Mirrors/blakeblackshear.frigate
1
0
Fork 0
mirror of https://github.com/blakeblackshear/frigate.git synced 2025-09-14 17:52:10 +02:00
Code Issues Projects Releases Wiki Activity

Fixes (#19984)

Browse Source 
* Always handle RKNN as NHWC in Frigate+ model loading

* Correct Intel stats

* Update inference time docs

* Update version

* Adjust inference speeds
This commit is contained in:
Nicolas Mowen 2025-09-09 06:17:56 -06:00 committed by GitHub
parent f46f8a2160
commit 205fdf3ae3
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 9 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Makefile
View File

@ -1,7 +1,7 @@
default_target: local default_target: local
COMMIT_HASH := $(shell git log -1 --pretty=format:"%h"|tail -1) COMMIT_HASH := $(shell git log -1 --pretty=format:"%h"|tail -1)
VERSION = 0.16.1 VERSION = 0.16.2
IMAGE_REPO ?= ghcr.io/blakeblackshear/frigate IMAGE_REPO ?= ghcr.io/blakeblackshear/frigate
GITHUB_REF_NAME ?= $(shell git rev-parse --abbrev-ref HEAD) GITHUB_REF_NAME ?= $(shell git rev-parse --abbrev-ref HEAD)
BOARDS= #Initialized empty BOARDS= #Initialized empty

6
docs/docs/frigate/hardware.md
View File

@ -138,11 +138,11 @@ Inference speeds vary greatly depending on the CPU or GPU used, some known examp
| Intel HD 620 | 15 - 25 ms | | 320: ~ 35 ms | | | | Intel HD 620 | 15 - 25 ms | | 320: ~ 35 ms | | |
| Intel HD 630 | ~ 15 ms | | 320: ~ 30 ms | | | | Intel HD 630 | ~ 15 ms | | 320: ~ 30 ms | | |
| Intel UHD 730 | ~ 10 ms | | 320: ~ 19 ms 640: ~ 54 ms | | | | Intel UHD 730 | ~ 10 ms | | 320: ~ 19 ms 640: ~ 54 ms | | |
| Intel UHD 770 | ~ 15 ms | t-320: 24 ms s-320: 30 ms s-640: 45 ms | 320: ~ 20 ms 640: ~ 46 ms | | | | Intel UHD 770 | ~ 15 ms | t-320: ~ 16 ms s-320: ~ 20 ms s-640: ~ 40 ms | 320: ~ 20 ms 640: ~ 46 ms | | |
| Intel N100 | ~ 15 ms | s-320: 30 ms | 320: ~ 25 ms | | Can only run one detector instance | | Intel N100 | ~ 15 ms | s-320: 30 ms | 320: ~ 25 ms | | Can only run one detector instance |
| Intel N150 | ~ 15 ms | t-320: 16ms s-320: 24 ms | | | | | Intel N150 | ~ 15 ms | t-320: 16 ms s-320: 24 ms | | | |
| Intel Iris XE | ~ 10 ms | s-320: 12 ms s-640: 30 ms | 320: ~ 18 ms 640: ~ 50 ms | | | | Intel Iris XE | ~ 10 ms | s-320: 12 ms s-640: 30 ms | 320: ~ 18 ms 640: ~ 50 ms | | |
| Intel Arc A310 | | t-320: 7 ms t-640: 11 ms s-320: 8 ms s-640: 15 ms | | | | | Intel Arc A310 | ~ 5 ms | t-320: 7 ms t-640: 11 ms s-320: 8 ms s-640: 15 ms | 320: ~ 8 ms 640: ~ 14 ms | | |
| Intel Arc A380 | ~ 6 ms | | 320: ~ 10 ms 640: ~ 22 ms | 336: 20 ms 448: 27 ms | | | Intel Arc A380 | ~ 6 ms | | 320: ~ 10 ms 640: ~ 22 ms | 336: 20 ms 448: 27 ms | |
| Intel Arc A750 | ~ 4 ms | | 320: ~ 8 ms | | | | Intel Arc A750 | ~ 4 ms | | 320: ~ 8 ms | | |

4
frigate/detectors/detector_config.py
View File

@ -161,6 +161,10 @@ class ModelConfig(BaseModel):
if model_info.get("inputDataType"): if model_info.get("inputDataType"):
self.input_dtype = model_info["inputDataType"] self.input_dtype = model_info["inputDataType"]
# RKNN always uses NHWC
if detector == "rknn":
self.input_tensor = InputTensorEnum.nhwc
# generate list of attribute labels # generate list of attribute labels
self.attributes_map = { self.attributes_map = {
**model_info.get("attributes", DEFAULT_ATTRIBUTE_LABEL_MAP), **model_info.get("attributes", DEFAULT_ATTRIBUTE_LABEL_MAP),

2
frigate/util/services.py
View File

@ -301,7 +301,7 @@ def get_intel_gpu_stats(intel_gpu_device: Optional[str]) -> Optional[dict[str, s
"-o", "-o",
"-", "-",
"-s", "-s",
"1", "1000", # Intel changed this from seconds to milliseconds in 2024+ versions
] ]
if intel_gpu_device: if intel_gpu_device: