Modifying spancat scorer threshold in config after training has finished.

[smisra1]

My spacy version is 3.2.2.
I am trying to train a spancat model.
I believe the components.spancat.threshold is talking about prediction confidence score threshold.
I wanted to know if changing the components.spancat.threshold from the config file AFTER training a model would be possible or can threshold only be fixed before training.
I have added mhy config file below:

[paths]
train = "./train_data.spacy"
dev = "./dev_data.spacy"
vectors = null
init_tok2vec = null

[system]
gpu_allocator = null
seed = 0

[nlp]
lang = "en"
pipeline = ["spancat"]
batch_size = 128
disabled = []
before_creation = null
after_creation = null
after_pipeline_creation = null
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}

[components]

[components.spancat]
factory = "spancat"
max_positive = null
scorer = {"@scorers":"spacy.spancat_scorer.v1"}
spans_key = "sc"
threshold = 0.01

[components.spancat.model]
@architectures = "spacy.SpanCategorizer.v1"

[components.spancat.model.reducer]
@layers = "spacy.mean_max_reducer.v1"
hidden_size = 128

[components.spancat.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO = null
nI = null

[components.spancat.model.tok2vec]
@architectures = "spacy.Tok2Vec.v1"

[components.spancat.model.tok2vec.embed]
@architectures = "spacy.MultiHashEmbed.v1"
width = 96
rows = [5000,2000,1000,1000]
attrs = ["ORTH","PREFIX","SUFFIX","SHAPE"]
include_static_vectors = false

[components.spancat.model.tok2vec.encode]
@architectures = "spacy.MaxoutWindowEncoder.v1"
width = 96
window_size = 1
maxout_pieces = 3
depth = 4

[components.spancat.suggester]
@misc = "spacy.ngram_suggester.v1"
sizes = [1,2,3]

[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 = 0
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 = 0.4
accumulate_gradient = 1
patience = 1600
max_epochs = 100
max_steps = 20000
eval_frequency = 200
frozen_components = []
annotating_components = []
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 = 0.001
grad_clip = 1.0
use_averages = false
eps = 0.00000001
learn_rate = 0.001

[training.score_weights]
spans_sc_f = 1.0
spans_sc_p = 0.0
spans_sc_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]

[polm]

Yes, it's fine to change the threshold after training. It doesn't affect the loss calculations and is only used to filter predictions.

[adrianeboyd]

There's a technical detail related to where the threshold is stored that may be confusing. For historical reasons (as a carry-over from v2), a few settings end up duplicated between the top-level config.cfg and spancat's internal .cfg, and at runtime only the internal spancat value is used.

If you're going to change this I'd recommend changing both so it's less confusing overall, but the value that is used at runtime is the one in spancat/cfg / nlp.get_pipe("spancat").cfg["threshold"].