Unable to resolve requirements

[OShapovalov]

I am trying to reproduce your results, but can't reproduce your environment. Could you provide versions for mmdetection and mmcv? If you provide full conda env, it would be great.

[yuguangnudt]

I am trying to reproduce your results, but can't reproduce your environment. Could you provide versions for mmdetection and mmcv? If you provide full conda env, it would be great.

Package Version
addict 2.2.1
albumentations 0.3.3
certifi 2019.9.11
chardet 3.0.4
cycler 0.10.0
Cython 0.29.13
decorator 4.4.0
h5py 2.10.0
idna 2.8
imagecorruptions 1.0.0
imageio 2.6.1
imgaug 0.2.5
joblib 0.14.0
Keras 2.3.1
Keras-Applications 1.0.8
Keras-Preprocessing 1.1.0
kiwisolver 1.1.0
matplotlib 3.1.1
mmcv 0.2.14
mmdet 1.0rc0+b287273
networkx 2.3
numpy 1.17.2
opencv-contrib-python 4.1.1.26
opencv-python-headless 4.1.1.26
Pillow 6.2.0
pip 19.2.3
pkg-resources 0.0.0
pycocotools 2.0.0
pyparsing 2.4.2
pypng 0.0.20
python-dateutil 2.8.0
PyWavelets 1.0.3
PyYAML 5.1.2
raft 1.4.1.3
requests 2.22.0
scikit-image 0.15.0
scikit-learn 0.21.3
scipy 1.3.1
setuptools 41.4.0
Shapely 1.6.4.post2
six 1.12.0
terminaltables 3.1.0
torch 1.1.0
torchvision 0.3.0
urllib3 1.25.6
wheel 0.33.6

You can refer to the package list in my environment. Note that the version of mmdetection we were using at the time was v1.0rc0, and its installation may be different from the latest. You can run the program strictly according to our version, or you can try the later versions of mmdetection and Pytorch. Good luck!