administrator/frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2026-08-01 00:22:19 +03:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

Miscellaneous fixes (0.17 beta) (#21350)
CI / AMD64 Build (push) Has been cancelled
Details
CI / ARM Build (push) Has been cancelled
Details
CI / Jetson Jetpack 6 (push) Has been cancelled
Details
CI / AMD64 Extra Build (push) Has been cancelled
Details
CI / ARM Extra Build (push) Has been cancelled
Details
CI / Synaptics Build (push) Has been cancelled
Details
CI / Assemble and push default build (push) Has been cancelled
Details

Browse Source 
* Fix genai callbacks in MQTT

* Cleanup cursor pointer for classification cards

* Cleanup

* Handle unknown SOCs for RKNN converter by only using known SOCs

* don't allow "none" as a classification class name

* change internal port user to admin and default unspecified username to viewer

* keep 5000 as anonymous user

* suppress tensorflow logging during classification training

* Always apply base log level suppressions for noisy third-party libraries even if no specific logConfig is provided

* remove decorator and specifically suppress TFLite delegate creation messages

---------

Co-authored-by: Josh Hawkins <32435876+hawkeye217@users.noreply.github.com>
This commit is contained in:
Nicolas Mowen
2025-12-18 15:12:10 -07:00
committed by GitHub
co-authored by Josh Hawkins
parent 6a0e31dcf9
commit e636449d56
20 changed files with 156 additions and 67 deletions
Download Patch File Download Diff File Expand all files Collapse all files
frigate/util/classification.py
+15 -10
View File
@@ -19,7 +19,7 @@ from frigate.const import (
PROCESS_PRIORITY_LOW,
UPDATE_MODEL_STATE,
)
from frigate.log import redirect_output_to_logger
from frigate.log import redirect_output_to_logger, suppress_stderr_during
from frigate.models import Event, Recordings, ReviewSegment
from frigate.types import ModelStatusTypesEnum
from frigate.util.downloader import ModelDownloader
@@ -250,15 +250,20 @@ class ClassificationTrainingProcess(FrigateProcess):
logger.debug(f"Converting {self.model_name} to TFLite...")
# convert model to tflite
converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = (
self.__generate_representative_dataset_factory(dataset_dir)
)
converter.target_spec.supported_ops = [tf.lite.OpsSet.TFLITE_BUILTINS_INT8]
converter.inference_input_type = tf.uint8
converter.inference_output_type = tf.uint8
tflite_model = converter.convert()
# Suppress stderr during conversion to avoid LLVM debug output
# (fully_quantize, inference_type, MLIR optimization messages, etc)
with suppress_stderr_during("tflite_conversion"):
converter = tf.lite.TFLiteConverter.from_keras_model(model)
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = (
self.__generate_representative_dataset_factory(dataset_dir)
)
converter.target_spec.supported_ops = [
tf.lite.OpsSet.TFLITE_BUILTINS_INT8
]
converter.inference_input_type = tf.uint8
converter.inference_output_type = tf.uint8
tflite_model = converter.convert()
# write model
model_path = os.path.join(model_dir, "model.tflite")