Preprocessing with the Tagger

Hi everyone, I think I trained syntaxnet after ubdating syntaxnet/context.pbx and using this command bazel test //syntaxnet:parser_trainer_test ths result was:

bazel-bin/syntaxnet/parser_trainer_test

INFO: Elapsed time: 2655.066s, Critical Path: 2628.15s
//syntaxnet:parser_trainer_test                                          PASSED in 28.6s

Executed 1 out of 1 tests: 1 test passes.
There were tests whose specified size is too big. Use the --test_verbose_timeout_warnings command line option to see which ones these are.

then I went through the next step of SyntaxNet tutorial, Preprocessing with tagger. First, I changed demo.sh to

PARAMS=128-0.08-3600-0.9-0 for SET in training tuning dev; do bazel-bin/syntaxnet/parser_eval \ --task_context=models/brain_pos/greedy/$PARAMS/context \ --hidden_layer_sizes=128 \ --input=$SET-corpus \ --output=tagged-$SET-corpus \ --arg_prefix=brain_pos \ --graph_builder=greedy \ --model_path=models/brain_pos/greedy/$PARAMS/model done

and when I ran demo.sh I got this output, probably errors:

W external/tf/tensorflow/core/framework/op_kernel.cc:899] Not found: models/brain_pos/greedy/128-0.08-3600-0.9-0/context

E external/tf/tensorflow/core/common_runtime/executor.cc:333] Executor failed to create kernel. Not found: models/brain_pos/greedy/128-0.08-3600-0.9-0/context [[Node: FeatureSize = FeatureSize[arg_prefix="brain_pos", task_context="models/brain_pos/greedy/128-0.08-3600-0.9-0/context", _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

W external/tf/tensorflow/core/framework/op_kernel.cc:899] Not found: models/brain_pos/greedy/128-0.08-3600-0.9-0/context

The massage was too long and the above error was repeated 3 times but did not want to bother you with long confusing code. after I saw these massages I expected not to see anything in models/brain_pos/greedy/$PARAMS/, actually I could not find the paths.

Could you please help me where the problem is?

tensorflow / models

Preprocessing with the Tagger #172