BaeHeeSun / APP

Official PyTorch implementation for Make Prompts Adaptable : Bayesian Modeling for Vision-Language Prompt Learning with Data-Dependent Prior [AAAI 2024]

APP

This folder contains the implementation of the APP method on prompt learning.

This code is built on top of CoOp, PLOT, and dassl .

Install Dataset

Please follow the instructions DATASETS.md to construct the datasets.

Run Scripts

The running scripts are in scripts/. cd ./scripts and change the your_data_path and your_work_path in scripts/main.sh Then, you can run the commands bash main.sh DATASET N under scripts/.

DATASET takes as input a dataset name, like caltech101.

N is the number of prompts, such as 4.

Performance