tfzhou / c-hoi Goto Github PK

When I try to run
python tools/test_pic.py configs/pic_v2.0/htc_rel_dconv_c3-c5_mstrain_400_1400_x101_64x4d_fpn_20e_train_rel_dcn_semantichead.py pic_latest.pth --json_out det_result.json
I get the following output:

None
loading annotations into memory...
Done (t=0.00s)
creating index...
index created!

The model and loaded state dict do not match exactly
missing keys in source state_dict: reldn_head.freq_bias.rel_baseline.weight, reldn_head.prd_cls_feats.0.weight, reldn_head.prd_cls_feats.0.bias, reldn_head.prd_cls_feats.2.weight, reldn_head.prd_cls_feats.2.bias, reldn_head.prd_cls_scores.0.weight, reldn_head.prd_cls_scores.0.bias, reldn_head.spt_cls_feats.0.weight, reldn_head.spt_cls_feats.0.bias, reldn_head.spt_cls_feats.2.weight, reldn_head.spt_cls_feats.2.bias, reldn_head.spt_cls_scores.0.weight, reldn_head.spt_cls_scores.0.bias, reldn_head.prd_sbj_scores.0.weight, reldn_head.prd_sbj_scores.0.bias, reldn_head.prd_sbj_scores.2.weight, reldn_head.prd_sbj_scores.2.bias, reldn_head.prd_obj_scores.0.weight, reldn_head.prd_obj_scores.0.bias, reldn_head.prd_obj_scores.2.weight, reldn_head.prd_obj_scores.2.bias, reldn_binary_head.vis_rank_feats.0.weight, reldn_binary_head.vis_rank_feats.0.bias, reldn_binary_head.vis_rank_feats.2.weight, reldn_binary_head.vis_rank_feats.2.bias, reldn_binary_head.spt_rank_feats.0.weight, reldn_binary_head.spt_rank_feats.0.bias, reldn_binary_head.spt_rank_feats.2.weight, reldn_binary_head.spt_rank_feats.2.bias, reldn_binary_head.proj.weight, reldn_binary_head.proj.bias, reldn_binary_head.readout.0.weight, reldn_binary_head.readout.0.bias

System:
Ubuntu 16.04
Cuda 9.2
Nvidia Driver 396.37

Please help!

I tried to train the model on the HOIW dataset, using Tools /train.py file for training, and got the model, but when using the model to train on tools/ test_hoiW. py, the obtained hoiw_result.json file has no result. As shown in the figure below.

We can get the results by testing with the hoiw_lastest.pth file provided by the author

I tried to continue the training under Hoiw_lastest.pth, but the following problems occurred and the training could not be carried out

missing keys in source state_dict: layer2.0.conv2_offset.weight, layer2.0.conv2_offset.bias, layer2.1.conv2_offset.weight, layer2.1.conv2_offset.bias, layer2.2.conv2_offset.weight, layer2.2.conv2_offset.bias, layer2.3.conv2_offset.weight, layer2.3.conv2_offset.bias, layer3.0.conv2_offset.weight, layer3.0.conv2_offset.bias, layer3.1.conv2_offset.weight, layer3.1.conv2_offset.bias, layer3.2.conv2_offset.weight, layer3.2.conv2_offset.bias, layer3.3.conv2_offset.weight, layer3.3.conv2_offset.bias, layer3.4.conv2_offset.weight, layer3.4.conv2_offset.bias, layer3.5.conv2_offset.weight, layer3.5.conv2_offset.bias, layer3.6.conv2_offset.weight, layer3.6.conv2_offset.bias, layer3.7.conv2_offset.weight, layer3.7.conv2_offset.bias, layer3.8.conv2_offset.weight, layer3.8.conv2_offset.bias, layer3.9.conv2_offset.weight, layer3.9.conv2_offset.bias, layer3.10.conv2_offset.weight, layer3.10.conv2_offset.bias, layer3.11.conv2_offset.weight, layer3.11.conv2_offset.bias, layer3.12.conv2_offset.weight, layer3.12.conv2_offset.bias, layer3.13.conv2_offset.weight, layer3.13.conv2_offset.bias, layer3.14.conv2_offset.weight, layer3.14.conv2_offset.bias, layer3.15.conv2_offset.weight, layer3.15.conv2_offset.bias, layer3.16.conv2_offset.weight, layer3.16.conv2_offset.bias, layer3.17.conv2_offset.weight, layer3.17.conv2_offset.bias, layer3.18.conv2_offset.weight, layer3.18.conv2_offset.bias, layer3.19.conv2_offset.weight, layer3.19.conv2_offset.bias, layer3.20.conv2_offset.weight, layer3.20.conv2_offset.bias, layer3.21.conv2_offset.weight, layer3.21.conv2_offset.bias, layer3.22.conv2_offset.weight, layer3.22.conv2_offset.bias, layer4.0.conv2_offset.weight, layer4.0.conv2_offset.bias, layer4.1.conv2_offset.weight, layer4.1.conv2_offset.bias, layer4.2.conv2_offset.weight, layer4.2.conv2_offset.bias

