model update

docker-compose.yml

@@ -68,7 +68,7 @@ services:
   # Imixs-ML-spaCy Service
   ###############################################
   imixs-ml-spacy: 
-    image: imixs/imixs-ml-spacy
+    image: imixs/imixs-ml-spacy:1.1.1
     environment:
       PYTHONUNBUFFERED: 1
       TZ: "Europe/Berlin"
@@ -83,7 +83,7 @@ services:
   # Imixs-ML Training service
   ###############################################
   imixs-ml-training:
-    image: imixs/imixs-ml-training
+    image: imixs/imixs-ml-training:latest
     environment:
       TZ: "Europe/Berlin"
       OCR_SERVICE_ENDPOINT: "http://tika:9998/tika"

models/README.md

@@ -19,7 +19,8 @@ Das Modell bei Alexander Logistics läst sich in der Dev Umggebung bei Bedarf na
 
 **2.)** Die Tikal-Cloud Pullen
 
-**3.)** den Inhalt des invoice-de-0.1.0 Folders aus dem Backup directory in die lokale Dev Umgebung kopieren / 
+**3.)** Um auf dem aktuellen Modell weiter zu trainierne, den Inhalt des invoice-de-0.1.0 Folders aus dem Backup directory in die lokale Dev Umgebung kopieren / 
+   um ein neues Modell zu genereiren einfach den localen ordner 'invoice-de-0.1.0' umbenennen oder leeren.
 
 **4.)** Jetzt lokal den Trainingsserver aufrufen  
 

models/invoice-de-0.1.0/ner/moves

@@ -1 +1 @@
-<EFBFBD>¥movesÚ
Ä{"0":{},"1":{"cdtr.iban":-1,"cdtr.bic":-2,"cdtr.name":-3,"invoice.total":-4,"invoice.number":-5,"invoice.date":-6},"2":{"cdtr.iban":-1,"cdtr.bic":-2,"cdtr.name":-3,"invoice.total":-4,"invoice.number":-5,"invoice.date":-6},"3":{"cdtr.iban":-1,"cdtr.bic":-2,"cdtr.name":-3,"invoice.total":-4,"invoice.number":-5,"invoice.date":-6},"4":{"":1,"cdtr.iban":-1,"cdtr.bic":-2,"cdtr.name":-3,"invoice.total":-4,"invoice.number":-5,"invoice.date":-6},"5":{"":1}}
+<EFBFBD>¥movesÚ
Ä{"0":{},"1":{"cdtr.name":-1,"cdtr.iban":-2,"cdtr.bic":-3,"invoice.total":-4,"invoice.date":-5,"invoice.number":-6},"2":{"cdtr.name":-1,"cdtr.iban":-2,"cdtr.bic":-3,"invoice.total":-4,"invoice.date":-5,"invoice.number":-6},"3":{"cdtr.name":-1,"cdtr.iban":-2,"cdtr.bic":-3,"invoice.total":-4,"invoice.date":-5,"invoice.number":-6},"4":{"":1,"cdtr.name":-1,"cdtr.iban":-2,"cdtr.bic":-3,"invoice.total":-4,"invoice.date":-5,"invoice.number":-6},"5":{"":1}}

models/invoice-de-20210518/config.cfg

@@ -0,0 +1,125 @@
+[paths]
+train = null
+dev = null
+vectors = null
+init_tok2vec = null
+
+[system]
+seed = 0
+gpu_allocator = null
+
+[nlp]
+lang = "de"
+pipeline = ["ner"]
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+batch_size = 1000
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+
+[components]
+
+[components.ner]
+factory = "ner"
+moves = null
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = true
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy.HashEmbedCNN.v1"
+pretrained_vectors = null
+width = 96
+depth = 4
+embed_size = 2000
+window_size = 1
+maxout_pieces = 3
+subword_features = true
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+gold_preproc = false
+max_length = 0
+limit = 0
+augmenter = null
+
+[training]
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+accumulate_gradient = 1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+before_to_disk = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_words.v1"
+discard_oversize = false
+tolerance = 0.2
+get_length = null
+
+[training.batcher.size]
+@schedules = "compounding.v1"
+start = 100
+stop = 1000
+compound = 1.001
+t = 0.0
+
+[training.logger]
+@loggers = "spacy.ConsoleLogger.v1"
+progress_bar = false
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+learn_rate = 0.001
+
+[training.score_weights]
+ents_per_type = null
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]

