Anish
panoContext_img_train.t7 : 414 examples Traceback (most recent call last): File "torch2pytorch_data.py", line 83, in <module> cvt2png(os.path.join(DATA_DIR, 'train'), train_pats, train_pano_map) File "torch2pytorch_data.py", line 65, in cvt2png imgs = load_lua(th_path).numpy() File "/opt/anaconda3/lib/python3.6/site-packages/torch/utils/serialization/read_lua_file.py",...
dataset_generator.py", line 514, in <module> generate_synthetic_dataset(args) File "dataset_generator.py", line 486, in generate_synthetic_dataset syn_img_files, anno_files = gen_syn_data(img_files, labels, img_dir, anno_dir, args.scale, args.rotation, args.dontocclude, args.add_distractors) File "dataset_generator.py", line 450, in gen_syn_data p.map(partial_func,...
can someone post the code on testing the model on a single image straightaway
Hi @KumapowerLIU What do you try to achieve with this feature equalization, are you normalizing the pixels to get rid of the checkerboard effect during pixel generation,
Hi @ebennequin, Thanks for this elegant code base, some questions(can be a feature request) 1) Can we add new backbones like (ViT, densenet, Convnext etc...)? 2) Building functionalities for model...