The dataset is used in the paper "EasyDAM_V4: Guided-GAN based cross-species data labeling for fruit detection with significant shape difference". (in Press)
Please fill out this form to get the download link.
We also provide examples of automatic labeling images as follows.
Clone this repo.
git clone https://github.com/I3-Laboratory/EasyDAM_dataset
Create a new conda environment and activate the environment.
conda create --name EasyDAM_V4 python=3.6
conda activate EasyDAM_V4
Install pytorch 0.4.1 and COCOAPI.
conda install pytorch=0.4.1 torchvision -c pytorch
git clone https://github.com/cocodataset/cocoapi.git $COCOAPI
cd $COCOAPI/PythonAPI
make
python setup.py install --user
Install the requirements.
pip install -r requirements.txt
Compile deformable convolutional (from DCNv2).
cd $EasyDAM_dataset/CenterNet/src/lib/models/networks/DCNv2
./make.sh
We support demo for automatic labeling.
First, download the pretrained models and put them in EasyDAM_dataset/CenterNet/exp/.
Then, run:
python demo.py ctdet --demo /path/to/image --load_model ../models/ctdet_coco_dla_2x.pth