How to get weights format from TensorFlow .pb model?

8
votes

I want to reorganize the nodes of tensorflow .pb model,so I first get NodeDef from GraphDef, and get attr use NodeDef.attr().for the node of "Conv2D". I can get parameters such as strides,padding,data_format,use_cudnn_on_gpu from attr, but cann't get the weights format parameters. The language I use is c++. How to get it! Thank you!

1
c++tensorflowmodel

1 Answers

4
votes

Conv2D has two inputs: the first one is data and the second one is filter (or weights), so you can simply check the format of the second input of Conv2D. If you are using C++, you can try this:

# Assuming inputs: conv2d_node, node_map.
filter_node_name = conv2d_node.input(1)
filter_node = node_map[filter_node_name]
# You might need to check identity node here.
# Get the shape of filter_node using NodeDef.attr()