Open qinliangql opened 11 months ago
Hi, were you able to run the command below in the inference sec? If I remember correct, that should produce the numbers in the table
modelname=rigidmask-sf
CUDA_VISIBLE_DEVICES=1 python submission.py --dataset sintel_mrflow_val --datapath path-to-sintel-training --outdir ./weights/$modelname/ --loadmodel ./weights/$modelname/weights.pth --testres 1.5 --refine
python eval/eval_seg.py --path weights/$modelname/ --dataset sintel
python eval/eval_sf.py --path weights/$modelname/ --dataset sintel
Hello, may I ask which sequences of Sintel were tested in the test results of Sintel in the paper? I tested all the sequences of Sintel and obtained a BG IOU result of 76, instead of the 86 in Table 1 of the paper