ft (INT8) · in1k-timm_int8_embedl_tensorrt
- timm
- INT8
- L4
- Labels
- Image
- Classification
- Build
- Embedl-optimized
- Precision
- INT8
- Runtime
- TensorRT 11.2.1 with Embedl optimizations
vit_tiny_patch16_224.augreg_in21k_ft_in1k is an image classifier from timm. It labels an image with one of the 1,000 ImageNet classes.
Methodology
- Latency: trtexec on the NVIDIA L4 with TensorRT 11.2.1: batch 1, median and p99 over the timed iterations.
- Accuracy: the ImageNet validation set, 50,000 images, on the NVIDIA L4.
- Build: Embedl Deploy INT8 quantization, calibrated on ImageNetCalibDataset (5,000 samples), compiled with TensorRT 11.2.1 on the NVIDIA L4.