Comments (4)
soft link to Outputs/model_logs/cvpods_playground/detection/coco/borderdet/borderdet.res101.fpn.coco.800size.2x
Command Line Args: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False)
[10/16 16:29:02 cvpods]: Rank of current process: 0. World size: 1
[10/16 16:29:02 cvpods]: Environment info:
sys.platform linux
Python 3.7.9 (default, Aug 31 2020, 12:42:55) [GCC 7.3.0]
numpy 1.18.2
cvpods 0.1 @/media/sda6/yhh/FCOS/BorderDet/cvpods
cvpods compiler GCC 5.5
cvpods CUDA compiler 10.1
cvpods arch flags sm_61
cvpods_ENV_MODULE
PyTorch 1.4.0 @/home/yons/anaconda3/envs/borderdet140-yhh/lib/python3.7/site-packages/torch
PyTorch debug build False
CUDA available True
GPU 0 GeForce GTX 1080 Ti
CUDA_HOME /usr/local/cuda-10.1
NVCC Cuda compilation tools, release 10.1, V10.1.105
Pillow 6.2.0
torchvision 0.5.0 @/home/yons/anaconda3/envs/borderdet140-yhh/lib/python3.7/site-packages/torchvision
torchvision arch flags sm_35, sm_50, sm_60, sm_70, sm_75
cv2 4.4.0
PyTorch built with:
- GCC 7.3
- Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v0.21.1 (Git Hash 7d2fd500bc78936d1d648ca713b901012f470dbc)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- NNPACK is enabled
- CUDA Runtime 10.1
- NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37
- CuDNN 7.6.3
- Magma 2.5.1
- Build settings: BLAS=MKL, BUILD_NAMEDTENSOR=OFF, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -fopenmp -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Wno-stringop-overflow, DISABLE_NUMA=1, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF,
[10/16 16:29:02 cvpods]: Command line arguments: Namespace(dist_url='tcp://127.0.0.1:50152', eval_only=False, machine_rank=0, num_gpus=1, num_machines=1, opts=[], resume=False)
from borderdet.
in cvpods/engine/launch.py
I changed
if world_size > 1:
# pytorch/pytorch#14391
# TODO prctl in spawned processes
to
if world_size >= 1:
# pytorch/pytorch#14391
# TODO prctl in spawned processes
it works
from borderdet.
Well, seems you are using 1-GPU during training? Such an error shouldn't happen. Could you please provide command your are using ?
from borderdet.
Since the reporter doesn't reply for a week, We close this issue.
from borderdet.
Related Issues (20)
- example for instance segmentation. HOT 2
- AssertionError: Requires PyTorch >= 1.3 HOT 1
- How to trun on evaluation during the training. HOT 2
- Details of enhacing the single point feature with region features? HOT 2
- 一个不成熟的小建议 HOT 2
- > 1. They are the same.
- I have the same question. HOT 1
- I wonder how you implement border align? HOT 1
- How do you realize border feature extracting in Table 1? HOT 2
- Border Feature Extraction HOT 2
- code issue HOT 1
- Can not reproduce the results. HOT 2
- where is the implementation details of border_align_forward HOT 2
- How to solve the error "cuda runtime error (98) : invalid device function" when run the borderDet? HOT 4
- Error at inference
- HTTP Error HOT 5
- no kernel image is available for execution on the device: border_align_kernel.cu:202 HOT 3
- BorderDet can not run on RTX 3090 GPU? HOT 3
- 论文图2中的实验也是在coarse的分支基础上,再添加新的分支来实现的吗
- 多尺度训练
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from borderdet.