)\Windows Kits\8.1\include\winrt" /EHsc /TpI:\D435\DepthCNN\models\ops\learn\11\src\my_lib.cpp /Fo.\Release\D435\DepthCNN\models\ops\learn\11\src\my_lib.obj -std=c99
Traceback (most recent call last):

File "C:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 668, in runfile
execfile(filename, namespace)

File "C:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\spyder_kernels\customize\spydercustomize.py", line 108, in execfile
exec(compile(f.read(), filename, 'exec'), namespace)

File "I:/models/ops/learn/11/build.py", line 38, in
ffi.build()

File "C:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\torch\utils\ffi_init_.py", line 189, in build
_build_extension(ffi, cffi_wrapper_name, target_dir, verbose)

File "C:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\torch\utils\ffi_init_.py", line 111, in _build_extension
outfile = ffi.compile(tmpdir=tmpdir, verbose=verbose, target=libname)

File "C:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\cffi\api.py", line 697, in compile
compiler_verbose=verbose, debug=debug, **kwds)

File "C:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\cffi\recompiler.py", line 1520, in recompile
compiler_verbose, debug)

File "C:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\cffi\ffiplatform.py", line 22, in compile
outputfilename = _build(tmpdir, ext, compiler_verbose, debug)

File "C:\Users\liyang\Anaconda3\envs\pytorch41\lib\site-packages\cffi\ffiplatform.py", line 58, in _build
raise VerificationError('%s: %s' % (e.class.name, e))

VerificationError: CompileError: command 'C:\Program Files (x86)\Microsoft Visual Studio 14.0\VC\BIN\x86_amd64\cl.exe' failed with exit status 2

ostyk@pytorch:~/DepthAwareCNN/models/ops/depthconv$ sh make.sh 
Traceback (most recent call last):
  File "build.py", line 3, in <module>
    from torch.utils.ffi import create_extension
  File "/home/ostyk/.local/lib/python3.5/site-packages/torch/utils/ffi/__init__.py", line 1, in <module>
    raise ImportError("torch.utils.ffi is deprecated. Please use cpp extensions instead.")
ImportError: torch.utils.ffi is deprecated. Please use cpp extensions instead.

Which torch version have you used? I'm not sure that fixing deprecated functions line by line is a very safe thing to do. Will be grateful for any tips. Thanks in advance.

@laughtervv Hello, I am trying to run the DepthAwareCNN code and I can not find dataset/lists/nyuv2/train.lst and dataset/lists/nyuv2/val.lst, Could you tell me where to find them? Thanks!

If you can help me, I would really appreciate it. My mail address is: [email protected]

Could you also share a pre-trained model (trained on e.g. NYUv2)?

Can you provide the processed nyuv2 dataset?Thank you very much!

File "train.py", line 54, in
model.forward(data)
File "/home/aaronsung/pyTorch/DepthAwareCNN-master/models/Deeplab.py", line 94, in forward
self.segpred = self.model(self.image,self.depth)
File "/home/aaronsung/.conda/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/aaronsung/pyTorch/DepthAwareCNN-master/models/Deeplab.py", line 23, in forward
output = self.Scale(x,depth) # for original scale
File "/home/aaronsung/.conda/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/aaronsung/pyTorch/DepthAwareCNN-master/models/VGG_Deeplab.py", line 430, in forward
x,depth = self.features(x,depth)
File "/home/aaronsung/.conda/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/aaronsung/pyTorch/DepthAwareCNN-master/models/VGG_Deeplab.py", line 228, in forward
x = self.conv1_1(x,self.conv1_1_depthconvweight * depth)
File "/home/aaronsung/.conda/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/aaronsung/pyTorch/DepthAwareCNN-master/models/VGG_Deeplab.py", line 77, in forward
x = module(x,depth)
File "/home/aaronsung/.conda/envs/pytorch/lib/python3.6/site-packages/torch/nn/modules/module.py", line 477, in call
result = self.forward(*input, **kwargs)
File "/home/aaronsung/pyTorch/DepthAwareCNN-master/models/ops/depthconv/modules/depthconv.py", line 48, in forward
self.padding, self.dilation)
File "/home/aaronsung/pyTorch/DepthAwareCNN-master/models/ops/depthconv/functions/depthconv.py", line 25, in depth_conv
return f(input, depth, weight, bias)
File "/home/aaronsung/pyTorch/DepthAwareCNN-master/models/ops/depthconv/functions/depthconv.py", line 65, in forward
self.padding[1], self.padding[0], self.dilation[1], self.dilation[0])
File "/home/aaronsung/.conda/envs/pytorch/lib/python3.6/site-packages/torch/utils/ffi/init.py", line 202, in safe_call
result = torch._C._safe_call(*args, **kwargs)
torch.FatalError: invalid argument 5: 4D weight tensor (nOutputPlane,nInputPlane,kH,kW) expected, but got: (null) at /home/aaronsung/pyTorch/DepthAwareCNN-master/models/ops/depthconv/src/depthconv_cuda.c:15

