MxnetResource

Tutorial

mxnet-gluon_tutorial by SherlockLiao

Application

Densenet by Nicatio.

Densenet (supporting ImageNet) by Xiong Lin.

Dual Path Net by miraclewkf

Resnet by tornadomeet

Focal loss by unsky.

FCIS by msracver.

MobileNet

Imagenet models

Interesting Architecture

Feature Pyramid Network mAP 0.7372

mxnet initializer

Uniform Initializes weights with random values uniformly sampled from a given range. Normal Initializes weights with random values sampled from a normal distribution with a mean of zero and standard deviation of sigma. Load Initializes variables by loading data from file or dict. Mixed Initialize parameters using multiple initializers. Zero Initializes weights to zero. One Initializes weights to one. Constant Initializes the weights to a scalar value. Orthogonal Initialize weight as orthogonal matrix. Xavier Returns an initializer performing “Xavier” initialization for weights. MSRAPrelu Initialize the weight according to a MSRA paper. Bilinear Initialize weight for upsampling layers. FusedRNN Initialize parameters for fused rnn layers.

mxnet optimizer