torchvision/lraspp_mobilenet_v3_large

torchvision_int8_modelopt_tensorrt

Labels

Build

Embedl-optimized

Precision

INT8

Runtime

TensorRT 11.2.1 with Embedl optimizations

lraspp_mobilenet_v3_large is a semantic segmentation model from torchvision: it assigns a class to every pixel of an image.

batch 1 · trtexec · Baseline TensorRT as baseline

1.52 ms

Median (ms)	p90 (ms)	p95 (ms)	p99 (ms)	Throughput (qps)
1.52	1.52	1.52	1.52	657

COCO segmentation validation · 2,000 images · Baseline TensorRT as baseline

43.54 %