None
loading annotations into memory...
Done (t=0.41s)
creating index...
index created!
2022-09-09 01:38:15,562 - INFO - load checkpoint from hoiw_latest.pth
2022-09-09 01:38:17,626 - WARNING - The model and loaded state dict do not match exactly

missing keys in source state_dict: sa.g.conv.weight, sa.g.conv.bias, sa.theta.conv.weight, sa.theta.conv.bias, sa.phi.conv.weight, sa.phi.conv.bias, sa.conv_out.conv.weight, sa.conv_out.conv.bias

Traceback (most recent call last):
File "tools/train.py", line 108, in
main()
File "tools/train.py", line 104, in main
logger=logger)
File "/root/anaconda3/envs/py37_torch/lib/python3.7/site-packages/mmdet-1.0rc0+65c1842-py3.7-linux-x86_64.egg/mmdet/apis/train.py", line 62, in train_detector
_non_dist_train(model, dataset, cfg, validate=validate)
File "/root/anaconda3/envs/py37_torch/lib/python3.7/site-packages/mmdet-1.0rc0+65c1842-py3.7-linux-x86_64.egg/mmdet/apis/train.py", line 287, in _non_dist_train
runner.resume(cfg.resume_from)
File "/root/anaconda3/envs/py37_torch/lib/python3.7/site-packages/mmcv/runner/runner.py", line 314, in resume
self.optimizer.load_state_dict(checkpoint['optimizer'])
File "/root/anaconda3/envs/py37_torch/lib/python3.7/site-packages/torch/optim/optimizer.py", line 141, in load_state_dict
raise ValueError("loaded state dict has a different number of "
ValueError: loaded state dict has a different number of parameter groups

In addition, missing Keys will also appear when the model provided by the author is used for testing, while the model trained by the train.py file will not appear:

The model and loaded state dict do not match exactly:

missing keys in source state_dict: sa.g.conv.weight, sa.g.conv.bias, sa.theta.conv.weight, sa.theta.conv.bias, sa.phi.conv.weight, sa.phi.conv.bias, sa.conv_out.conv.weight, sa.conv_out.conv.bias

The GPU I use is V100
python=3.7
mmcv=0.4.3
mmdet =1.0rc0+65c1842
pytorch= 1.10

I hope the author can answer.Thank you.

My target system has no CUDA and got this error:

OSError: CUDA_HOME environment variable is not set. Please set it to your CUDA install root.

mmdetection has CPU-only version https://mmdetection.readthedocs.io/en/v2.2.0/install.html#install-with-cpu-only

When I want to train it using dist_train.sh tool, I got errors as flowing:

