Official Code for "Towards Local Visual Modeling for Image Captioning"
Please refer to meshed-memory-transformer
- Annotation. Download the annotation file annotation.zip. Extarct and put it in the project root directory.
- Feature. You can download our ResNeXt-101 feature (hdf5 file) here. Acess code: jcj6.
- evaluation. Download the evaluation tools here. Acess code: jcj6. Extarct and put it in the project root directory.
python train.py --exp_name LSTNet --batch_size 50 --rl_batch_size 100 --workers 4 --head 8 --warmup 10000 --features_path /home/data/coco_grid_feats2.hdf5 --annotation /home/data/m2_annotations --logs_folder tensorboard_logs
python eval.py --batch_size 50 --exp_name LSTNet --features_path /home/data/coco_grid_feats2.hdf5 --annotation /home/data/m2_annotations