Comments (12)
hasanirtiza
commented on May 24, 2024
Can you share with us your PyTorch and CUDA version. Moreover, also which GPU (V100 etc) are you using ?
from pedestron.
Morteza-j8
commented on May 24, 2024
Can you share with us your PyTorch and CUDA version. Moreover, also which GPU (V100 etc) are you using ?
$ cat /usr/local/cuda/version.txt
CUDA Version 10.2.89
$ pip3 show torch torchvision
Name: torch
Version: 1.4.0
Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration
Home-page: https://pytorch.org/
Author: PyTorch Team
Author-email: [email protected]
License: BSD-3
Location: /home/morteza/.local/lib/python3.8/site-packages
Requires:
Required-by: torchvision
---
Name: torchvision
Version: 0.5.0
Summary: image and video datasets and models for torch deep learning
Home-page: https://github.com/pytorch/vision
Author: PyTorch Core Team
Author-email: [email protected]
License: BSD
Location: /home/morteza/.local/lib/python3.8/site-packages
Requires: torch, six, pillow, numpy
Required-by:
from pedestron.
Morteza-j8
commented on May 24, 2024
i used NVIDIA 740M GPU.
from pedestron.
hasanirtiza
commented on May 24, 2024
Most probably its the CUDA version. We have tested Pedestron with CUDA 10.0 and 9.0. I suggest perhaps you revert back to CUDA 10.0 and recompile it, to test if it works on your machine. Furthermore you can also refer to the following issues (in case you have not seen them already)
issue:1
Secondly have a look at the
issue:2
scroll down to the bottom and look at point 4. See if it also applies to you.
from pedestron.
Morteza-j8
commented on May 24, 2024
when i wait for your response, i changed my device by config :
OS: ubuntu 16.04
GPU: NVIDIA Quadro-M1000M
CUDA Version: 10.2.89
Python: 3.5
PyTorch: 1.4.0
after run same as previous example get me this error:
RuntimeError: CUDA out of memory. Tried to allocate 128.00 MiB (GPU 0; 1.96 GiB total capacity; 473.88 MiB already allocated; 27.25 MiB free; 480.00 MiB reserved in total by PyTorch)
from pedestron.
hasanirtiza
commented on May 24, 2024
That is a different problem. I would suggest first simply changing the CUDA version back to 10.0, compiling Pedestron (just to be on the safe side) and see if it works.
from pedestron.
Morteza-j8
commented on May 24, 2024
i install CUDA version 10.0:
$ cat /usr/local/cuda/version.txt
CUDA Version 10.0.130
changed my error:
$ python3 tools/demo.py configs/elephant/cityperson/cascade_hrnet.py ./models_pretrained/epoch_5.pth.stu demo/ result_demo/
Traceback (most recent call last):
File "tools/demo.py", line 14, in <module>
from mmdet.apis import inference_detector, init_detector, show_result
File "./Pedestron-master/tools/../mmdet/apis/__init__.py", line 2, in <module>
from .train import train_detector
File "./Pedestron-master/tools/../mmdet/apis/train.py", line 7, in <module>
from mmdet.core.my_mmcv.runner.mean_teacher_runner import Mean_teacher_Runner as Runner
File "./Pedestron-master/tools/../mmdet/core/__init__.py", line 6, in <module>
from .post_processing import * # noqa: F401, F403
File "./Pedestron-master/tools/../mmdet/core/post_processing/__init__.py", line 1, in <module>
from .bbox_nms import multiclass_nms
File "./Pedestron-master/tools/../mmdet/core/post_processing/bbox_nms.py", line 3, in <module>
from mmdet.ops.nms import nms_wrapper
File "./Pedestron-master/tools/../mmdet/ops/__init__.py", line 1, in <module>
from .dcn import (DeformConv, DeformConvPack, ModulatedDeformConv,
File "./Pedestron-master/tools/../mmdet/ops/dcn/__init__.py", line 1, in <module>
from .functions.deform_conv import deform_conv, modulated_deform_conv
File "./Pedestron-master/tools/../mmdet/ops/dcn/functions/deform_conv.py", line 5, in <module>
from .. import deform_conv_cuda
ImportError: libcudart.so.10.2: cannot open shared object file: No such file or directory
from pedestron.
hasanirtiza
commented on May 24, 2024
Did you recompile Pedestron after you changed CUDA version ?
from pedestron.