with TensorRT, please make sure the missing libraries mentioned above are installed properly.
Traceback (most recent call last):
File "./tools/train.py", line 108, in
main()
File "./tools/train.py", line 104, in main
logger=logger)
File "/sas_data/e01163/C-HOI/workspace/C-HOI/mmdet/apis/train.py", line 62, in train_detector
_dist_train(model, dataset, cfg, validate=validate)
File "/sas_data/e01163/C-HOI/workspace/C-HOI/mmdet/apis/train.py", line 256, in _dist_train
runner.run(data_loaders, cfg.workflow, cfg.total_epochs)
File "/sas_data/e01163/C-HOI/workspace/mmcv/mmcv/runner/runner.py", line 368, in run
epoch_runner(data_loaders[i], **kwargs)
File "/sas_data/e01163/C-HOI/workspace/mmcv/mmcv/runner/runner.py", line 267, in train
self.model, data_batch, train_mode=True, **kwargs)
File "/sas_data/e01163/C-HOI/workspace/C-HOI/mmdet/apis/train.py", line 41, in batch_processor
losses = model(**data)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/parallel/distributed.py", line 888, in forward
output = self.module(*inputs, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/sas_data/e01163/C-HOI/workspace/C-HOI/mmdet/core/fp16/decorators.py", line 49, in new_func
return old_func(*args, **kwargs)
File "/sas_data/e01163/C-HOI/workspace/C-HOI/mmdet/models/detectors/base.py", line 95, in forward
return self.forward_train(img, img_meta, **kwargs)
File "/sas_data/e01163/C-HOI/workspace/C-HOI/mmdet/models/detectors/cascade_rcnn_rel.py", line 414, in forward_train
x = self.extract_feat(img)
File "/sas_data/e01163/C-HOI/workspace/C-HOI/mmdet/models/detectors/cascade_rcnn_rel.py", line 165, in extract_feat
x = self.backbone(img)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/sas_data/e01163/C-HOI/workspace/C-HOI/mmdet/models/backbones/resnet.py", line 506, in forward
x = self.conv1(x)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 446, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 443, in _conv_forward
self.padding, self.dilation, self.groups)
TypeError: conv2d() received an invalid combination of arguments - got (DataContainer, Parameter, NoneType, tuple, tuple, tuple, int), but expected one of:

• (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, tuple of ints padding, tuple of ints dilation, int groups)
  didn't match because some of the arguments have invalid types: (DataContainer, Parameter, NoneType, tuple, tuple, tuple, int)
• (Tensor input, Tensor weight, Tensor bias, tuple of ints stride, str padding, tuple of ints dilation, int groups)
  didn't match because some of the arguments have invalid types: (DataContainer, Parameter, NoneType, tuple, tuple, tuple, int)

Hi, great respect to your work!
How to train this model?

Hi, Mr Zhou, thanks for u contribution of this project. I try to achieve the script on HOIW dataset python tools/test_hoiw.py configs/hoiw/cascade_rcnn_x101_64x4d_fpn_1x_4gpu_rel.py hoiw_latest.pth --json_out det_result.json --hoiw_out hoiw_result.json
however, I cant find the det_result.json or hoiw_result.json in your google driver. In your driver, only three files are provided, hoiw_latest.pth, pic_latest.pth and pic_result.zip. So could u please provide the hoiw_result.zip with det_result.json and hoiw_result.json?

I used the config in the cascade_rcnn_x101_64x4d_fpn_1x_4gpu_rel.py, and loaded the pretrained weights of the backbone ResNext101 and the Cascade R-CNN from openmmlab and mmdetection model zoo respectively, but can only get an mAP of only 0.3+.

So are there something I missed, or if you could provide us with the parameters and the training details, it will be more obliged.

thanks for your jobs,but how can i get the mAP, using the test_hoiw.py only get the hoiw_result.json

1. I did not find commmit id 65c1842 in mmdetection
2. MMdetection 1.0rc0 is not compatible with pytroch1.5
   In this commit, they fixed the bug
   open-mmlab/mmdetection@e5921ca

hello, how wonderful the work is! when i run test, i encountered the error:
FileNotFoundError: [Errno 2] No such file or directory: 'data/hoiw/annotations/hoiw_val.json'
what's the hoiw_val.json?

how to fix the issue please

hello , I run the file . hoiw datasets , I find the error about dataset in my file .

cats = self.dataset['categories']
KeyError: 'categories'

hoiw labels format form need to be transform the coco label ?

