Embedl-optimized
- timm/dla102x2.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
dla102x2.in1k is an image classifier from timm. It labels an image with one of the 1,000 ImageNet classes.
License: bsd-3-clause (the upstream model's).
Methodology
- Latency: trtexec on the NVIDIA Jetson AGX Thor: batch 1, 500 warm-up runs, then 200 timed; GPU compute is the engine's time on the GPU, without copies to and from it.
- Accuracy: the ImageNet validation set, 50,000 images, on the L4 build's INT8 engine. This page's engine is compiled from the same quantized ONNX, so its accuracy is the same up to the device's kernels, which the self-test checks.
- Self-test: during the build, on the Thor: the runtime's own `embedl info`, `benchmark`, `infer` and its KServe server, and on the L4 build's example images each engine's top class must be in the other's top 3 (they matched exactly on 3 of 3).
- Build: the L4 build's quantized ONNX (Embedl Deploy, INT8 Q/DQ), compiled with TensorRT 10.16.2.10 on the device itself.
- Baseline TensorRT: the original model in FP16 on upstream TensorRT, same settings, same device.