Morteza-j8
commented on May 24, 2024
$ sudo python3 setup.py develop
No CUDA runtime is found, using CUDA_HOME='/usr'
Compiling mmdet/ops/nms/src/soft_nms_cpu.pyx because it depends on /usr/local/lib/python3.5/dist-packages/Cython/Includes/numpy/__init__.pxd.
[1/1] Cythonizing mmdet/ops/nms/src/soft_nms_cpu.pyx
running develop
running egg_info
writing top-level names to mmdet.egg-info/top_level.txt
writing dependency_links to mmdet.egg-info/dependency_links.txt
writing mmdet.egg-info/PKG-INFO
writing requirements to mmdet.egg-info/requires.txt
reading manifest file 'mmdet.egg-info/SOURCES.txt'
writing manifest file 'mmdet.egg-info/SOURCES.txt'
running build_ext
building 'mmdet.ops.nms.soft_nms_cpu' extension
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 -I/home/morteza/.local/lib/python3.5/site-packages/numpy/core/include -I/usr/include/python3.5m -c mmdet/ops/nms/src/soft_nms_cpu.cpp -o build/temp.linux-x86_64-3.5/mmdet/ops/nms/src/soft_nms_cpu.o -Wno-unused-function -Wno-write-strings -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=soft_nms_cpu -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11
cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++
In file included from /home/morteza/.local/lib/python3.5/site-packages/numpy/core/include/numpy/ndarraytypes.h:1832:0,
from /home/morteza/.local/lib/python3.5/site-packages/numpy/core/include/numpy/ndarrayobject.h:12,
from /home/morteza/.local/lib/python3.5/site-packages/numpy/core/include/numpy/arrayobject.h:4,
from mmdet/ops/nms/src/soft_nms_cpu.cpp:640:
/home/morteza/.local/lib/python3.5/site-packages/numpy/core/include/numpy/npy_1_7_deprecated_api.h:17:2: warning: #warning "Using deprecated NumPy API, disable it with " "#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-Wcpp]
#warning "Using deprecated NumPy API, disable it with " \
^
mmdet/ops/nms/src/soft_nms_cpu.cpp: In function ‘PyObject* __pyx_pf_5mmdet_3ops_3nms_12soft_nms_cpu_soft_nms_cpu(PyObject*, PyArrayObject*, float, unsigned int, float, float)’:
mmdet/ops/nms/src/soft_nms_cpu.cpp:2497:34: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
__pyx_t_10 = ((__pyx_v_pos < __pyx_v_N) != 0);
^
mmdet/ops/nms/src/soft_nms_cpu.cpp:3008:34: warning: comparison between signed and unsigned integer expressions [-Wsign-compare]
__pyx_t_10 = ((__pyx_v_pos < __pyx_v_N) != 0);
^
x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.5/mmdet/ops/nms/src/soft_nms_cpu.o -o build/lib.linux-x86_64-3.5/mmdet/ops/nms/soft_nms_cpu.cpython-35m-x86_64-linux-gnu.so
copying build/lib.linux-x86_64-3.5/mmdet/ops/nms/soft_nms_cpu.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/nms
copying build/lib.linux-x86_64-3.5/mmdet/ops/roi_align/roi_align_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/roi_align
copying build/lib.linux-x86_64-3.5/mmdet/ops/roi_pool/roi_pool_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/roi_pool
copying build/lib.linux-x86_64-3.5/mmdet/ops/nms/nms_cpu.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/nms
copying build/lib.linux-x86_64-3.5/mmdet/ops/nms/nms_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/nms
copying build/lib.linux-x86_64-3.5/mmdet/ops/dcn/deform_conv_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/dcn
copying build/lib.linux-x86_64-3.5/mmdet/ops/dcn/deform_pool_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/dcn
copying build/lib.linux-x86_64-3.5/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/sigmoid_focal_loss
copying build/lib.linux-x86_64-3.5/mmdet/ops/masked_conv/masked_conv2d_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/masked_conv
Creating /usr/local/lib/python3.5/dist-packages/mmdet.egg-link (link to .)
