代码拉取完成,页面将自动刷新
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.
Iluvatar GPU | IXUCA SDK |
---|---|
MR-V100 | 4.2.0 |
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 libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-glx
pip3 install -r requirements.txt
mkdir checkpoints
python3 export_model.py --output_model /Path/to/checkpoints/inceptionresnetv2.onnx
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
# Accuracy
bash scripts/infer_inceptionresnetv2_fp16_accuracy.sh
# Performance
bash scripts/infer_inceptionresnetv2_fp16_performance.sh
# Accuracy
bash scripts/infer_inceptionresnetv2_int8_accuracy.sh
# Performance
bash scripts/infer_inceptionresnetv2_int8_performance.sh
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 |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。