Skip to main content

Keras implementation of MixNets of any configuration.

Project description

Keras MixNets: Mixed Depthwise Convolutional Kernels

Keras Implementation of MixNets from the paper MixNets: : Mixed Depthwise Convolution Kernels.

Code ported from the official codebase https://github.com/tensorflow/tpu/blob/master/models/official/mnasnet/mixnet

Mixed Depthwise Convolutional Kernel

From the above paper, a Mixed Convolution is a group of convolutions with varying filter sizes. The paper suggests that [3x3, 5x5, 7x7] can be used safely without any loss in performance (and possible increase in performance), while a 9x9 or 11x11 may degrade performance if used without proper architecture search.

Usage

Due to the use of Model Subclassing, the keras model built *cannot be deserialized using load_model. You must build the model each time. tf.keras supports writing Layers which have additional Layers within them, but as Keras itself does not support it yet, these models cannot be deserialized using load_model.

from keras_mixnets import MixNetSmall  # Medium and Large can also be used

model = MixNetSmall((224, 224, 3), include_top=True)

Weights

Weights for these models have not been ported yet from Tensorflow.

Requirements

  • Tensorflow 1.14+ (Not 2.x)
  • Keras 2.2.4+

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

keras_mixnets-0.1.0-py2.py3-none-any.whl (14.1 kB view details)

Uploaded Python 2 Python 3

File details

Details for the file keras_mixnets-0.1.0-py2.py3-none-any.whl.

File metadata

  • Download URL: keras_mixnets-0.1.0-py2.py3-none-any.whl
  • Upload date:
  • Size: 14.1 kB
  • Tags: Python 2, Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/1.13.0 pkginfo/1.3.2 requests/2.19.1 setuptools/41.0.1 requests-toolbelt/0.8.0 tqdm/4.28.1 CPython/3.5.2

File hashes

Hashes for keras_mixnets-0.1.0-py2.py3-none-any.whl
Algorithm Hash digest
SHA256 9b67bd31a56a4a8b95da151f1e2791dc07ebc801231eb63fe3f4c6b95e8d3518
MD5 f2f0cf4bc1422e851f5ce3af1f06a847
BLAKE2b-256 51e4d653aad41c7b10cdeb0dd762d584cc8b5cdacbe71f4796e060661eac6518

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page