pytorch=0.4.1,CUDA=10.0,ubuntu=18.04
How could I slove it?

Sorry for always opening up issues here..
I tried looking around online, and I think the illegal memory access might have to do with the dataset that I'm using?(SUNRGBD dataset)
I can't think of any other reason for this error so would be much appreciated if you could help.

CustomDatasetDataLoader
dataset [sunrgbd_dataset] was created
#training images = 5285
model [BaseModel] was created
create web directory ./checkpoints/test_depthconv/web...
error in depthconv_col2im: an illegal memory access was encountered
THCudaCheck FAIL file=/opt/conda/conda-bld/pytorch_1513368888240/work/torch/lib/THC/generic/THCTensorMath.cu line=26 error=77 : an illegal memory access was encountered
Traceback (most recent call last):
File "train.py", line 55, in
model.backward(total_steps, opt.nepochs * dataset.len() * opt.batchSize + 1)
File "/disks/local/Documents/DepthAwareCNN-master/models/Deeplab.py", line 107, in backward
self.loss.backward()
File "/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/autograd/variable.py", line 167, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, retain_variables)
File "/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/autograd/init.py", line 99, in backward
variables, grad_variables, retain_graph)
File "/disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/functions/depthconv.py", line 91, in backward
grad_weight = weight.new(*weight.size()).zero_()
RuntimeError: cuda runtime error (77) : an illegal memory access was encountered at /opt/conda/conda-bld/pytorch_1513368888240/work/torch/lib/THC/generic/THCTensorMath.cu:26

When I tried running it again today, the error no longer appeared(did not change anything with the code..)

I`m a student, now i run the code, when i run train.sh. I got some error:

Traceback (most recent call last):
File "train.py", line 33, in
data_loader = CreateDataLoader(opt)
File "/home/fattyhu/catkin_ws/DepthAwareCNN-master/data/data_loader.py", line 6, in CreateDataLoader
data_loader.initialize(opt)
File "/home/fattyhu/catkin_ws/DepthAwareCNN-master/data/custom_dataset_data_loader.py", line 51, in initialize
self.dataset, self.dataset_val = CreateDataset(opt)
File "/home/fattyhu/catkin_ws/DepthAwareCNN-master/data/custom_dataset_data_loader.py", line 40, in CreateDataset
dataset.initialize(opt)
File "/home/fattyhu/catkin_ws/DepthAwareCNN-master/data/nyuv2_dataset_crop.py", line 38, in initialize
self.paths_dict = make_dataset_fromlst(opt.list)
File "/home/fattyhu/catkin_ws/DepthAwareCNN-master/data/nyuv2_dataset_crop.py", line 23, in make_dataset_fromlst
with open(listfilename) as f:
FileNotFoundError: [Errno 2] No such file or directory: './lists/train.lst'

how can i prepare the lst file?

Hello,

I want to try your 'depthconv' model however there seems to be missing object file to do make.
I have gotten this error message : gcc: error: /home/shgold/Documents/DepthAwareCNN/models/ops/depthconv/src/depthconv_cuda_kernel.cu.o: No such file or directory

There is missing file of 'depthconv_cuda_kernel.cu.o'. Could you help to fix this problem?
Thanks.

I think this is very important to make best result in NYU v2 test dataset?thank you very mach!