models/invoice-de-20210518/meta.json

@@ -0,0 +1,37 @@
+{
+  "lang":"de",
+  "name":"pipeline",
+  "version":"0.0.0",
+  "spacy_version":">=3.0.1,<3.1.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_git_version":"91a3cab1c",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "ner":[
+      "cdtr.bic",
+      "cdtr.iban",
+      "cdtr.name",
+      "invoice.date",
+      "invoice.number",
+      "invoice.total"
+    ]
+  },
+  "pipeline":[
+    "ner"
+  ],
+  "components":[
+    "ner"
+  ],
+  "disabled":[
+
+  ]
+}

models/invoice-de-20210518/ner/cfg

@@ -0,0 +1,12 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":1,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0
+}

models/invoice-de-20210518/ner/moves

@@ -0,0 +1 @@
+<EFBFBD>¥movesÚ
Ä{"0":{},"1":{"cdtr.iban":-1,"cdtr.bic":-2,"cdtr.name":-3,"invoice.total":-4,"invoice.number":-5,"invoice.date":-6},"2":{"cdtr.iban":-1,"cdtr.bic":-2,"cdtr.name":-3,"invoice.total":-4,"invoice.number":-5,"invoice.date":-6},"3":{"cdtr.iban":-1,"cdtr.bic":-2,"cdtr.name":-3,"invoice.total":-4,"invoice.number":-5,"invoice.date":-6},"4":{"":1,"cdtr.iban":-1,"cdtr.bic":-2,"cdtr.name":-3,"invoice.total":-4,"invoice.number":-5,"invoice.date":-6},"5":{"":1}}

models/invoice-de-20210518/vocab/key2row

@@ -0,0 +1 @@
+<EFBFBD>

models/invoice-de-20210518/vocab/lookups.bin

@@ -0,0 +1 @@
+<EFBFBD>

models/training-config-prod.xml

@@ -7,8 +7,10 @@
 	<item name="workflow.userid"><value xsi:type="xs:string">admin</value></item>
 	<item name="workflow.password"><value xsi:type="xs:string">imixs4.null</value></item>
 
-	<item name="workflow.query"><value xsi:type="xs:string">($workflowgroup:"Rechnungseingang") AND ($taskid:[5300 TO 5900])</value></item>
-	
+<!-- 	
+	<item name="workflow.query"><value xsi:type="xs:string">($workflowgroup:"Rechnungseingang" OR $workflowgroup:"Sachrechnung") AND ($taskid:5900)</value></item>
+	 -->
+	<item name="workflow.query"><value xsi:type="xs:string">($uniqueid:344372ce-55ee-4dd1-b492-822d59be38b7)</value></item>
 	
 	<item name="workflow.pagesize"><value xsi:type="xs:int">30</value></item>
 	<item name="workflow.pageindex"><value xsi:type="xs:int">0</value></item>
@@ -25,8 +27,8 @@
 		
 	</item>
 	<item name="workflow.locale">
-		<value xsi:type="xs:string">UK</value>
-		<value xsi:type="xs:string">DE</value>
+		<value xsi:type="xs:string">en_GB</value>
+		<value xsi:type="xs:string">de_DE</value>
 	</item>
 	
 	<!-- Tika OCR Server  -->

pom.xml

@@ -31,7 +31,7 @@
 		<org.imixs.adapters.version>2.2.6</org.imixs.adapters.version>
 		<org.imixs.archive.version>2.2.11</org.imixs.archive.version>
 		<org.imixs.melman.version>1.0.20</org.imixs.melman.version>
-		<org.imixs.ml.version>1.1.0</org.imixs.ml.version>
+		<org.imixs.ml.version>1.1.1</org.imixs.ml.version>
 		<microprofile.version>2.2</microprofile.version>
 
 		<custom.webResources>src/main/webapp</custom.webResources>