Skip to content

Keras2ncnn Release v0.1.1

Pre-release
Pre-release
Compare
Choose a tag to compare
@MarsTechHAN MarsTechHAN released this 08 Dec 16:43
· 67 commits to master since this release
0.1.1
fac474a
This commit was created on GitHub.com and signed with GitHub’s verified signature. The key has expired.
GPG key ID: 4AEE18F83AFDEB23
Expired
Learn about vigilant mode.

Feature Highlights

  • Keras h5df to ncnn param/bin file converter
  • Support a variety of models, sequential or not, TF1 or TF2 !
  • New weight indexing method, better model compatibility !
  • Emended debugger for comparing accuracy with ncnn. (Working on)

Supported Op

  • InputLayer
  • Conv2D (With fused relu, sigmoid activation)
  • Conv2DTranspose (With fused relu, sigmoid activation)
  • DepthwiseConv2D
  • Add
  • Multiply
  • ZeroPadding2D
  • ReLU
  • LeakyReLU
  • UpSampling2D
  • Concatenate
  • GlobalAveragePooling2D
  • MaxAveragePooling2D
  • AveragePooling2D
  • MaxPooling2D
  • BatchNormalization
  • Dense (With fused relu, sigmoid, and non-fused softmax activation)
  • Activation (Support relu, sigmoid)
Assets 4
Loading