Implementation needed in case that encoder != 'VGG':

Hi, I tried running sh make.sh to build the depth conv operation but I got the following error..
Is it because I keep the depthconv folder in the HDD disk and not the local disk??

If so, how do I modify the make.sh file?

(UPDATE: even if I move the depthconv folder to the local disk, it's still not working..)

~/HDD/Documents/DepthAwareCNN-master/models/ops/depthconv$ sh make.sh
nvcc fatal : Value 'sm_60' is not defined for option 'gpu-architecture'
Including CUDA code.
/disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv
generating /tmp/tmpbhq1tqzn/_depthconv.c
setting the current directory to '/tmp/tmpbhq1tqzn'
running build_ext
building '_depthconv' extension
creating disks
creating disks/local
creating disks/local/Documents
creating disks/local/Documents/DepthAwareCNN-master
creating disks/local/Documents/DepthAwareCNN-master/models
creating disks/local/Documents/DepthAwareCNN-master/models/ops
creating disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv
creating disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src
g++ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/home/muser/.pyenv/versions/anaconda3-5.0.1/include/python3.6m -c _depthconv.c -o ./_depthconv.o
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
g++ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/home/muser/.pyenv/versions/anaconda3-5.0.1/include/python3.6m -c /disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src/depthconv.c -o ./disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src/depthconv.o
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
g++ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -DWITH_CUDA -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/home/muser/.pyenv/versions/anaconda3-5.0.1/include/python3.6m -c /disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src/depthconv_cuda.c -o ./disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src/depthconv_cuda.o
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
gcc -pthread -shared -B /home/muser/.pyenv/versions/anaconda3-5.0.1/compiler_compat -L/home/muser/.pyenv/versions/anaconda3-5.0.1/lib -Wl,-rpath=/home/muser/.pyenv/versions/anaconda3-5.0.1/lib -Wl,--no-as-needed -Wl,--sysroot=/ ./_depthconv.o ./disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src/depthconv.o ./disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src/depthconv_cuda.o /disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src/depthconv_cuda_kernel.cu.o -L/home/muser/.pyenv/versions/anaconda3-5.0.1/lib -lpython3.6m -o ./_depthconv.so
gcc: error: /disks/local/Documents/DepthAwareCNN-master/models/ops/depthconv/src/depthconv_cuda_kernel.cu.o: No such file or directory
Traceback (most recent call last):
File "/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/distutils/unixccompiler.py", line 197, in link
self.spawn(linker + ld_args)
File "/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/distutils/ccompiler.py", line 909, in spawn
spawn(cmd, dry_run=self.dry_run)
File "/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/distutils/spawn.py", line 36, in spawn
_spawn_posix(cmd, search_path, dry_run=dry_run)
File "/home/muser/.pyenv/versions/anaconda3-5.0.1/lib/python3.6/distutils/spawn.py", line 159, in _spawn_posix
% (cmd, exit_status))
distutils.errors.DistutilsExecError: command 'gcc' failed with exit status 1

excuse me. when l run sh make,sh ,the following problem occurred.
`
depthavgpooling_cuda_kernel.cu(42): warning: variable "divcount" was declared but never referenced
detected during instantiation of "void AvePoolForward_kernel<Dtype,Acctype>(int, const Dtype *, const Dtype *, int, int, int, int, int, int, int, int, int, int, int, Dtype *, Dtype *) [with Dtype=float, Acctype=double]"
(65): here

Including CUDA code.
/home/pyq/segmentation/DepthAwareCNN/models/ops/depthavgpooling
Traceback (most recent call last):
File "build.py", line 32, in
extra_objects=extra_objects
File "/home/public/anaconda3/lib/python3.6/site-packages/setuptools/init.py", line 147, in init
_Command.init(self, dist)
File "/home/public/anaconda3/lib/python3.6/distutils/cmd.py", line 57, in init
raise TypeError("dist must be a Distribution instance")
TypeError: dist must be a Distribution instance

`

And then I tried to lower the version of setuptool, but it appeared
AttributeError: module 'importlib._bootstrap' has no attribute 'SourceFileLoader'

Can you give me some advice?Thanks.

