Open MitraTj opened 4 years ago
Can't you just do something like
features = model.backbone(images.tensors)
feat = features[2]
?
Yes, but the problem is the error happens for this line: detections, detector_losses = self.roi_heads(feat, proposals, images.image_sizes, targets)
I want to extract the third layer of feature pyramid from
features = self.backbone(images.tensors) in generalized_rcnn.py
any help please?