资源算法SE_ResNeXt_3D

SE_ResNeXt_3D

2020-02-24 | |  50 |   0 |   0

SE_ResNeXt_3D

The origin of SENet

Code modified from 2d se-resnext

Note

The first layer was changed to ResNet-like structure due to the high memory cost.

  • Before:

  x = conv_layer(x, filter=64, kernel=[3, 3], stride=1, layer_name=scope+'_conv1')
  x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')
  • After:

  x = Conv3D(filters=self.init_filters, kernel_size=(7, 7, 7), strides=(2, 2, 2), padding='same')(x)
  x = MaxPooling3D(pool_size=(3, 3, 3), strides=(2, 2, 2), padding="same")(x)
  x = Batch_Normalization(x, training=self.training, scope=scope+'_batch1')


上一篇:ResNext-SELayer

下一篇:chainer-resnext

用户评价
全部评价

热门资源

  • TensorFlow-Course

    This repository aims to provide simple and read...

  • seetafaceJNI

    项目介绍 基于中科院seetaface2进行封装的JAVA...

  • mxnet_VanillaCNN

    This is a mxnet implementation of the Vanilla C...

  • DuReader_QANet_BiDAF

    Machine Reading Comprehension on DuReader Usin...

  • Klukshu-Sockeye-...

    KLUKSHU SOCKEYE PROJECTS 2016 This repositor...