Nvidia RTX 2060 · yolov7x-640 · 9 cameras

Community build
Posted Sep 2023·GitHub #7601 ·db-133
I run this too, add my numbers Opens the submit form prefilled with this hardware, model and version
Inference
43.8 ms
as reported
Est. capacity
~23 det/s
1000 ÷ 43.8 ms · estimate
Cameras
9
as reported
CPU
—
not reported
Power
150 W
as reported

Parts

prices show only once verified by hand
Accelerator
Nvidia RTX 2060
TensorRT (Nvidia, legacy) · 2 builds on DetectFPS
price not tracked yet
Get price drops in the weekly newsletter

Price drops, once a week

When a tracked price is verified or drops, it goes in the newsletter alongside new benchmarks. No per-device alerts and no tracking: the newsletter is the only list.

Newsletter coming soon The signup form appears here as soon as the newsletter embed code is pasted into site.json. Issue #1 is already readable here.
Host
—
not reported
—
CPU
Intel Core i5-3570K
as reported
—
Cameras
9 cameras
resolution not reported
—
Tracked totalno verified prices yet

Setup

Detector
TensorRT (Nvidia, legacy)
Detector instances
—
Model, as reported
yolov7x-640
Model family · input
yolov7x · 640
Camera resolution
—
Cameras
9
Frigate version
—
OS
—

Numbers

dashes mean the source didn't say
Inference
43.8 ms
Inference range
—
Total fps
—
CPU
—
Power
150 W
Used in stats
Yes

Notes and flags

Night

Source

Where
Date, as the source wrote it
2023-09/2023-11 (month precision)
Added to DetectFPS
from a public post; numbers copied as written, not re-tested

Similar builds

Same device, then the same model family

Nvidia RTX 2060
TensorRT (Nvidia, legacy) · Night; 49 W idle
Speed17.4 ms
Cameras9
Modelyolov7x-320
Version—
  • AcceleratorNvidia RTX 2060price not tracked
  • Host—
  • CPUIntel Core i5-3570K

1 other build uses the same device.