After setup the evironment and change some code, there are still two problems in checkpoints and datasets:

1. I convert test_2019.json to relations_all.json. however, relations_all.json can not comform the coco style, so I got the error
   cats = self.dataset['categories']
   KeyError: 'categories'
2. I load checkpoint from hoiw_latest.pth, the model and loaded state dict do not match exactly, both sizes and keys. The error is
   size mismatch for reldn_head.freq_bias.rel_baseline.weight: copying a param with shape torch.Size([121, 11]) from checkpoint, the shape in current model is torch.Size([121, 12]).
   size mismatch for reldn_head.prd_cls_feats.0.weight: copying a param with shape torch.Size([1024, 37632]) from checkpoint, the shape in current model is torch.Size([2048, 37632]).
   size mismatch for reldn_head.prd_cls_feats.0.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([2048]).
   size mismatch for reldn_head.prd_cls_feats.2.weight: copying a param with shape torch.Size([1024, 1024]) from checkpoint, the shape in current model is torch.Size([2048, 2048]).
   size mismatch for reldn_head.prd_cls_feats.2.bias: copying a param with shape torch.Size([1024]) from checkpoint, the shape in current model is torch.Size([2048]).
   size mismatch for reldn_head.prd_cls_scores.0.weight: copying a param with shape torch.Size([11, 1024]) from checkpoint, the shape in current model is torch.Size([11, 2048]).
   size mismatch for reldn_head.prd_sbj_scores.0.weight: copying a param with shape torch.Size([11, 12544]) from checkpoint, the shape in current model is torch.Size([1024, 12544]).
   size mismatch for reldn_head.prd_sbj_scores.0.bias: copying a param with shape torch.Size([11]) from checkpoint, the shape in current model is torch.Size([1024]).
   size mismatch for reldn_head.prd_obj_scores.0.weight: copying a param with shape torch.Size([11, 12544]) from checkpoint, the shape in current model is torch.Size([1024, 12544]).
   size mismatch for reldn_head.prd_obj_scores.0.bias: copying a param with shape torch.Size([11]) from checkpoint, the shape in current model is torch.Size([1024]).
   missing keys in source state_dict: reldn_head.prd_sbj_scores.2.weight, reldn_head.prd_sbj_scores.2.bias, reldn_head.prd_obj_scores.2.weight, reldn_head.prd_obj_scores.2.bias, sa.g.conv.weight, sa.g.conv.bias, sa.theta.conv.weight, sa.theta.conv.bias, sa.phi.conv.weight, sa.phi.conv.bias, sa.conv_out.conv.weight, sa.conv_out.conv.bias