*how to build make.sh in pytorch1.0, when load model in c++, it needs to convert model to script.Could you give me some reference?Thanks

when I run "sh make.sh". I get the following error. some one can help me?

running build_ext
building '_depthconv' extension
creating home
creating home/siat
creating home/siat/code
creating home/siat/code/my_code
creating home/siat/code/my_code/姿态估计1_posecnn复现
creating home/siat/code/my_code/姿态估计1_posecnn复现/densefusion
creating home/siat/code/my_code/姿态估计1_posecnn复现/densefusion/DepthAwareCNN-master
creating home/siat/code/my_code/姿态估计1_posecnn复现/densefusion/DepthAwareCNN-master/models
creating home/siat/code/my_code/姿态估计1_posecnn复现/densefusion/DepthAwareCNN-master/models/ops
creating home/siat/code/my_code/姿态估计1_posecnn复现/densefusion/DepthAwareCNN-master/models/ops/depthconv
creating home/siat/code/my_code/姿态估计1_posecnn复现/densefusion/DepthAwareCNN-master/models/ops/depthconv/src
g++ -Wno-unused-result -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -m64 -fPIC -m64 -fPIC -fPIC -DWITH_CUDA -I/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include -I/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH -I/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/THC -I/usr/local/cuda/include -I/home/siat/anaconda3/include/python3.6m -c _depthconv.c -o ./_depthconv.o -std=c99
cc1plus: warning: command line option ‘-std=c99’ is valid for C/ObjC but not for C++
In file included from /usr/include/c++/5/type_traits:35:0,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:19,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Error.h:4,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Allocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THAllocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THStorage.h:4,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/TH.h:15,
from _depthconv.c:433:
/usr/include/c++/5/bits/c++0x_warning.h:32:2: error: #error This file requires compiler and library support for the ISO C++ 2011 standard. This support must be enabled with the -std=c++11 or -std=gnu++11 compiler options.
#error This file requires compiler and library support
^
In file included from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Error.h:4:0,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Allocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THAllocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THStorage.h:4,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/TH.h:15,
from depthconv.c:433:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:115:1: warning: identifier ‘constexpr’ is a keyword in C++11 [-Wc++0x-compat]
template inline constexpr T&& constexpr_forward(typename std::remove
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:115:1: warning: identifier ‘noexcept’ is a keyword in C++11 [-Wc++0x-compat]
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:122:5: warning: identifier ‘static_assert’ is a keyword in C++11 [-Wc++0x-compat]
static_assert(!std::is_lvalue_reference::value, "!!");
^
In file included from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Error.h:4:0,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Allocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THAllocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THStorage.h:4,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/TH.h:15,
from depthconv.c:433:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:549:3: warning: identifier ‘nullptr’ is a keyword in C++11 [-Wc++0x-compat]
constexpr optional() noexcept : ref(nullptr) {}
^
In file included from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Error.h:4:0,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Allocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THAllocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THStorage.h:4,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/TH.h:15,
from depthconv.c:433:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:115:27: error: ‘constexpr’ does not name a type
template inline constexpr T&& constexpr_forward(typename std::remove
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:115:27: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:120:27: error: ‘constexpr’ does not name a type
template inline constexpr T&& constexpr_forward(typename std::remove
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:120:27: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:126:27: error: ‘constexpr’ does not name a type
template inline constexpr typename std::remove_reference::type&& c
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:126:27: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:147:3: error: ‘constexpr’ does not name a type
constexpr static bool has_overload(...) { return false; }
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:147:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:149:40: error: ‘declval’ is not a member of ‘std’
template <class X, size_t S = sizeof(std::declval<X&>().operator&()) >
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:149:54: error: expected primary-expression before ‘&’ token
template <class X, size_t S = sizeof(std::declval<X&>().operator&()) >
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:149:55: error: expected primary-expression before ‘>’ token
template <class X, size_t S = sizeof(std::declval<X&>().operator&()) >
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:149:57: error: expected primary-expression before ‘)’ token
template <class X, size_t S = sizeof(std::declval<X&>().operator&()) >
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:150:3: error: ‘constexpr’ does not name a type
constexpr static bool has_overload(bool) { return true; }
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:150:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:152:3: error: ‘constexpr’ does not name a type
constexpr static bool value = has_overload(true);
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:152:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:26:51: error: ‘enable_if’ in namespace ‘std’ does not name a template type

