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

ResNet-34-D

timm/resnet34d.ra2_in1k
Left and right arrow keys switch the vendor.
int8_embedl_tensorrt
timm resnet34d.ra2_in1k architecture graph
timm resnet34d.ra2_in1k architecture graph
  • timm/resnet34d.ra2_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

resnet34d.ra2_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:resnet34d.ra2_in1k-timm_int8_embedl_tensorrt_thor.b15b7b49eb11950e

—

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)

5 Embedl builds of ResNet-34-D on 5 devices: latency against Top-1. Click a build to open it.

75.576.076.577.077.578.0Top-1 (%)0.20.40.60.81.01.2Latency (ms)↖ Better