You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Cascade R-CNN: Delving into High Quality Object Detection
Abstract
This repo is based on FPN, and completed by YangXue.
Train on COCO train2017 and test on COCO val2017 (coco minival).
Model
Backbone
Train Schedule
GPU
Image/GPU
FP16
Box AP(Mask AP)
test stage
Faster (paper)
R50v1-FPN
1X
8X TITAN XP
1
no
38.3
3
Faster (ours)
R50v1-FPN
1X
8X 2080 Ti
1
no
38.2
3
Faster (Face++)
R50v1-FPN
1X
8X 2080 Ti
2
no
39.1
3
My Development Environment
1、python3.5 (anaconda recommend)
2、cuda9.0 (If you want to use cuda8, please set CUDA9 = False in the cfgs.py file.)
3、opencv(cv2)
4、tfplot
5、tensorflow == 1.12
Download Model
Pretrain weights
1、Please download resnet50_v1, resnet101_v1 pre-trained models on Imagenet, put it to data/pretrained_weights.
2、Or you can choose to use a better backbone, refer to gluon2TF. Pretrain Model Link, password: 5ht9.
Trained weights
Select a configuration file in the folder ($PATH_ROOT/libs/configs/) and copy its contents into cfgs.py, then download the corresponding weights.
Compile
cd $PATH_ROOT/libs/box_utils/cython_utils
python setup.py build_ext --inplace
Train
1、If you want to train your own data, please note:
(1) Modify parameters (such as CLASS_NUM, DATASET_NAME, VERSION, etc.) in $PATH_ROOT/libs/configs/cfgs.py
(2) Add category information in $PATH_ROOT/libs/label_name_dict/lable_dict.py
(3) Add data_name to $PATH_ROOT/data/io/read_tfrecord_multi_gpu.py
2、make tfrecord
cd $PATH_ROOT/data/io/
python convert_data_to_tfrecord_coco.py --VOC_dir='/PATH/TO/JSON/FILE/'
--save_name='train'
--dataset='coco'
3、multi-gpu train
cd $PATH_ROOT/tools
python multi_gpu_train.py
Eval
cd $PATH_ROOT/tools
python eval_coco.py --eval_data='/PATH/TO/IMAGES/'
--eval_gt='/PATH/TO/TEST/ANNOTATION/'
--GPU='0'
Tensorboard
cd $PATH_ROOT/output/summary
tensorboard --logdir=.
