Closed liyangliu closed 4 years ago
Dear Liyang,
There is a parameter '--scores_field', with default='cls_prob_reshape', which is the cls_prob before the rescaling. This is the one used in experiments. We experimented with the scaled scores, but their performance was lower.
Hi, @jshtok,
In the paper the foreground probability and background probability are computed as follows, And actually in the code you seem to output another probability by adding a softmax activation after the above probability scaled by cfg.network.SOFTMAX_MUL during training https://github.com/jshtok/RepMet/blob/d5b13e01940bbb7ed59dd1ff073e03c0808f76c0/fpn/symbols/resnet_v1_101_fpn_dcn_rcnn_oneshot_v3.py#L1159-L1160 and in testing you output two sets of probability, one is the original one as in the paper cls_score_orig, and the other is scaled by cfg.network.SOFTMAX_MUL cls_prob. https://github.com/jshtok/RepMet/blob/d5b13e01940bbb7ed59dd1ff073e03c0808f76c0/fpn/symbols/resnet_v1_101_fpn_dcn_rcnn_oneshot_v3.py#L1253-L1261 So what probability do you use for the final output detection results? Thanks.