MCPcopy Create free account
hub / github.com/VCIP-RGBD/DFormer / extract_feat

Method extract_feat

mmseg/models/segmentors/encoder_decoder.py:65–70  ·  view source on GitHub ↗

Extract features from images.

(self, img)

Source from the content-addressed store, hash-verified

63 self.auxiliary_head = builder.build_head(auxiliary_head)
64
65 def extract_feat(self, img):
66 """Extract features from images."""
67 x = self.backbone(img)
68 if self.with_neck:
69 x = self.neck(x)
70 return x
71
72 def encode_decode(self, img, img_metas):
73 """Encode images with backbone and decode into a semantic segmentation

Callers 2

encode_decodeMethod · 0.95
forward_trainMethod · 0.95

Calls

no outgoing calls

Tested by

no test coverage detected