define TR2_OPTIONAL_REQUIRES(...) typename std::enable_if<VA_ARGS::value,

                                               ^

/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:155:23: note: in expansion of macro ‘TR2_OPTIONAL_REQUIRES’
template <typename T, TR2_OPTIONAL_REQUIRES(!has_overloaded_addressof)>
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:26:60: error: expected ‘>’ before ‘<’ token

define TR2_OPTIONAL_REQUIRES(...) typename std::enable_if<VA_ARGS::value,

                                                        ^

/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:155:23: note: in expansion of macro ‘TR2_OPTIONAL_REQUIRES’
template <typename T, TR2_OPTIONAL_REQUIRES(!has_overloaded_addressof)>
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:156:1: error: ‘constexpr’ does not name a type
constexpr T* static_addressof(T& ref)
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:156:1: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:26:51: error: ‘enable_if’ in namespace ‘std’ does not name a template type

define TR2_OPTIONAL_REQUIRES(...) typename std::enable_if<VA_ARGS::value,

                                               ^

/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:161:23: note: in expansion of macro ‘TR2_OPTIONAL_REQUIRES’
template <typename T, TR2_OPTIONAL_REQUIRES(has_overloaded_addressof)>
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:26:60: error: expected ‘>’ before ‘<’ token

define TR2_OPTIONAL_REQUIRES(...) typename std::enable_if<VA_ARGS::value,

                                                        ^

/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:161:23: note: in expansion of macro ‘TR2_OPTIONAL_REQUIRES’
template <typename T, TR2_OPTIONAL_REQUIRES(has_overloaded_addressof)>
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h: In function ‘T* at::detail_::static_addressof(T&)’:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:164:10: error: ‘addressof’ is not a member of ‘std’
return std::addressof(ref);
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h: At global scope:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:170:1: error: ‘constexpr’ does not name a type
constexpr U convert(U v) { return v; }
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:170:1: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:175:1: error: ‘constexpr’ does not name a type
constexpr struct trivial_init_t{} trivial_init{};
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:175:1: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:175:35: error: ‘trivial_init’ does not name a type
constexpr struct trivial_init_t{} trivial_init{};
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:179:1: error: ‘constexpr’ does not name a type
constexpr struct in_place_t{} in_place{};
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:179:1: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:179:31: error: ‘in_place’ does not name a type
constexpr struct in_place_t{} in_place{};
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:186:3: error: ‘constexpr’ does not name a type
constexpr explicit nullopt_t(init){}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:186:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:188:1: error: ‘constexpr’ does not name a type
constexpr nullopt_t nullopt{nullopt_t::init()};
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:188:1: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h: In constructor ‘at::bad_optional_access::bad_optional_access(const string&)’:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:194:74: warning: extended initializer lists only available with -std=c++11 or -std=gnu++11
licit bad_optional_access(const std::string& what_arg) : logic_error{what_arg}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h: In constructor ‘at::bad_optional_access::bad_optional_access(const char*)’:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:195:67: warning: extended initializer lists only available with -std=c++11 or -std=gnu++11
explicit bad_optional_access(const char* what_arg) : logic_error{what_arg} {}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h: At global scope:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:205:3: error: ‘constexpr’ does not name a type
constexpr storage_t( trivial_init_t ) noexcept : dummy_() {};
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:205:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:207:18: warning: variadic templates only available with -std=c++11 or -std=gnu++11
template <class... Args>
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:208:3: error: ‘constexpr’ does not name a type
constexpr storage_t( Args&&... args ) : value_(constexpr_forward(args).
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:208:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:220:5: error: ‘constexpr’ does not name a type
constexpr constexpr_storage_t( trivial_init_t ) noexcept : dummy_() {};
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:220:5: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:222:20: warning: variadic templates only available with -std=c++11 or -std=gnu++11
template <class... Args>
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:223:5: error: ‘constexpr’ does not name a type
constexpr constexpr_storage_t( Args&&... args ) : value_(constexpr_forward<
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:223:5: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:225:30: warning: defaulted and deleted functions only available with -std=c++11 or -std=gnu++11
~constexpr_storage_t() = default;
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:235:5: error: ‘constexpr’ does not name a type
constexpr optional_base() noexcept : init_(false), storage_(trivial_init) {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:235:5: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:237:14: error: ‘constexpr’ does not name a type
explicit constexpr optional_base(const T& v) : init_(true), storage_(v) {}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:237:14: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:239:14: error: ‘constexpr’ does not name a type
explicit constexpr optional_base(T&& v) : init_(true), storage_(constexpr_m
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:239:14: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:241:20: warning: variadic templates only available with -std=c++11 or -std=gnu++11
template <class... Args> explicit optional_base(in_place_t, Args&&... args)
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:241:63: error: expected ‘)’ before ‘,’ token
template <class... Args> explicit optional_base(in_place_t, Args&&... args)
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:244:29: warning: variadic templates only available with -std=c++11 or -std=gnu++11
template <class U, class... Args, TR2_OPTIONAL_REQUIRES(std::is_constructib
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:26:51: error: ‘enable_if’ in namespace ‘std’ does not name a template type

