TF-Slim > Variables > regular variables / local (transient) variables / model variables / non-model variables


動作環境
GeForce GTX 1070 (8GB)
ASRock Z170M Pro4S [Intel Z170chipset]
Ubuntu 14.04 LTS desktop amd64
TensorFlow v0.11
cuDNN v5.1 for Linux
CUDA v8.0
Python 2.7.6
IPython 5.1.0 -- An enhanced Interactive Python.

TF-Slimを使っていると、以下のvariablesがあるようだ。

  • TensorFlow標準Variables (参考)
    • regular variables
    • local (transient) variables
  • TF-Slim Variablesで加わったもの (doc)
    • model variables
    • non-model variables

Model variables are trained or fine-tuned during learning and are loaded from a checkpoint during evaluation or inference. Examples include the variables created by a slim.fully_connected or slim.conv2d layer.

...

Non-model variables are all other variables that are used during learning or evaluation but are not required for actually performing inference. For example, the global_step is a variable using during learning and evaluation but it is not actually part of the model.

TF-SlimのNon-model variablesとTensorFlowのlocal variablesの区別は未消化。

したいことはweightとbiasの出力。