After a few iterations of pruning, you’ll get a model that much smaller than its original size. Finally, you need to do a transformation of the model to get a final model.
vai_p_tensorflow \
--action=transform \
--input_ckpt=model.ckpt-10000 \
--output_ckpt=dense.ckpt
It should be noted that transformation is only required after all iterations of pruning have been completed and you do not need to run transform command between each iteration of pruning.
Now you have a GraphDef file containing the architecture of the pruned model and a checkpoint file saving trained weights. For prediction or quantization, you need to merge these two files into a single pb file. For more details about freezing, see https://www.tensorflow.org/guide/extend/model_files#freezing.