igie

EfficientNetv2_rw_t (IGIE)

Model Description

EfficientNetV2_rw_t is an enhanced version of the EfficientNet family of convolutional neural network architectures. It builds upon the success of its predecessors by introducing novel advancements aimed at further improving performance and efficiency in various computer vision tasks.

Supported Environments

GPU	IXUCA SDK	Release	Branch
MR-V100	4.4.0	26.03	release/26.03
MR-V100	4.3.0	25.12	release/25.12

Note: 请切换到与您的 SDK 版本对应的 Release 分支进行测试。请勿直接在 master 分支上运行测试，因为 master 分支可能包含与您的本地 SDK 版本不兼容的最新更改。

切换分支命令示例：git checkout release/26.03

Model Preparation

Prepare Resources

Pretrained model: https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/efficientnetv2_t_agc-3620981a.pth

Dataset: https://www.image-net.org/download.php to download the validation dataset.

Install Dependencies

pip3 install -r ../../igie_common/requirements.txt
pip3 install timm

Model Conversion

python3 ../../igie_common/export_timm.py --model-name efficientnetv2_rw_t --weight efficientnetv2_t_agc-3620981a.pth --output efficientnetv2_rw_t.onnx

Model Inference

export DATASETS_DIR=/Path/to/imagenet_val/
export RUN_DIR=../../igie_common/

FP16

# Accuracy
bash scripts/infer_efficientnetv2_rw_t_fp16_accuracy.sh
# Performance
bash scripts/infer_efficientnetv2_rw_t_fp16_performance.sh

Model Results

Model	BatchSize	Precision	FPS	Top-1(%)	Top-5(%)
Efficientnetv2_rw_t	32	FP16	831.678	82.306	96.163