hub / github.com/VincentHancoder/SSGD / PatchEmbed

Class PatchEmbed

mmdet/models/utils/transformer.py:134–257 · view source on GitHub ↗

Image to Patch Embedding. We use a conv layer to implement PatchEmbed. Args: in_channels (int): The num of input channels. Default: 3 embed_dims (int): The dimensions of embedding. Default: 768 conv_type (str): The config dict for embedding conv layer ty

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 3

test_patch_embedFunction · 0.90

__init__Method · 0.85

Calls

no outgoing calls

Tested by 1

test_patch_embedFunction · 0.72