10 Star 20 Fork 12

DeepSpark/DeepSparkInference

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
文件
克隆/下载
贡献代码
同步代码
取消
提示: 由于 Git 不支持空文件夾,创建文件夹后会生成空的 .keep 文件
Loading...
README

Inception-ResNet-V2 (IxRT)

Model Description

Inception-ResNet-V2 is a deep learning model proposed by Google in 2016, which combines the architectures of Inception and ResNet. This model integrates the dense connections of the Inception series with the residual connections of ResNet, aiming to enhance model performance and training efficiency.

Supported Environments

Iluvatar GPU IXUCA SDK
MR-V100 4.2.0

Model Preparation

Prepare Resources

Pretrained model: http://data.lip6.fr/cadene/pretrainedmodels/inceptionresnetv2-520b38e4.pth

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

Install Dependencies

# Install libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-glx

pip3 install -r requirements.txt

Model Conversion


mkdir checkpoints
python3 export_model.py --output_model /Path/to/checkpoints/inceptionresnetv2.onnx

Model Inference

export PROJ_DIR=/Path/to/inceptionresnetv2/ixrt
export DATASETS_DIR=/path/to/imagenet_val/
export CHECKPOINTS_DIR=./checkpoints
export RUN_DIR=/Path/to/inceptionresnetv2/ixrt
export CONFIG_DIR=/Path/to/config/INCEPTIONRESNETV2_CONFIG
export PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python

FP16

# Accuracy
bash scripts/infer_inceptionresnetv2_fp16_accuracy.sh
# Performance
bash scripts/infer_inceptionresnetv2_fp16_performance.sh

INT8

# Accuracy
bash scripts/infer_inceptionresnetv2_int8_accuracy.sh
# Performance
bash scripts/infer_inceptionresnetv2_int8_performance.sh

Model Results

Model BatchSize Precision FPS Top-1(%) Top-5(%)
Inception-ResNet-V2 64 FP16 871.74 80.20 95.18
Inception-ResNet-V2 64 INT8 1059.35 79.73 95.04
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
Python
1
https://gitee.com/deep-spark/deepsparkinference.git
git@gitee.com:deep-spark/deepsparkinference.git
deep-spark
deepsparkinference
DeepSparkInference
master

搜索帮助

371d5123 14472233 46e8bd33 14472233