How to test the trained SyntaxNet model (Spanish UD)?

Training my own SyntaxNet model for Spanish-Ancora UD corpus in accordance with the instructions here did not give me errors.

After all the steps he created were:

-category-map  
-char-map  
-checkpoint  
-context  
-graph  
-label-map  
-latest-model  
-latest-model.meta  
-lcword-map  
-model  
-model.meta  
-prefix-table  
-status  
-suffix-table  
-tag-map  
-tag-to-category  
-tagged-dev-corpus  
-tagged-training-corpus  
-tagged-tunning-corpus  
-word-map 

The context.pbtxt file used for training was one of the syntax / models / parsey _universal.

Then, when I try to check it by calling parser.shfrom the syntax / models / parsey _universal, we return a couple of errors:

F syntaxnet/term_frequency_map.cc:63] Check failed: ::tensorflow::Status::OK() == (tensorflow::Env::Default()->NewRandomAccessFile(filename, &file)) (OK vs. Not found: syntaxnet/models/parsey_universal/modeltest/char-ngram-map)
F syntaxnet/term_frequency_map.cc:63] Check failed: ::tensorflow::Status::OK() == (tensorflow::Env::Default()->NewRandomAccessFile(filename, &file)) (OK vs. Not found: syntaxnet/models/parsey_universal/modeltest/morphology-map) 

Then I downloaded the Spanish preliminary model from here . And I checked the files. It seems that there are two missing files, according to the preliminary model it is by default, but in the one I trained, these files were missing.

, : SyntaxNet?
?
-?

+4
1

, parse_universal : /parsey_universal/modeltest/char-ngram-map /parsey_universal/modeltest/morphology-map

0

Source: https://habr.com/ru/post/1657429/


All Articles