mmdet 0.6.0+unknown is already the active version in easy-install.pth
Installed /home/morteza/Documents/rajman/Pedestron-master
Processing dependencies for mmdet==0.6.0+unknown
Searching for torch==1.4.0
Best match: torch 1.4.0
Adding torch 1.4.0 to easy-install.pth file
Installing convert-onnx-to-caffe2 script to /usr/local/bin
Installing convert-caffe2-to-onnx script to /usr/local/bin
Using /usr/local/lib/python3.5/dist-packages
Searching for pycocotools==2.0.0
Best match: pycocotools 2.0.0
Processing pycocotools-2.0.0-py3.5-linux-x86_64.egg
pycocotools 2.0.0 is already the active version in easy-install.pth
Using /usr/local/lib/python3.5/dist-packages/pycocotools-2.0.0-py3.5-linux-x86_64.egg
Searching for terminaltables==3.1.0
Best match: terminaltables 3.1.0
Processing terminaltables-3.1.0-py3.5.egg
terminaltables 3.1.0 is already the active version in easy-install.pth
Using /usr/local/lib/python3.5/dist-packages/terminaltables-3.1.0-py3.5.egg
Searching for six==1.14.0
Best match: six 1.14.0
Adding six 1.14.0 to easy-install.pth file
Using /usr/local/lib/python3.5/dist-packages
Searching for matplotlib==1.5.1
Best match: matplotlib 1.5.1
Adding matplotlib 1.5.1 to easy-install.pth file
Using /usr/lib/python3/dist-packages
Searching for numpy==1.18.2
Best match: numpy 1.18.2
Adding numpy 1.18.2 to easy-install.pth file
Installing f2py3.5 script to /usr/local/bin
Installing f2py script to /usr/local/bin
Installing f2py3 script to /usr/local/bin
Using /home/morteza/.local/lib/python3.5/site-packages
Searching for mmcv==0.2.10
Best match: mmcv 0.2.10
Adding mmcv 0.2.10 to easy-install.pth file
Using /usr/local/lib/python3.5/dist-packages
Searching for requests==2.23.0
Best match: requests 2.23.0
Adding requests 2.23.0 to easy-install.pth file
Using /usr/local/lib/python3.5/dist-packages
Searching for opencv-python==3.4.2.17
Best match: opencv-python 3.4.2.17
Adding opencv-python 3.4.2.17 to easy-install.pth file
Using /usr/local/lib/python3.5/dist-packages
Searching for Cython==0.29.16
Best match: Cython 0.29.16
Adding Cython 0.29.16 to easy-install.pth file
Installing cython script to /usr/local/bin
Installing cygdb script to /usr/local/bin
Installing cythonize script to /usr/local/bin
Using /usr/local/lib/python3.5/dist-packages
Searching for addict==2.2.1
Best match: addict 2.2.1
Processing addict-2.2.1-py3.5.egg
addict 2.2.1 is already the active version in easy-install.pth
Using /usr/local/lib/python3.5/dist-packages/addict-2.2.1-py3.5.egg
Searching for PyYAML==3.13
Best match: PyYAML 3.13
Adding PyYAML 3.13 to easy-install.pth file
Using /usr/local/lib/python3.5/dist-packages
Searching for urllib3==1.22
Best match: urllib3 1.22
Adding urllib3 1.22 to easy-install.pth file
Using /usr/local/lib/python3.5/dist-packages
Searching for chardet==3.0.4
Best match: chardet 3.0.4
Adding chardet 3.0.4 to easy-install.pth file
Installing chardetect script to /usr/local/bin
Using /usr/local/lib/python3.5/dist-packages
Searching for certifi==2020.4.5.1
Best match: certifi 2020.4.5.1
Adding certifi 2020.4.5.1 to easy-install.pth file
Using /usr/local/lib/python3.5/dist-packages
Searching for idna==2.6
Best match: idna 2.6
Adding idna 2.6 to easy-install.pth file
Using /usr/local/lib/python3.5/dist-packages
Finished processing dependencies for mmdet==0.6.0+unknown
from pedestron.
