mobilenet model of tensorflow

Usage no npm install needed!

<script type="module">
  import pipcookPluginsTensorflowMobilenetModelDefine from 'https://cdn.skypack.dev/@pipcook/plugins-tensorflow-mobilenet-model-define';




This plugin defines a image classification model. This model is mobilenet. The model is built using python tensorflow.

Required Parameters

Parameter Type Description

Optional Parameters

Parameter Type Default Value Description
loss string categorical_crossentropy the loss function to be defined. Look more
metrics string[] [ 'accuracy' ] metrics used to evaluate model. Look more
learningRate number 0.001 base learning rate for Adam
decay number 0.05 decay rate for Adam
freeze boolean false Whether to freeze first several layers
labelMap object null label map, only specified when recoverPath is provided
recoverPath string null Recover path of pretrained model


"modelDefine": {
  "package": "@pipcook/plugins-tensorflow-mobilenet-model-define",
  "params": {
    "freeze": true