Train NER based on existing model or add custom trained NER to existing model error

[taghouti-ghofrane]

Spacy : 3.2
python: 3.9.0
config.cfg

[paths]
train = null
dev = null
vectors = null
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "en"
pipeline = ["tok2vec","tagger","parser","ner"]
batch_size = 1000
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}

[components]

[components.tagger]
source = "en_core_web_sm"
replace_listeners = ["model.tok2vec"]

[components.parser]
source = "en_core_web_sm"
replace_listeners = ["model.tok2vec"]

[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.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
upstream = "*"

[components.tok2vec]
source = "en_core_web_sm"

[components.tok2vec.model]
@architectures = "spacy.Tok2Vec.v2"

[components.tok2vec.model.embed]
@architectures = "spacy.MultiHashEmbed.v1"
width = ${components.tok2vec.model.encode.width}
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
rows = [5000,2500,2500,2500]
include_static_vectors = false

[components.tok2vec.model.encode]
@architectures = "spacy.MaxoutWindowEncoder.v2"
width = 256
depth = 8
window_size = 1
maxout_pieces = 3

[corpora]

[corpora.dev]
@readers = "spacy.Corpus.v1"
path = ${paths.dev}
max_length = 0
gold_preproc = false
limit = 0
augmenter = null

[corpora.train]
@readers = "spacy.Corpus.v1"
path = ${paths.train}
max_length = 2000
gold_preproc = false
limit = 0
augmenter = null

[training]
dev_corpus = "corpora.dev"
train_corpus = "corpora.train"
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 = ["tagger","parser"]
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 = "en_core_web_lg"
init_tok2vec = ${paths.init_tok2vec}
vocab_data = null
lookups = null
before_init = null
after_init = null

[initialize.components]

[initialize.tokenizer]

[taghouti-ghofrane]

ERROR:
ValueError: operands could not be broadcast together with shapes (1,96) (1,256) (1,96)

[polm]

What are you trying to do? I don't understand from just your title.

Also if you have an error please post the whole stack trace.

[taghouti-ghofrane]

Hello again , sorry to make things not clear ,
what i want to d : i want to retrain an old model with old ner and add new ner to THE MODEL ,
i used this discussion #7149 but i dont find the solution

the config is the last one that i puted it !
ALL THER ERROR 👍

[2022-01-11 19:55:40,278] [INFO] Set up nlp object from config
[2022-01-11 19:55:40,306] [INFO] Pipeline: ['tok2vec', 'tagger', 'parser', 'ner']
[2022-01-11 19:55:40,307] [INFO] Resuming training for: ['tok2vec']
[2022-01-11 19:55:40,315] [INFO] Created vocabulary
[2022-01-11 19:55:42,139] [INFO] Added vectors: en_core_web_lg
C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\training\initialize.py:138: UserWarning: [W113] Sourced component 'tok2vec' may not work as expected: source vectors are not identical to current pipeline vectors.
warnings.warn(Warnings.W113.format(name=sourced_component))
C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\training\initialize.py:138: UserWarning: [W113] Sourced component 'tagger' may not work as expected: source vectors are not
identical to current pipeline vectors.
warnings.warn(Warnings.W113.format(name=sourced_component))
C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\training\initialize.py:138: UserWarning: [W113] Sourced component 'parser' may not work as expected: source vectors are not
identical to current pipeline vectors.
warnings.warn(Warnings.W113.format(name=sourced_component))
[2022-01-11 19:55:43,869] [INFO] Finished initializing nlp object
[2022-01-11 19:55:49,682] [INFO] Initialized pipeline components: ['ner']
✔ Initialized pipeline

============================= Training pipeline =============================
ℹ Pipeline: ['tok2vec', 'tagger', 'parser', 'ner']
ℹ Frozen components: ['tagger', 'parser']
ℹ Initial learn rate: 0.001
E # LOSS TOK2VEC LOSS NER TAG_ACC DEP_UAS DEP_LAS SENTS_F ENTS_F ENTS_P ENTS_R SCORE

---

⚠ Aborting and saving the final best model. Encountered exception:
ValueError('operands could not be broadcast together with shapes (1,96) (1,256)
(1,96) ')
Traceback (most recent call last):
File "C:\Python39\lib\runpy.py", line 197, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Python39\lib\runpy.py", line 87, in run_code
exec(code, run_globals)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy_main.py", line 4, in
setup_cli()
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\cli_util.py", line 71, in setup_cli
command(prog_name=COMMAND)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\click\core.py", line 1128, in call
return self.main(*args, **kwargs)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\click\core.py", line 1053, in main
rv = self.invoke(ctx)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\click\core.py", line 1659, in invoke
return _process_result(sub_ctx.command.invoke(sub_ctx))
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\click\core.py", line 1395, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\click\core.py", line 754, in
invoke
return __callback(*args, **kwargs)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\typer\main.py", line 500, in
wrapper
return callback(**use_params) # type: ignore
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\cli\train.py", line 45, in train_cli
train(config_path, output_path, use_gpu=use_gpu, overrides=overrides)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\cli\train.py", line 75, in train
train_nlp(nlp, output_path, use_gpu=use_gpu, stdout=sys.stdout, stderr=sys.stderr)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\training\loop.py", line 122, in train
raise e
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\training\loop.py", line 105, in train
for batch, info, is_best_checkpoint in training_step_iterator:
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\training\loop.py", line 203, in train_while_improving
nlp.update(
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\language.py", line 1153, in update
proc.update(examples, sgd=None, losses=losses, **component_cfg[name]) # type: ignore
File "spacy\pipeline\transition_parser.pyx", line 419, in spacy.pipeline.transition_parser.Parser.update
File "spacy\ml\parser_model.pyx", line 300, in spacy.ml.parser_model.ParserStepModel.finish_steps
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\thinc\layers\chain.py", line
60, in backprop
dX = callback(dY)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\pipeline\tok2vec.py", line 180, in backprop
accumulate_gradient(one_d_tokvecs)
File "C:\Users\user\Desktop\DATABASE\Pseudo\lib\site-packages\spacy\pipeline\tok2vec.py", line 174, in accumulate_gradient
d_tokvecs[i] += one_d_tokvecs[i]
ValueError: operands could not be broadcast together with shapes (1,96) (1,256) (1,96)

[adrianeboyd]

Your new ner component's tok2vec listener settings are mismatched with the settings for the sourced tok2vec from en_core_web_sm. If you use source =, don't include any other config settings for this block since they will be overwritten with the settings from the source model instead.

This line is using the value from your mismatched config, which is later replaced with the source config, but the new config already has the incorrect value:

width = ${components.tok2vec.model.encode.width}