Morteza-j8
commented on May 24, 2024
Did you recompile Pedestron after you changed CUDA version ?
That is a different problem. I would suggest first simply changing the CUDA version back to 10.0, compiling Pedestron (just to be on the safe side) and see if it works.
do i open issue for this problem?
from pedestron.
hasanirtiza
commented on May 24, 2024
Yes, you can.
from pedestron.
hasanirtiza
commented on May 24, 2024
$ sudo python3 setup.py developNo CUDA runtime is found, using CUDA_HOME='/usr' Compiling mmdet/ops/nms/src/soft_nms_cpu.pyx because it depends on /usr/local/lib/python3.5/dist-packages/Cython/Includes/numpy/__init__.pxd. [1/1] Cythonizing mmdet/ops/nms/src/soft_nms_cpu.pyx running develop running egg_info writing top-level names to mmdet.egg-info/top_level.txt writing dependency_links to mmdet.egg-info/dependency_links.txt writing mmdet.egg-info/PKG-INFO writing requirements to mmdet.egg-info/requires.txt reading manifest file 'mmdet.egg-info/SOURCES.txt' writing manifest file 'mmdet.egg-info/SOURCES.txt' running build_ext building 'mmdet.ops.nms.soft_nms_cpu' extension 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 -I/home/morteza/.local/lib/python3.5/site-packages/numpy/core/include -I/usr/include/python3.5m -c mmdet/ops/nms/src/soft_nms_cpu.cpp -o build/temp.linux-x86_64-3.5/mmdet/ops/nms/src/soft_nms_cpu.o -Wno-unused-function -Wno-write-strings -DTORCH_API_INCLUDE_EXTENSION_H -DTORCH_EXTENSION_NAME=soft_nms_cpu -D_GLIBCXX_USE_CXX11_ABI=0 -std=c++11 cc1plus: warning: command line option ‘-Wstrict-prototypes’ is valid for C/ObjC but not for C++ In file included from /home/morteza/.local/lib/python3.5/site-packages/numpy/core/include/numpy/ndarraytypes.h:1832:0, from /home/morteza/.local/lib/python3.5/site-packages/numpy/core/include/numpy/ndarrayobject.h:12, from /home/morteza/.local/lib/python3.5/site-packages/numpy/core/include/numpy/arrayobject.h:4, from mmdet/ops/nms/src/soft_nms_cpu.cpp:640: /home/morteza/.local/lib/python3.5/site-packages/numpy/core/include/numpy/npy_1_7_deprecated_api.h:17:2: warning: #warning "Using deprecated NumPy API, disable it with " "#define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION" [-Wcpp] #warning "Using deprecated NumPy API, disable it with " \ ^ mmdet/ops/nms/src/soft_nms_cpu.cpp: In function ‘PyObject* __pyx_pf_5mmdet_3ops_3nms_12soft_nms_cpu_soft_nms_cpu(PyObject*, PyArrayObject*, float, unsigned int, float, float)’: mmdet/ops/nms/src/soft_nms_cpu.cpp:2497:34: warning: comparison between signed and unsigned integer expressions [-Wsign-compare] __pyx_t_10 = ((__pyx_v_pos < __pyx_v_N) != 0); ^ mmdet/ops/nms/src/soft_nms_cpu.cpp:3008:34: warning: comparison between signed and unsigned integer expressions [-Wsign-compare] __pyx_t_10 = ((__pyx_v_pos < __pyx_v_N) != 0); ^ x86_64-linux-gnu-g++ -pthread -shared -Wl,-O1 -Wl,-Bsymbolic-functions -Wl,-Bsymbolic-functions -Wl,-z,relro -Wl,-Bsymbolic-functions -Wl,-z,relro -g -fstack-protector-strong -Wformat -Werror=format-security -Wdate-time -D_FORTIFY_SOURCE=2 build/temp.linux-x86_64-3.5/mmdet/ops/nms/src/soft_nms_cpu.o -o build/lib.linux-x86_64-3.5/mmdet/ops/nms/soft_nms_cpu.cpython-35m-x86_64-linux-gnu.so copying build/lib.linux-x86_64-3.5/mmdet/ops/nms/soft_nms_cpu.