Skip to content

Latest commit

 

History

History
executable file
·
80 lines (62 loc) · 3.81 KB

README.md

File metadata and controls

executable file
·
80 lines (62 loc) · 3.81 KB
Raw

English | 简体中文

Example of PaddleClas models Python Deployment

Before deployment, two steps require confirmation.

This directory provides examples that infer.py fast finishes the deployment of ResNet50_vd on CPU/GPU and GPU accelerated by TensorRT. The script is as follows

# Download deployment example code 
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd  FastDeploy/examples/vision/classification/paddleclas/python

# Download the ResNet50_vd model file and test images 
wget https://bj.bcebos.com/paddlehub/fastdeploy/ResNet50_vd_infer.tgz
tar -xvf ResNet50_vd_infer.tgz
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg

# CPU inference
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device cpu --topk 1
# GPU inference
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --topk 1
# Use TensorRT inference on GPU （Attention: It is somewhat time-consuming for the operation of model serialization when running TensorRT inference for the first time. Please be patient.）
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device gpu --use_trt True --topk 1
# IPU inference（Attention: It is somewhat time-consuming for the operation of model serialization when running IPU inference for the first time. Please be patient.）
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device ipu --topk 1
# XPU inference
python infer.py --model ResNet50_vd_infer --image ILSVRC2012_val_00000010.jpeg --device xpu --topk 1

The result returned after running is as follows

ClassifyResult(
label_ids: 153,
scores: 0.686229,
)

PaddleClasModel Python Interface

fd.vision.classification.PaddleClasModel(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)

PaddleClas model loading and initialization, where model_file and params_file are the Paddle inference files exported from the training model. Refer to Model Export for more information

Parameter

  • model_file(str): Model file path
  • params_file(str): Parameter file path
  • config_file(str): Inference deployment configuration file
  • runtime_option(RuntimeOption): Backend Inference configuration. None by default. (use the default configuration)
  • model_format(ModelFormat): Model format. Paddle format by default

predict function

PaddleClasModel.predict(input_image, topk=1)

Model prediction interface. Input images and output classification topk results directly.

Parameter

  • input_image(np.ndarray): Input data in HWC or BGR format
  • topk(int): Return the topk classification results with the highest prediction probability. Default 1

Return

Return fastdeploy.vision.ClassifyResult structure. Refer to Visual Model Prediction Results for the description of the structure.

Other documents