- HAPZero: Hierarchical Attribute Prompting Based Zero-Shot Learning for Pest Recognition This repository contains the reference code for the paper "HAPZero: Hierarchical Attribute Prompting Based Zero-Shot Learning for Pest Recognition".
Python 3.6.7PyTorch = 1.7.0- All experiments are performed with one RTX 4090 GPU.
- Dataset: please download the dataset, i.e., IP102 to the dataset root path on your machine, Datasets can be download from Xian et al. (CVPR2017) and take them into dir
./datasets/. - Data split: dataset split files for the three groups are placed at
./data/xlsa19/split - Attribute w2v: download from link IP102 Att and place it in
./data/xlsa/w2v. - Download pretranined vision Transformer as the vision encoder and place it in
./pretrain_model_vit.
Before running commands, you can set the hyperparameters in config on different datasets:
config/ip102.yaml #IP102
Train:
python train.pyEval:
python test.pyYou can test our trained model: GroupA, [GroupB](please wait), [GroupC](please wait).
We thank the following repos providing helpful components in our work. PSVMA