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/nms copying build/lib.linux-x86_64-3.5/mmdet/ops/roi_align/roi_align_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/roi_align copying build/lib.linux-x86_64-3.5/mmdet/ops/roi_pool/roi_pool_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/roi_pool copying build/lib.linux-x86_64-3.5/mmdet/ops/nms/nms_cpu.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/nms copying build/lib.linux-x86_64-3.5/mmdet/ops/nms/nms_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/nms copying build/lib.linux-x86_64-3.5/mmdet/ops/dcn/deform_conv_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/dcn copying build/lib.linux-x86_64-3.5/mmdet/ops/dcn/deform_pool_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/dcn copying build/lib.linux-x86_64-3.5/mmdet/ops/sigmoid_focal_loss/sigmoid_focal_loss_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/sigmoid_focal_loss copying build/lib.linux-x86_64-3.5/mmdet/ops/masked_conv/masked_conv2d_cuda.cpython-35m-x86_64-linux-gnu.so -> mmdet/ops/masked_conv Creating /usr/local/lib/python3.5/dist-packages/mmdet.egg-link (link to .) mmdet 0.6.0+unknown is already the active version in easy-install.pth Installed /home/morteza/Documents/rajman/Pedestron-master Processing dependencies for mmdet==0.6.0+unknown Searching for torch==1.4.0 Best match: torch 1.4.0 Adding torch 1.4.0 to easy-install.pth file Installing convert-onnx-to-caffe2 script to /usr/local/bin Installing convert-caffe2-to-onnx script to /usr/local/bin Using /usr/local/lib/python3.5/dist-packages Searching for pycocotools==2.0.0 Best match: pycocotools 2.0.0 Processing pycocotools-2.0.0-py3.5-linux-x86_64.egg pycocotools 2.0.0 is already the active version in easy-install.pth Using /usr/local/lib/python3.5/dist-packages/pycocotools-2.0.0-py3.5-linux-x86_64.egg Searching for terminaltables==3.1.0 Best match: terminaltables 3.1.0 Processing terminaltables-3.1.0-py3.5.egg terminaltables 3.1.0 is already the active version in easy-install.pth Using /usr/local/lib/python3.5/dist-packages/terminaltables-3.1.0-py3.5.egg Searching for six==1.14.0 Best match: six 1.14.0 Adding six 1.14.0 to easy-install.pth file Using /usr/local/lib/python3.5/dist-packages Searching for matplotlib==1.5.1 Best match: matplotlib 1.5.1 Adding matplotlib 1.5.1 to easy-install.pth file Using /usr/lib/python3/dist-packages Searching for numpy==1.18.2 Best match: numpy 1.18.2 Adding numpy 1.18.2 to easy-install.pth file Installing f2py3.5 script to /usr/local/bin Installing f2py script to /usr/local/bin Installing f2py3 script to /usr/local/bin Using /home/morteza/.local/lib/python3.5/site-packages Searching for mmcv==0.2.10 Best match: mmcv 0.2.10 Adding mmcv 0.2.10 to easy-install.pth file Using /usr/local/lib/python3.5/dist-packages Searching for requests==2.23.0 Best match: requests 2.23.0 Adding requests 2.23.0 to