define TR2_OPTIONAL_REQUIRES(...) typename std::enable_if<VA_ARGS::value,

                                               ^

/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:244:39: note: in expansion of macro ‘TR2_OPTIONAL_REQUIRES’
template <class U, class... Args, TR2_OPTIONAL_REQUIRES(std::is_constructib
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:26:60: error: expected ‘>’ before ‘<’ token

define TR2_OPTIONAL_REQUIRES(...) typename std::enable_if<VA_ARGS::value,

                                                        ^

/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:244:39: note: in expansion of macro ‘TR2_OPTIONAL_REQUIRES’
template <class U, class... Args, TR2_OPTIONAL_REQUIRES(std::is_constructib
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:246:66: error: expected unqualified-id before ‘{’ token
: init_(true), storage_(il, std::forward(args)...) {}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:258:5: error: ‘constexpr’ does not name a type
constexpr constexpr_optional_base() noexcept : init_(false), storage_(trivi
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:258:5: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:260:14: error: ‘constexpr’ does not name a type
explicit constexpr constexpr_optional_base(const T& v) : init_(true), stora
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:260:14: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:262:14: error: ‘constexpr’ does not name a type
explicit constexpr constexpr_optional_base(T&& v) : init_(true), storage_(c
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:262:14: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:264:20: warning: variadic templates only available with -std=c++11 or -std=gnu++11
template <class... Args> explicit constexpr constexpr_optional_base(in_plac
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:264:39: error: ‘constexpr’ does not name a type
template <class... Args> explicit constexpr constexpr_optional_base(in_plac
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:264:39: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:267:29: warning: variadic templates only available with -std=c++11 or -std=gnu++11
template <class U, class... Args, TR2_OPTIONAL_REQUIRES(std::is_constructib
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:26:51: error: ‘enable_if’ in namespace ‘std’ does not name a template type

define TR2_OPTIONAL_REQUIRES(...) typename std::enable_if<VA_ARGS::value,

                                               ^

/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:267:39: note: in expansion of macro ‘TR2_OPTIONAL_REQUIRES’
template <class U, class... Args, TR2_OPTIONAL_REQUIRES(std::is_constructib
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:26:60: error: expected ‘>’ before ‘<’ token