so anyone address these questions ? or we need the help from the author @tfzhou

I got some errors when building the environment

FAILED: /home/xian/Documents/code/C-HOI/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_cuda.o
c++ -MMD -MF /home/xian/Documents/code/C-HOI/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_cuda.o.d -pthread -B /home/xian/anaconda3/envs/open-mmlab/compiler_compat -Wl,--sysroot=/ -Wsign-compare -DNDEBUG -g -fwrapv -O3 -Wall -Wstrict-prototypes -fPIC -I/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include -I/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/TH -I/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-9.2/include -I/home/xian/anaconda3/envs/open-mmlab/include/python3.7m -c -c /home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_cuda.cpp -o /home/xian/Documents/code/C-HOI/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_cuda.o -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++14
cc1plus: warning: command line option ?Wstrict-prototypes?is valid for C/ObjC but not for C++
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_cuda.cpp: In function t::Tensor nms(const at::Tensor&, float)鈥?
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_cuda.cpp:4:39: warning: t::DeprecatedTypeProperties& at::Tensor::type() const鈥?is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
^
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_cuda.cpp:9:3: note: in expansion of macro HECK_CUDA?
CHECK_CUDA(dets);
^
In file included from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/ATen/Tensor.h:11:0,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/ATen/Context.h:4,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/ATen/ATen.h:5,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/types.h:3,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader_options.h:4,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/base.h:3,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader/stateful.h:3,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data/dataloader.h:3,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/data.h:3,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include/torch/all.h:4,
from /home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/extension.h:4,
from /home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_cuda.cpp:2:
/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:30: note: declared here
DeprecatedTypeProperties & type() const {
^
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_cuda.cpp:4:80: error: T_CHECK?was not declared in this scope
#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
^
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_cuda.cpp:9:3: note: in expansion of macro HECK_CUDA?
CHECK_CUDA(dets);
^
[2/2] /usr/local/cuda-9.2/bin/nvcc -I/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include -I/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/TH -I/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-9.2/include -I/home/xian/anaconda3/envs/open-mmlab/include/python3.7m -c -c /home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_kernel.cu -o /home/xian/Documents/code/C-HOI/build/temp.linux-x86_64-3.7/mmdet/ops/nms/src/nms_kernel.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options ''"'"'-fPIC'"'"'' -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=nms_cuda -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_61,code=sm_61 -std=c++14
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_kernel.cu: In function t::Tensor nms_cuda(at::Tensor, float)?
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_kernel.cu:72:62: warning: t::DeprecatedTypeProperties& at::Tensor::type() const?is deprecated: Tensor.type() is deprecated. Instead use Tensor.options(), which in many cases (e.g. in a constructor) is a drop-in replacement. If you were using data from type(), that is now available from Tensor itself, so instead of tensor.type().scalar_type(), use tensor.scalar_type() instead and instead of tensor.type().backend() use tensor.device(). [-Wdeprecated-declarations]
AT_ASSERTM(boxes.type().is_cuda(), "boxes must be a CUDA tensor");
^
/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:262:1: note: declared here
DeprecatedTypeProperties & type() const {
^
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_kernel.cu:81:50: warning: * at::Tensor::data() const [with T = float]?is deprecated: Tensor.data() is deprecated. Please use Tensor.data_ptr() instead. [-Wdeprecated-declarations]
scalar_t* boxes_dev = boxes_sorted.data<scalar_t>();
^
/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:341:1: note: declared here
T * data() const {
^
/home/xian/Documents/code/C-HOI/mmdet/ops/nms/src/nms_kernel.cu:109:39: warning: * at::Tensor::data() const [with T = long int]?is deprecated: Tensor.data() is deprecated. Please use Tensor.data_ptr() instead. [-Wdeprecated-declarations]
int64_t* keep_out = keep.data<int64_t>();
^
/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/include/ATen/core/TensorBody.h:341:1: note: declared here
T * data() const {
^
ninja: build stopped: subcommand failed.
Traceback (most recent call last):
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1423, in _run_ninja_build
check=True)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/subprocess.py", line 512, in run
output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "setup.py", line 196, in
zip_safe=False)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/setuptools/init.py", line 153, in setup
return distutils.core.setup(**attrs)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/core.py", line 148, in setup
dist.run_commands()
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/dist.py", line 966, in run_commands
self.run_command(cmd)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/setuptools/command/develop.py", line 34, in run
self.install_for_development()
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/setuptools/command/develop.py", line 136, in install_for_development
self.run_command('build_ext')
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/cmd.py", line 313, in run_command
self.distribution.run_command(command)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/dist.py", line 985, in run_command
cmd_obj.run()
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 79, in run
_build_ext.run(self)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/command/build_ext.py", line 340, in run
self.build_extensions()
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 603, in build_extensions
build_ext.build_extensions(self)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/command/build_ext.py", line 449, in build_extensions
self._build_extensions_serial()
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/command/build_ext.py", line 474, in _build_extensions_serial
self.build_extension(ext)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/setuptools/command/build_ext.py", line 196, in build_extension
_build_ext.build_extension(self, ext)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/distutils/command/build_ext.py", line 534, in build_extension
depends=ext.depends)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 437, in unix_wrap_ninja_compile
with_cuda=with_cuda)
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1163, in _write_ninja_file_and_compile_objects
error_prefix='Error compiling objects for extension')
File "/home/xian/anaconda3/envs/open-mmlab/lib/python3.7/site-packages/torch/utils/cpp_extension.py", line 1436, in _run_ninja_build
raise RuntimeError(message)
RuntimeError: Error compiling objects for extension

How can I solve it?

I run test_pic.py. It said No such file or directory: 'pred_dist_overlap.npz'. The problem is caused by codes in /C-HOI/mmdet/models/rel_heads/sparse_targets_rel.py at line 66. I check the code, it always load a file called "pred_dist_overlap.npz". I have no idea what this "pred_dist_overlap.npz" is. I cannot find it. Can anybody help me?