代码拉取完成,页面将自动刷新
SqueezeNet 1.1 is a deep learning model for image classification, designed to be lightweight and efficient for deployment on resource-constrained devices.
It was developed by researchers at DeepScale and released in 2016.
# Install libGL
## CentOS
yum install -y mesa-libGL
## Ubuntu
apt install -y libgl1-mesa-dev
pip3 install tqdm
pip3 install onnx
pip3 install onnxsim
pip3 install tabulate
pip3 install ppq
pip3 install pycuda
pip3 install opencv-python==4.6.0.66
Pretrained model: https://download.pytorch.org/models/squeezenet1_1-b8a52dc0.pth
Dataset: https://www.image-net.org/download.php to download the validation dataset.
mkdir checkpoints
python3 export_onnx.py --origin_model /path/to/squeezenet1_1-b8a52dc0.pth --output_model checkpoints/squeezenetv11.onnx
export PROJ_DIR=./
export DATASETS_DIR=/path/to/imagenet_val/
export CHECKPOINTS_DIR=./checkpoints
export RUN_DIR=./
export CONFIG_DIR=config/SQUEEZENET_V11_CONFIG
# Accuracy
bash scripts/infer_squeezenet_v11_fp16_accuracy.sh
# Performance
bash scripts/infer_squeezenet_v11_fp16_performance.sh
# Accuracy
bash scripts/infer_squeezenet_v11_int8_accuracy.sh
# Performance
bash scripts/infer_squeezenet_v11_int8_performance.sh
Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) |
---|---|---|---|---|---|
SqueezeNet 1.1 | 32 | FP16 | 13701 | 0.58182 | 0.80622 |
SqueezeNet 1.1 | 32 | INT8 | 20128 | 0.50966 | 0.77552 |
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。