- github:https://github.com/open-mmlab/mmdetection
- paper:https://arxiv.org/abs/1906.07155
一、簡介
- mmdetetion是香港中文大學 MMLab實驗室開源的目標檢測框架， 是一款基於pytorch 深度學習框架搭建的目標檢測庫，包含很多主流的算法，包括anchor、anchor-free， one-stage,two-stage。
二、安裝
-
官方安裝教程：https://github.com/jmu201521121021/mmdetection/blob/master/docs/INSTALL.md
-
不過官方教程還是有些坑， 有些細節需要注意，比如cuda、pytorch版本。本博客主要安裝版本如下, 所有包可以看最後conda的包。
- ubuntu16.04
- cuda9.0
- pytorch1.1
- python3.7
-
具體步驟
1、安裝cuda和Anaconda，可以參考：https://blog.csdn.net/jmu201521121021/article/details/78323032
2、 安裝nccl 2
sudo apt install libnccl2=2.4.8-1+cuda9.0 libnccl-dev=2.4.8-1+cuda9.0
3、 新建虛擬環境（所有conda 或pip安裝都需要在這個環境下）
conda create -n open-mmlab python=3.7 -y
source activate open-mmlab
4、安裝 pytorch
conda install pytorch torchvision cudatoolkit=9.0 -c pytorch
5、安裝依賴包
pip install mmcv
pip install matplotlib
pip install seaborn
6、 mmdetection
git clone https://github.com/open-mmlab/mmdetection.git
cd mmdetection
python setup.py develop
# or "pip install -v -e ."
7、test
在demo文件下新建 test_retinaNet_res50.py
from mmdet.apis import init_detector, inference_detector, show_result
import mmcv
config_file = '../configs/retinanet_r50_fpn_1x.py'
checkpoint_file = '../checkpoints/retinanet_r50_fpn_1x_20181125-7b0c2548.pth'
# build the model from a config file and a checkpoint file
model = init_detector(config_file, checkpoint_file, device='cuda:0')
# test a single image and show the results
img = 'demo.jpg' # or img = mmcv.imread(img), which will only load it once
result = inference_detector(model, img)
# visualize the results in a new window
show_result(img, result, model.CLASSES)
# or save the visualization results to image files
show_result(img, result, model.CLASSES, out_file='result.jpg')
三、conda list
#
# Name Version Build Channel
_libgcc_mutex 0.1 main
addict 2.2.1 <pip>
blas 1.0 mkl
ca-certificates 2019.5.15 1
certifi 2019.6.16 py37_1
cffi 1.12.3 py37h2e261b9_0
chardet 3.0.4 <pip>
cuda90 1.0 h6433d27_0 pytorch
cudatoolkit 9.0 h13b8566_0
cycler 0.10.0 py37_0
Cython 0.29.13 <pip>
dbus 1.13.6 h746ee38_0
decorator 4.4.0 <pip>
expat 2.2.6 he6710b0_0
fontconfig 2.13.0 h9420a91_0
freetype 2.9.1 h8a8886c_1
glib 2.56.2 hd408876_0
gst-plugins-base 1.14.0 hbbd80ab_1
gstreamer 1.14.0 hb453b48_1
icu 58.2 h9c2bf20_1
idna 2.8 <pip>
imagecorruptions 1.0.0 <pip>
imageio 2.5.0 <pip>
intel-openmp 2019.4 243
jpeg 9b h024ee3a_2
kiwisolver 1.1.0 py37he6710b0_0
libedit 3.1.20181209 hc058e9b_0
libffi 3.2.1 hd88cf55_4
libgcc-ng 9.1.0 hdf63c60_0
libgfortran-ng 7.3.0 hdf63c60_0
libpng 1.6.37 hbc83047_0
libstdcxx-ng 9.1.0 hdf63c60_0
libtiff 4.0.10 h2733197_2
libuuid 1.0.3 h1bed415_2
libxcb 1.13 h1bed415_1
libxml2 2.9.9 hea5a465_1
matplotlib 3.1.1 py37h5429711_0
mkl 2019.4 243
mkl-service 2.0.2 py37h7b6447c_0
mkl_fft 1.0.14 py37ha843d7b_0
mkl_random 1.0.2 py37hd81dba3_0
mmcv 0.2.13 <pip>
mmdet 1.0rc0+c5c7ef9 <pip>
ncurses 6.1 he6710b0_1
networkx 2.3 <pip>
ninja 1.9.0 py37hfd86e86_0
numpy 1.16.4 py37h7e9f1db_0
numpy-base 1.16.4 py37hde5b4d6_0
olefile 0.46 py37_0
opencv-python 4.1.1.26 <pip>
openssl 1.1.1c h7b6447c_1
pandas 0.25.1 <pip>
pcre 8.43 he6710b0_0
pillow 6.1.0 py37h34e0f95_0
pip 19.2.2 py37_0
pycocotools 2.0.0 <pip>
pycparser 2.19 py37_0
pyparsing 2.4.2 py_0
pyqt 5.9.2 py37h05f1152_2
python 3.7.4 h265db76_1
python-dateutil 2.8.0 py37_0
pytorch 1.1.0 py3.7_cuda9.0.176_cudnn7.5.1_0 pytorch
pytz 2019.2 py_0
PyWavelets 1.0.3 <pip>
PyYAML 5.1.2 <pip>
qt 5.9.7 h5867ecd_1
readline 7.0 h7b6447c_5
requests 2.22.0 <pip>
scikit-image 0.15.0 <pip>
scipy 1.3.1 <pip>
seaborn 0.9.0 <pip>
setuptools 41.0.1 py37_0
sip 4.19.8 py37hf484d3e_0
six 1.12.0 py37_0
sqlite 3.29.0 h7b6447c_0
tk 8.6.8 hbc83047_0
torchvision 0.3.0 py37_cu9.0.176_1 pytorch
tornado 6.0.3 py37h7b6447c_0
urllib3 1.25.3 <pip>
wheel 0.33.4 py37_0
xz 5.2.4 h14c3975_4
zlib 1.2.11 h7b6447c_3
zstd 1.3.7 h0b5b093_0