HCCAN

This is an implementation of HCCAN.

Update

Some updates and corrections, please see update.md

Installation

Clone this repository. git clone https://github.com/cutexin66/HCCAN

Getting Started

Please refer to GETTING_STARGTED.md to learn how to prepare the datasets and pretrained checkpoints.

Pre_trained Model

The models with ResNet-50 backbone is available in [Gdrive]

	RefCOCO			RefCOCO+			RefCOCOg			Flickr30k
	val	testA	testB	val	testA	testB	g-val	u-val	u-test	test
R-50	83.61	86.66	78.57	69.90	74.96	59.33	71.53	71.49	71.84	79.47

Training and Evaluation

1. Training

   CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --use_env train.py --batch_size 8 --lr_bert 0.00001 --aug_crop --aug_scale --aug_translate --backbone resnet50 --detr_model ./checkpoints/detr-r50-unc.pth --bert_enc_num 12 --detr_enc_num 6 --dataset unc --max_query_len 20 --output_dir outputs/unc_r50 --epochs 90 --lr_drop 60
   

   We recommend to set --max_query_len 40 for RefCOCOg, and --max_query_len 20 for other datasets.

   We recommend to set --epochs 180 (--lr_drop 120 acoordingly) for RefCOCO+, and --epochs 90 (--lr_drop 60 acoordingly) for other datasets.

2. Evaluation

   CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 --use_env eval.py --batch_size 8 --num_workers 4 --bert_enc_num 12 --detr_enc_num 6 --backbone resnet50 --dataset unc --max_query_len 20 --eval_set val --eval_model ./outputs/unc_r50/best_checkpoint.pth --output_dir ./outputs/unc_r50
   

Acknowledge

This codebase is partially based on TransVG and DETR.