easy-install.pth file Using /usr/local/lib/python3.5/dist-packages Searching for opencv-python==3.4.2.17 Best match: opencv-python 3.4.2.17 Adding opencv-python 3.4.2.17 to easy-install.pth file Using /usr/local/lib/python3.5/dist-packages Searching for Cython==0.29.16 Best match: Cython 0.29.16 Adding Cython 0.29.16 to easy-install.pth file Installing cython script to /usr/local/bin Installing cygdb script to /usr/local/bin Installing cythonize script to /usr/local/bin Using /usr/local/lib/python3.5/dist-packages Searching for addict==2.2.1 Best match: addict 2.2.1 Processing addict-2.2.1-py3.5.egg addict 2.2.1 is already the active version in easy-install.pth Using /usr/local/lib/python3.5/dist-packages/addict-2.2.1-py3.5.egg Searching for PyYAML==3.13 Best match: PyYAML 3.13 Adding PyYAML 3.13 to easy-install.pth file Using /usr/local/lib/python3.5/dist-packages Searching for urllib3==1.22 Best match: urllib3 1.22 Adding urllib3 1.22 to easy-install.pth file Using /usr/local/lib/python3.5/dist-packages Searching for chardet==3.0.4 Best match: chardet 3.0.4 Adding chardet 3.0.4 to easy-install.pth file Installing chardetect script to /usr/local/bin Using /usr/local/lib/python3.5/dist-packages Searching for certifi==2020.4.5.1 Best match: certifi 2020.4.5.1 Adding certifi 2020.4.5.1 to easy-install.pth file Using /usr/local/lib/python3.5/dist-packages Searching for idna==2.6 Best match: idna 2.6 Adding idna 2.6 to easy-install.pth file Using /usr/local/lib/python3.5/dist-packages Finished processing dependencies for mmdet==0.6.0+unknown
Something is wrong with your CUDA installation. May be this will help.
By the way can you run some other official PyTorch tutorials on your GPU ?
from pedestron.
Related Issues (20)
- Demo not workingt HOT 1
- Identifier "THCudaCheck" is undefined HOT 1
- Docker image is not working! HOT 4
- Impact of mean_teacher on the training process HOT 1
- CSP pretrained weights HOT 1
- Reproduce resutls on Caltech dataset HOT 3
- Information regarding the training HOT 1
- Image_scale of Caltech while training HOT 6
- ImportError: /pedestron/tools/../mmdet/ops/dcn/deform_conv_cuda.cpython-36m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe26detail37_typeMetaDataInstance_preallocated_32E HOT 1
- RuntimeError: Expected cudaMemcpy(&mask_host[0], mask_dev, sizeof(unsigned long long) * boxes_num * col_blocks, cudaMemcpyDeviceToHost) == cudaSuccess to be true, but got false. (Could this error message be improved? If so, please report an enhancement request to PyTorch.) HOT 1
- Training citypersons with all the instances? HOT 1
- Welcome update to OpenMMLab 2.0
- Runtime error - Training with EuroCity persons HOT 1
- Training Caltech using CSP HOT 1
- What's ignore_other_vru in ECP evaluation? HOT 2
- result has no bbox HOT 5
- mmdet/ops/roi_align/src/roi_align_kernel.cu(145): error: identifier "THCudaCheck" is undefined HOT 1
- Update instruction for 2023 HOT 1
- custom dataset test HOT 1
- Evaluate different pre-trained model
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 pedestron.