Train error

[anton-avramchuk]

I'm trying to train UD_English and I want to see output like this. After transform context.pbtxt like context from English and run ./train.sh -v -v I see error: INFO:tensorflow:Training... INFO:tensorflow:Building training network with parameters: feature_sizes: [] domain_sizes: [] Traceback (most recent call last): File "/home/anton/models/syntaxnet/bazel-bin/syntaxnet/parser_trainer.runfiles/syntaxnet/parser_trainer.py", line 303, in <module> tf.app.run() File "/home/anton/models/syntaxnet/bazel-bin/syntaxnet/parser_trainer.runfiles/external/org_tensorflow/tensorflow/python/platform/app.py", line 30, in run sys.exit(main(sys.argv)) File "/home/anton/models/syntaxnet/bazel-bin/syntaxnet/parser_trainer.runfiles/syntaxnet/parser_trainer.py", line 299, in main Train(sess, num_actions, feature_sizes, domain_sizes, embedding_dims) File "/home/anton/models/syntaxnet/bazel-bin/syntaxnet/parser_trainer.runfiles/syntaxnet/parser_trainer.py", line 212, in Train corpus_name=corpus_name) File "/home/anton/models/syntaxnet/bazel-bin/syntaxnet/parser_trainer.runfiles/syntaxnet/graph_builder.py", line 512, in AddTraining nodes.update(self._AddGoldReader(task_context, batch_size, corpus_name)) File "/home/anton/models/syntaxnet/bazel-bin/syntaxnet/parser_trainer.runfiles/syntaxnet/graph_builder.py", line 381, in _AddGoldReader arg_prefix=self._arg_prefix)) File "/home/anton/models/syntaxnet/bazel-bin/syntaxnet/parser_trainer.runfiles/syntaxnet/ops/gen_parser_ops.py", line 321, in gold_parse_reader arg_prefix=arg_prefix, name=name) File "/home/anton/models/syntaxnet/bazel-bin/syntaxnet/parser_trainer.runfiles/external/org_tensorflow/tensorflow/python/framework/op_def_library.py", line 627, in apply_op (key, op_type_name, attr_value.i, attr_def.minimum)) ValueError: Attr 'feature_size' of 'GoldParseReader' Op passed 0 less than minimum 1.

context2.txt

[dsindex]

@zizoo

hello zizoo~

'English' directory(a model of Parsey's cousin) was downloaded from 'http://download.tensorflow.org/models/parsey_universal/.zip' ( https://github.com/tensorflow/models/blob/master/syntaxnet/universal.md )

you can see that there are tokenizer and morpher model(params) with tagger and parser. unfortunately, at least now, it is not possible to train tokenizer and morpher model from UD_English because the code is not provided yet.

but you can train tagger and parser by using train.sh.

[anton-avramchuk]

Thank you!