define TR2_OPTIONAL_REQUIRES(...) typename std::enable_if<VA_ARGS::value,

                                                        ^

/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:267:39: note: in expansion of macro ‘TR2_OPTIONAL_REQUIRES’
template <class U, class... Args, TR2_OPTIONAL_REQUIRES(std::is_constructib
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:269:64: error: expected unqualified-id before ‘{’ token
: init_(true), storage_(il, std::forward(args)...) {}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:271:34: warning: defaulted and deleted functions only available with -std=c++11 or -std=gnu++11
~constexpr_optional_base() = default;
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:275:1: error: expected unqualified-id before ‘using’
using OptionalBase = typename std::conditional<
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:284:38: error: expected template-name before ‘<’ token
class optional : private OptionalBase
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:284:38: error: expected ‘{’ before ‘<’ token
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:284:38: error: expected unqualified-id before ‘<’ token
In file included from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Error.h:4:0,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/Allocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THAllocator.h:6,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/THStorage.h:4,
from /home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/TH/TH.h:15,
from depthconv.c:433:
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:542:18: error: expected identifier before ‘!’ token
static_assert( !std::is_same<T, nullopt_t>::value, "bad T" );
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:542:18: error: expected ‘,’ or ‘...’ before ‘!’ token
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:542:62: error: ISO C++ forbids declaration of ‘static_assert’ with no type [-fpermissive]
static_assert( !std::is_same<T, nullopt_t>::value, "bad T" );
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:543:18: error: expected identifier before ‘!’ token
static_assert( !std::is_same<T, in_place_t>::value, "bad T" );
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:543:18: error: expected ‘,’ or ‘...’ before ‘!’ token
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:543:63: error: ISO C++ forbids declaration of ‘static_assert’ with no type [-fpermissive]
static_assert( !std::is_same<T, in_place_t>::value, "bad T" );
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:543:3: error: ‘int at::optional<T&>::static_assert(int)’ cannot be overloaded
static_assert( !std::is_same<T, in_place_t>::value, "bad T" );
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:542:3: error: with ‘int at::optional<T&>::static_assert(int)’
static_assert( !std::is_same<T, nullopt_t>::value, "bad T" );
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:549:3: error: ‘constexpr’ does not name a type
constexpr optional() noexcept : ref(nullptr) {}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:549:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:551:3: error: ‘constexpr’ does not name a type
constexpr optional(nullopt_t) noexcept : ref(nullptr) {}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:551:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:553:3: error: ‘constexpr’ does not name a type
constexpr optional(T& v) noexcept : ref(detail::static_addressof(v)) {}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:553:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:555:13: error: expected ‘,’ or ‘...’ before ‘&&’ token
optional(T&&) = delete;
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:555:19: warning: defaulted and deleted functions only available with -std=c++11 or -std=gnu++11
optional(T&&) = delete;
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:557:3: error: ‘constexpr’ does not name a type
constexpr optional(const optional& rhs) noexcept : ref(rhs.ref) {}
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:557:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:559:12: error: ‘constexpr’ does not name a type
explicit constexpr optional(in_place_t, T& v) noexcept : ref(detail_::static_
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:559:12: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:561:31: error: expected ‘)’ before ‘,’ token
explicit optional(in_place_t, T&&) = delete;
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:563:17: warning: defaulted and deleted functions only available with -std=c++11 or -std=gnu++11
~optional() = default;
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:566:32: error: expected ‘;’ at end of member declaration
optional& operator=(nullopt_t) noexcept {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:566:34: error: ‘noexcept’ does not name a type
optional& operator=(nullopt_t) noexcept {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:566:34: note: C++11 ‘noexcept’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:582:3: warning: ‘auto’ changes meaning in C++11; please remove it [-Wc++0x-compat]
auto operator=(U&& rhs) noexcept
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:582:19: error: expected ‘,’ or ‘...’ before ‘&&’ token
auto operator=(U&& rhs) noexcept
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:582:27: error: expected initializer before ‘noexcept’
auto operator=(U&& rhs) noexcept
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:594:3: warning: ‘auto’ changes meaning in C++11; please remove it [-Wc++0x-compat]
auto operator=(U&& rhs) noexcept
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:594:19: error: expected ‘,’ or ‘...’ before ‘&&’ token
auto operator=(U&& rhs) noexcept
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:594:27: error: expected initializer before ‘noexcept’
auto operator=(U&& rhs) noexcept
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:602:20: error: expected ‘;’ at end of member declaration
void emplace(T& v) noexcept {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:602:22: error: ‘noexcept’ does not name a type
void emplace(T& v) noexcept {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:602:22: note: C++11 ‘noexcept’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:606:17: error: expected ‘,’ or ‘...’ before ‘&&’ token
void emplace(T&&) = delete;
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:606:23: warning: defaulted and deleted functions only available with -std=c++11 or -std=gnu++11
void emplace(T&&) = delete;
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:609:30: error: expected ‘;’ at end of member declaration
void swap(optional<T&>& rhs) noexcept
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:609:32: error: ‘noexcept’ does not name a type
void swap(optional<T&>& rhs) noexcept
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:609:32: note: C++11 ‘noexcept’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:615:3: error: ‘constexpr’ does not name a type
constexpr T* operator->() const {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:615:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:619:3: error: ‘constexpr’ does not name a type
constexpr T& operator*() const {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:619:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:623:3: error: ‘constexpr’ does not name a type
constexpr T& value() const {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:623:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:627:12: error: ‘constexpr’ does not name a type
explicit constexpr operator bool() const noexcept {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:627:12: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:631:3: error: ‘constexpr’ does not name a type
constexpr bool has_value() const noexcept {
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:631:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:636:3: error: ‘constexpr’ does not name a type
constexpr typename std::decay::type value_or(V&& v) const
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:636:3: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:642:14: error: expected ‘;’ at end of member declaration
void reset() noexcept { ref = nullptr; }
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:642:16: error: ‘noexcept’ does not name a type
void reset() noexcept { ref = nullptr; }
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:642:16: note: C++11 ‘noexcept’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:647:19: error: template argument 1 is invalid
class optional<T&&>
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:654:20: error: ‘constexpr’ does not name a type
template constexpr bool operator==(const optional& x, const option
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:654:20: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:659:20: error: ‘constexpr’ does not name a type
template constexpr bool operator!=(const optional& x, const option
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:659:20: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:664:20: error: ‘constexpr’ does not name a type
template constexpr bool operator<(const optional& x, const optiona
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:664:20: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:669:20: error: ‘constexpr’ does not name a type
template constexpr bool operator>(const optional& x, const optiona
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:669:20: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:674:20: error: ‘constexpr’ does not name a type
template constexpr bool operator<=(const optional& x, const option
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:674:20: note: C++11 ‘constexpr’ only available with -std=c++11 or -std=gnu++11
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/include/ATen/optional.h:679:20: error: ‘constexpr’ does not name a type
template constexpr bool operator>=(const optional& x, const option
^
/home/siat/anaconda3/lib/python3.6/site-packages/torch/utils/ffi/../../lib/inclu

