Skip to content
Search models or paste a model link. Press Enter to search.

RegNetY-080 (tv)

timm/regnety_080_tv.tv2_in1k
Left and right arrow keys switch the vendor.
int8_embedl_tensorrt
timm regnety_080_tv.tv2_in1k architecture graph
timm regnety_080_tv.tv2_in1k architecture graph
  • timm/regnety_080_tv.tv2_in1k
  • INT8
  • AGX Thor
Labels
  • Image
  • Classification
Build
Embedl-optimized
Precision
INT8
Runtime
TensorRT 10.16.2.10 with Embedl optimizations
Input size
224×224

regnety_080_tv.tv2_in1k is an image classifier from timm. It labels an image with one of the 1,000 ImageNet classes.

Files

Image Size

Model

docker.io/embedl/model-artifacts:regnety_080_tv.tv2_in1k-timm_int8_embedl_tensorrt_thor.afa13cd61d7abd58

—

Runtime

docker.io/embedl/models:timm-embedl.jetson.runtime.arm64.202610180907f8cd

—

Select hardware to start

Its measured speed and accuracy, its files and how to run it are per device.

Model variants (Pareto)

3 Embedl builds of RegNetY-080 (tv) on 3 devices: latency against Top-1. Click a build to open it.

81.081.582.082.583.083.5Top-1 (%)1.81.92.02.12.2Latency (ms)↖ Better