PreciseRoIPooling
PreciseRoIPooling copied to clipboard
vacancy
Precise RoI Pooling with coordinate gradient support, proposed in the paper "Acquisition of Localization Confidence for Accurate Object Detection" (https://arxiv.org/abs/1807.11590).
I create setup.py for toech version like this: ``` import os import glob import torch from torch.utils.cpp_extension import CUDA_HOME from torch.utils.cpp_extension import CppExtension from torch.utils.cpp_extension import CUDAExtension from setuptools import...
Hi, I tried to execute another GitHub repo [dissect](https://github.com/davidbau/dissect) which uses your product. However, it shows error: ``` Traceback (most recent call last): File "./dissect_continual-master/netdissect/upsegmodel/prroi_pool/functional.py", line 22, in verbose=False File...
I am facing this error I am using gcc version greater then 11 maybe that is the issue ?
/home/c506plus/anaconda3/envs/transt/bin/python3.7 /home/c506plus/wq/TransT/AlphaRefine/demo.py Select a ROI and then press SPACE or ENTER button! Cancel the selection process by pressing c button! pumping /home/c506plus/wq/datasets/OTB2015/Basketball/img/0001.jpg /home/c506plus/anaconda3/envs/transt/lib/python3.7/site-packages/torch/nn/functional.py:2506: UserWarning: Default upsampling behavior when mode=bilinear is...
Hi prroi_pooling_gpu.c seems not support to pytorch1.11 and pytorch1.12. It has have the following questions： RuntimeError: Error building extension '_prroi_pooling': [1/3] /usr/local/cuda/bin/nvcc -DTORCH_EXTENSION_NAME=_prroi_pooling -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /usr/local/lib/python3.7/dist-packages/torch/include -isystem...
I get into the following error when running in the latest stable version of PyTorch, which is 1.11 with Cuda toolkit 11.3. It seems the THC namespace is not recognized...
Hi! I have got a 3090 GPU. However, I find some problems when I compile DCN The system is Ubuntu 18.04, the version of PyTorch is 1.7.0. the problem is...
when I run "output = _prroi_pooling.prroi_pooling_forward_cuda(features, rois, *params)" ,I get the debug "cudaCheckError() failed: initialization error".
Is there any plan to achieve CPU version？ _Originally posted by @cybaol in https://github.com/vacancy/PreciseRoIPooling/issues/57#issuecomment-972750666_ I would also be interested to know please
