Vo Tran Hai Anh

EMA model forward

1

``` # model forward in online mode (student) x = self.encoder(src, mask, **kwargs)['encoder_out'] # fetch the last layer outputs if trg is None: return x # model forward in offline...

Implementation issue

4

I used this config [e2e_mask_rcnn_R_101_FPN_4x_voc_coco_aug_cocostyle] to retrain and seems like the model is not trained correctly with the two new losses for mask ?, After training the result for masks...