FCOS: Fully Convolutional One-Stage Object Detection
This is an unofficial implementation of FCOS in a gluon-cv style, we implemented this anchor-free framework in a fully Gluon API, please stay tuned!
Model | Backbone | Train Size | Batch Size | AP(val) |
---|---|---|---|---|
fcos_resnet50_v1_coco | ResNet50-V1 | 800 | 1 | - |
fcos_resnet50_v1b_coco | ResNet50-V1b | 800 | 1 | 33.1 |
fcos_resnet101_v1d_coco | ResNet101-V1d | 800 | 1 | 37.5 |
Note: To be update.
10.0
and mxnet 1.4.0
.sudo pip3 install mxnet-cu100==1.4.0.post0
setup.py
.cd fcos-gluon-cv
sudo python3 setup.py build
sudo python3 setup.py install
COCO2017
datasets follow the official tutorials and create a soft link.ln -s $DOWNLOAD_PATH ~/.mxnet/datasets/coco
You can also download from cocodataset and execute the command above.
More preparations can also refer to GluonCV.
All experiments are performed on 8 * 2080ti
GPU with Python3.5
, cuda10.0
and cudnn7.5.0
.
* Model : $ROOT/gluoncv/model_zoo/fcos
* Train & valid scripts : $ROOT/scripts/detection/fcos
* Data Transform : $ROOT/gluoncv/data/transform/presets
fcos_resnet50_v1b_coco
with:python3 train_fcos.py --network resnet50_v1b --gpus 0,1,2,3,4,5,6,7 --num-workers 32 --batch-size 8 --log-interval 10
fcos_resnet50_v1b_coco
with:python3 eval_fcos.py --network resnet50_v1b --gpus 0,1,2,3,4,5,6,7 --num-workers 32 --pretrained $SAVE_PATH/XXX.params