update ml modelle - korrektur validerung iban/bic

This commit is contained in:
Ralph Soika 2021-03-26 10:27:19 +01:00
parent cfba088140
commit 79b6983ae9
14 changed files with 31632 additions and 2218 deletions

View file

@ -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]

View file

@ -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":[
]
}

View file

@ -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
}

Binary file not shown.

View file

@ -0,0 +1 @@
<EFBFBD>¥movesÚÄ{"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}}

File diff suppressed because one or more lines are too long

View file

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

View file

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

File diff suppressed because it is too large Load diff

Binary file not shown.

Binary file not shown.

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff

File diff suppressed because it is too large Load diff