Your paper has evaluate the per-class-iou(the pink chart),but your sharing on github has not this test code.could you share it?If you have shared it,could you please give me a guidance to get the per-class-iou.

Which PyTorch version is required for this project?

Fail to load pretrained vgg model。

Fails to compile the depthconv function. I'm using PyTorch 1.0.

I use the sunrgbd dataset to train, and get the following results, but the results are quite different from the experimental results of the paper.

Accuracy: 52.18331861069419
Accuracy Class: 21.65154302916059
Mean IU: 13.361277218676214
FWAV Accuracy: 36.994343765004906

And I directly use the pretrain-Model(best_net_HHA.pth,best_net_rgb.pth) to test nyuv2, and also get the bad result as following:

Accuracy: 5.886450036442711
Accuracy Class: 2.6109730562398203
Mean IU: 0.697199549228473
FWAV Accuracy: 2.2405542009448167

Can anyone give me some advises,please? Thank you very much

I hope to use the depth-aware pooling and depth-aware convolutional to my network, but I found some errors after compiling sh make.sh. I want to know how to operate?
On this path \ops\depthavgpooling_ext\depthavgpooling_init_.py ，I can't find _depthavgpooling

from torch.utils.ffi import _wrap_function
from ._depthavgpooling import lib as _lib, ffi as _ffi

all = []
def _import_symbols(locals):
for symbol in dir(_lib):
fn = getattr(_lib, symbol)
if callable(fn):
locals[symbol] = _wrap_function(fn, _ffi)
else:
locals[symbol] = fn
all.append(symbol)

_import_symbols(locals())

“”
Traceback (most recent call last):
File "F:/ops/depthavgpooling/_ext/depthavgpooling/init.py", line 3, in
from ._depthavgpooling import lib as _lib, ffi as _ffi
ModuleNotFoundError: No module named 'main._depthavgpooling'; 'main' is not a package

“”