mirror of
https://github.com/blakeblackshear/frigate.git
synced 2024-12-29 00:06:19 +01:00
24ac9f3e5a
* swap sqlite_vec for chroma in requirements * load sqlite_vec in embeddings manager * remove chroma and revamp Embeddings class for sqlite_vec * manual minilm onnx inference * remove chroma in clip model * migrate api from chroma to sqlite_vec * migrate event cleanup from chroma to sqlite_vec * migrate embedding maintainer from chroma to sqlite_vec * genai description for sqlite_vec * load sqlite_vec in main thread db * extend the SqliteQueueDatabase class and use peewee db.execute_sql * search with Event type for similarity * fix similarity search * install and add comment about transformers * fix normalization * add id filter * clean up * clean up * fully remove chroma and add transformers env var * readd uvicorn for fastapi * readd tokenizer parallelism env var * remove chroma from docs * remove chroma from UI * try removing custom pysqlite3 build * hard code limit * optimize queries * revert explore query * fix query * keep building pysqlite3 * single pass fetch and process * remove unnecessary re-embed * update deps * move SqliteVecQueueDatabase to db directory * make search thumbnail take up full size of results box * improve typing * improve model downloading and add status screen * daemon downloading thread * catch case when semantic search is disabled * fix typing * build sqlite_vec from source * resolve conflict * file permissions * try build deps * remove sources * sources * fix thread start * include git in build * reorder embeddings after detectors are started * build with sqlite amalgamation * non-platform specific * use wget instead of curl * remove unzip -d * remove sqlite_vec from requirements and load the compiled version * fix build * avoid race in db connection * add scale_factor and bias to description zscore normalization
54 lines
1.4 KiB
Python
54 lines
1.4 KiB
Python
"""Z-score normalization for search distance."""
|
|
|
|
import math
|
|
|
|
|
|
class ZScoreNormalization:
|
|
def __init__(self, scale_factor: float = 1.0, bias: float = 0.0):
|
|
"""Initialize with optional scaling and bias adjustments."""
|
|
"""scale_factor adjusts the magnitude of each score"""
|
|
"""bias will artificially shift the entire distribution upwards"""
|
|
self.n = 0
|
|
self.mean = 0
|
|
self.m2 = 0
|
|
self.scale_factor = scale_factor
|
|
self.bias = bias
|
|
|
|
@property
|
|
def variance(self):
|
|
return self.m2 / (self.n - 1) if self.n > 1 else 0.0
|
|
|
|
@property
|
|
def stddev(self):
|
|
return math.sqrt(self.variance)
|
|
|
|
def normalize(self, distances: list[float]):
|
|
self._update(distances)
|
|
if self.stddev == 0:
|
|
return distances
|
|
return [
|
|
(x - self.mean) / self.stddev * self.scale_factor + self.bias
|
|
for x in distances
|
|
]
|
|
|
|
def _update(self, distances: list[float]):
|
|
for x in distances:
|
|
self.n += 1
|
|
delta = x - self.mean
|
|
self.mean += delta / self.n
|
|
delta2 = x - self.mean
|
|
self.m2 += delta * delta2
|
|
|
|
def to_dict(self):
|
|
return {
|
|
"n": self.n,
|
|
"mean": self.mean,
|
|
"m2": self.m2,
|
|
}
|
|
|
|
def from_dict(self, data: dict):
|
|
self.n = data["n"]
|
|
self.mean = data["mean"]
|
|
self.m2 = data["m2"]
|
|
return self
|