vgg_19 slim model a frozen.pb graph?

Question

I downloaded the vgg_19_2016_08_28.tar.gz and extracted a vgg-19.pb graph. I am using this for tf2onnx. However, this seems to have some dynamic parameters and hence tf2onnx if failing. I want to check if the vgg-19.pb is a frozen graph, if not how can I get a frozen vgg_19.pb graph?

Same question for tensorflow_inception_graph - inception_v3_2016_08_28.tar.gz

Same question for resnet - resnet_v1_50_2016_08_28.tar.gz

All downloaded from here - https://github.com/tensorflow/models/tree/master/research/slim#pre-trained-models

Answer 1

To convert TF models to ONNX you need to freeze the graph. The TensorFlow tool to freeze the graph is https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/tools/freeze_graph.py

For example

 python -m tensorflow.python.tools.freeze_graph \
   --input_graph=my_checkpoint_dir/graphdef.pb \
   --input_binary=true \
   --output_node_names=output \
   --input_checkpoint=my_checkpoint_dir \
   --output_graph=tests/models/fc-layers/frozen.pb 

To find the inputs and outputs for the TensorFlow graph the model developer will know or you can consult TensorFlow's summarize_graph tool (https://github.com/tensorflow/tensorflow/tree/master/tensorflow/tools/graph_transforms), for example:

summarize_graph --in_graph=tests/models/fc-layers/frozen.pb