To setup repository, please follow these instructions:

Setup Faster R-CNN using instructions given in https://github.com/jwyang/faster-rcnn.pytorch
Download pre-trained weights for resnet-50 for image feature extractor and follow instructions given in image_model
Download pretrained weights for resnet-50 for sketch feature extractor and metadata: sketch_model
Store the downloaded data in ../data folder
Download the models from here

Download and Process QuickDraw

Download quickdraw dataset here and create the pickle file [processed_quick_draw_paths_common_classes.pkl] by running following commands:

python read_store_quick_draw.py
python get_train_test_quick_draw.py
python get_common_classes.py

Enter default --sketch-path and --sketch_class_2_label paths in train and test files
To train - Run: python train_val_sketch_oneshot.py --dataset coco --net res50 --cuda --seen 7 --nw 10 --bs 10
To test - Run: python test_net_oneshot.py --dataset coco --net res50 --cuda --seen 7 --s <session> --checkepoch <epoch> --p <checkpoint>

Name		Name	Last commit message	Last commit date
Latest commit History 5 Commits
cfgs		cfgs
lib		lib
README.MD		README.MD
_init_paths.py		_init_paths.py
check_image.py		check_image.py
cls_utils.py		cls_utils.py
coco_class_map.pkl		coco_class_map.pkl
explore.ipynb		explore.ipynb
get_common_classes.py		get_common_classes.py
get_train_test_quick_draw.py		get_train_test_quick_draw.py
ratio_index.pkl		ratio_index.pkl
ratio_list.pkl		ratio_list.pkl
read_store_quick_draw.py		read_store_quick_draw.py
readme.local		readme.local
test_cat_list.pkl		test_cat_list.pkl
test_compare.py		test_compare.py
test_net_oneshot.py		test_net_oneshot.py
test_net_oneshot_voc.py		test_net_oneshot_voc.py
test_ratio_index.pkl		test_ratio_index.pkl
test_ratio_list.pkl		test_ratio_list.pkl
train_val_sketch_early_fusion.py		train_val_sketch_early_fusion.py
train_val_sketch_oneshot.py		train_val_sketch_oneshot.py