- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I am using the following page to export an inference graph of GNMT from Tensorflow:
I have already applied the patch to the commit hash provided in the tutorial. Once training the model, I ran inference with the recommended command:
python3 -m nmt.nmt \ --src=de \ --tgt=en \ --ckpt=/tmp/nmt_out/translate.ckpt \ --hparams_path=/home/khalique/tf_github/nmt/nmt/standard_hparams/wmt16_gnmt_4_layer.json \ --vocab_prefix=/tmp/nmt_model/vocab.bpe.32000 \ --out_dir="" \ --dump_inference_model \ --infer_mode beam_search \ --path_to_dump /tmp/nmt_infer
and received the following error:
Dumping inference graph to /tmp/nmt_infer Dumping done! Freezing GNMT graph with output node index_to_string_Lookup... WARNING:tensorflow:From /home/khalique/tf_github/nmt/nmt/inference.py:128: convert_variables_to_constants (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.compat.v1.graph_util.convert_variables_to_constants` W1202 11:28:43.727387 139826626107136 deprecation.py:323] From /home/khalique/tf_github/nmt/nmt/inference.py:128: convert_variables_to_constants (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.compat.v1.graph_util.convert_variables_to_constants` WARNING:tensorflow:From /home/khalique/.local/lib/python3.5/site-packages/tensorflow/python/framework/graph_util_impl.py:270: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.compat.v1.graph_util.extract_sub_graph` W1202 11:28:43.727668 139826626107136 deprecation.py:323] From /home/khalique/.local/lib/python3.5/site-packages/tensorflow/python/framework/graph_util_impl.py:270: extract_sub_graph (from tensorflow.python.framework.graph_util_impl) is deprecated and will be removed in a future version. Instructions for updating: Use `tf.compat.v1.graph_util.extract_sub_graph` Traceback (most recent call last): File "/usr/lib/python3.5/runpy.py", line 184, in _run_module_as_main "__main__", mod_spec) File "/usr/lib/python3.5/runpy.py", line 85, in _run_code exec(code, run_globals) File "/home/khalique/tf_github/nmt/nmt/nmt.py", line 732, in <module> tf.app.run(main=main, argv=[sys.argv[0]] + unparsed) File "/home/khalique/.local/lib/python3.5/site-packages/tensorflow/python/platform/app.py", line 40, in run _run(main=main, argv=argv, flags_parser=_parse_flags_tolerate_undef) File "/home/khalique/.local/lib/python3.5/site-packages/absl/app.py", line 299, in run _run_main(main, args) File "/home/khalique/.local/lib/python3.5/site-packages/absl/app.py", line 250, in _run_main sys.exit(main(argv)) File "/home/khalique/tf_github/nmt/nmt/nmt.py", line 725, in main run_main(FLAGS, default_hparams, train_fn, inference_fn, inference_dump) File "/home/khalique/tf_github/nmt/nmt/nmt.py", line 684, in run_main inference_dump(ckpt, path_to_dump, hparams) File "/home/khalique/tf_github/nmt/nmt/inference.py", line 128, in inference_dump_graph [output_node_name]) File "/home/khalique/.local/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func return func(*args, **kwargs) File "/home/khalique/.local/lib/python3.5/site-packages/tensorflow/python/framework/graph_util_impl.py", line 270, in convert_variables_to_constants inference_graph = extract_sub_graph(input_graph_def, output_node_names) File "/home/khalique/.local/lib/python3.5/site-packages/tensorflow/python/util/deprecation.py", line 324, in new_func return func(*args, **kwargs) File "/home/khalique/.local/lib/python3.5/site-packages/tensorflow/python/framework/graph_util_impl.py", line 182, in extract_sub_graph _assert_nodes_are_present(name_to_node, dest_nodes) File "/home/khalique/.local/lib/python3.5/site-packages/tensorflow/python/framework/graph_util_impl.py", line 137, in _assert_nodes_are_present assert d in name_to_node, "%s is not in graph" % d AssertionError: index_to_string_Lookup is not in graph
I am using tensorflow version 1.14 with python3.5. Does the tutorial still work with this configuration?
Link Copied
0 Replies
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page