ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update:

Browse Source 
- Text Categorization
- Crawler, Extraction, and Chunking strategies
- Clustering for semantic segmentation
This commit is contained in:
unclecode
2024-05-12 22:37:21 +08:00
parent 7039e3c1ee
commit 82706129f5
19 changed files with 84568 additions and 102 deletions
Download Patch File Download Diff File Expand all files Collapse all files

144
models/reuters/config.cfg Normal file
View File

@@ -0,0 +1,144 @@
[paths]
train = null
dev = null
vectors = null
init_tok2vec = null
[system]
seed = 0
gpu_allocator = null
[nlp]
lang = "en"
pipeline = ["textcat_multilabel"]
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
batch_size = 1000
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
vectors = {"@vectors":"spacy.Vectors.v1"}
[components]
[components.textcat_multilabel]
factory = "textcat_multilabel"
scorer = {"@scorers":"spacy.textcat_multilabel_scorer.v2"}
threshold = 0.5
[components.textcat_multilabel.model]
@architectures = "spacy.TextCatEnsemble.v2"
nO = null
[components.textcat_multilabel.model.linear_model]
@architectures = "spacy.TextCatBOW.v3"
exclusive_classes = false
length = 262144
ngram_size = 1
no_output_layer = false
nO = null
[components.textcat_multilabel.model.tok2vec]
@architectures = "spacy.Tok2Vec.v2"
[components.textcat_multilabel.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v2"
width = 64
rows = [2000,2000,500,1000,500]
attrs = ["NORM","LOWER","PREFIX","SUFFIX","SHAPE"]
include_static_vectors = false
[components.textcat_multilabel.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 64
window_size = 1
maxout_pieces = 3
depth = 2
[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 = []
annotating_components = []
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
before_to_disk = null
before_update = 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]
cats_score = 1.0
cats_score_desc = null
cats_micro_p = null
cats_micro_r = null
cats_micro_f = null
cats_macro_p = null
cats_macro_r = null
cats_macro_f = null
cats_macro_auc = null
cats_f_per_type = null
[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]

122
models/reuters/meta.json Normal file
View File

@@ -0,0 +1,122 @@
{
"lang":"en",
"name":"pipeline",
"version":"0.0.0",
"spacy_version":">=3.7.4,<3.8.0",
"description":"",
"author":"",
"email":"",
"url":"",
"license":"",
"spacy_git_version":"bff8725f4",
"vectors":{
"width":0,
"vectors":0,
"keys":0,
"name":null,
"mode":"default"
},
"labels":{
"textcat_multilabel":[
"acq",
"alum",
"barley",
"bop",
"carcass",
"castor-oil",
"cocoa",
"coconut",
"coconut-oil",
"coffee",
"copper",
"copra-cake",
"corn",
"cotton",
"cotton-oil",
"cpi",
"cpu",
"crude",
"dfl",
"dlr",
"dmk",
"earn",
"fuel",
"gas",
"gnp",
"gold",
"grain",
"groundnut",
"groundnut-oil",
"heat",
"hog",
"housing",
"income",
"instal-debt",
"interest",
"ipi",
"iron-steel",
"jet",
"jobs",
"l-cattle",
"lead",
"lei",
"lin-oil",
"livestock",
"lumber",
"meal-feed",
"money-fx",
"money-supply",
"naphtha",
"nat-gas",
"nickel",
"nkr",
"nzdlr",
"oat",
"oilseed",
"orange",
"palladium",
"palm-oil",
"palmkernel",
"pet-chem",
"platinum",
"potato",
"propane",
"rand",
"rape-oil",
"rapeseed",
"reserves",
"retail",
"rice",
"rubber",
"rye",
"ship",
"silver",
"sorghum",
"soy-meal",
"soy-oil",
"soybean",
"strategic-metal",
"sugar",
"sun-meal",
"sun-oil",
"sunseed",
"tea",
"tin",
"trade",
"veg-oil",
"wheat",
"wpi",
"yen",
"zinc"
]
},
"pipeline":[
"textcat_multilabel"
],
"components":[
"textcat_multilabel"
],
"disabled":[
]
}

95
models/reuters/textcat_multilabel/cfg Normal file
View File

@@ -0,0 +1,95 @@
{
"labels":[
"acq",
"alum",
"barley",
"bop",
"carcass",
"castor-oil",
"cocoa",
"coconut",
"coconut-oil",
"coffee",
"copper",
"copra-cake",
"corn",
"cotton",
"cotton-oil",
"cpi",
"cpu",
"crude",
"dfl",
"dlr",
"dmk",
"earn",
"fuel",
"gas",
"gnp",
"gold",
"grain",
"groundnut",
"groundnut-oil",
"heat",
"hog",
"housing",
"income",
"instal-debt",
"interest",
"ipi",
"iron-steel",
"jet",
"jobs",
"l-cattle",
"lead",
"lei",
"lin-oil",
"livestock",
"lumber",
"meal-feed",
"money-fx",
"money-supply",
"naphtha",
"nat-gas",
"nickel",
"nkr",
"nzdlr",
"oat",
"oilseed",
"orange",
"palladium",
"palm-oil",
"palmkernel",
"pet-chem",
"platinum",
"potato",
"propane",
"rand",
"rape-oil",
"rapeseed",
"reserves",
"retail",
"rice",
"rubber",
"rye",
"ship",
"silver",
"sorghum",
"soy-meal",
"soy-oil",
"soybean",
"strategic-metal",
"sugar",
"sun-meal",
"sun-oil",
"sunseed",
"tea",
"tin",
"trade",
"veg-oil",
"wheat",
"wpi",
"yen",
"zinc"
],
"threshold":0.5
}

BIN
models/reuters/textcat_multilabel/model Normal file
View File

Binary file not shown.

3
models/reuters/tokenizer Normal file
View File

File diff suppressed because one or more lines are too long

1
models/reuters/vocab/key2row Normal file
View File

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

1
models/reuters/vocab/lookups.bin Normal file
View File

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

83457
models/reuters/vocab/strings.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
models/reuters/vocab/vectors Normal file
View File

Binary file not shown.

3
models/reuters/vocab/vectors.cfg Normal file
View File

@@ -0,0 +1,3 @@
{
"mode":"default"
}