Track-Anything
High‑performance interactive tracking and segmentation in videos.
Track‑Anything is a video based machine learning model to track an object in a video.
Technical Details
Model checkpoint:xmem
Input resolution:320x568
Number of parameters (TrackAnythingEncodeKeyWithShrinkage):9.72M
Model size (TrackAnythingEncodeKeyWithShrinkage) (float):37.1 MB
Number of parameters (TrackAnythingEncodeValue):23.3M
Model size (TrackAnythingEncodeValue) (float):88.8 MB
Number of parameters (TrackAnythingEncodeKeyWithoutShrinkage):9.71M
Model size (TrackAnythingEncodeKeyWithoutShrinkage) (float):37.1 MB
Number of parameters (TrackAnythingSegment):30.1M
Model size (TrackAnythingSegment) (float):115 MB
Applicable Scenarios
Licenses
Source Model:APACHE-2.0
Deployable Model:AI-HUB-MODELS-LICENSE
Supported IoT Devices
- QCS8275 (Proxy)
- QCS8550 (Proxy)
- QCS9075 (Proxy)
Supported IoT Chipsets
- Qualcomm® QCS8275 (Proxy)
- Qualcomm® QCS8550 (Proxy)
- Qualcomm® QCS9075 (Proxy)
Looking for more? See models created by industry leaders.
Discover Model Makers