search

longcw / faster_rcnn_pytorch

Faster RCNN with PyTorch
MIT License
1.7k stars 466 forks source link

is it using ground-truth box information in test time? #43

Closed rimchang closed 6 years ago

rimchang commented 6 years ago

proposal_target_layer.py

65 all_rois = np.vstack((all_rois, \ 66 np.hstack((zeros, np.vstack((gt_easyboxes[:, :-1], jittered_gt_boxes[:, :-1]))))))

I think using ground-truth box as candidate box in test time I can't find any test time proposal code in this repo Is it correct? is It wrong evaluation?

proposal_target_layer.py

179 labels = labels[keep_inds]

I think "labels = labels[keep_inds]" is also using ground-truth information because proposal_target_layer returns only 256 sampled rois( it is filtered by IOU then it is sampled)

Is it correct evaluation? do i misunderstand? I am not good at English. Sorry

rimchang commented 6 years ago

i'm sorry I really misunderstanded this repo not use ground-truth information in test tiem