MCPcopy Index your code
hub / github.com/DylanWusee/pointconv / feature_encoding_layer

Function feature_encoding_layer

PointConv.py:78–133  ·  view source on GitHub ↗

Input: xyz: (batch_size, ndataset, 3) TF tensor feature: (batch_size, ndataset, channel) TF tensor npoint: int32 -- #points sampled in farthest point sampling sigma: float32 -- KDE bandwidth K: int32 -- how many points in each local region

(xyz, feature, npoint, radius, sigma, K, mlp, is_training, bn_decay, weight_decay, scope, bn=True, use_xyz=True)

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 3

get_modelFunction · 0.90
get_modelFunction · 0.90
PointConv.pyFile · 0.85

Calls 2

weight_net_hiddenFunction · 0.85
nonlinear_transformFunction · 0.85

Tested by

no test coverage detected