FastDeploy

FastDeploy copied to clipboard

[Model] Support PaddleDetection SSD Model

3

### PR types(PR类型) Model ### Describe - Support PaddleDetection SSD Model

totorolin

[Backend] cuda normalize and permute, cuda concat, optimized ppcls, ppdet & ppseg

3

### PR types(PR类型) Backend ### Describe - CUDA kernel for Color convert + Normalize + Permute - Concat support GPU - Applied this optimization to PPClas, PPDet and PPSeg -...

wang-xinyu

### Describe - Update p2o version to 1.0.3

yeliang2258

请问在jetson 上能运行benchmark?

4

当运行时报错 [ERROR] fastdeploy/runtime.cc(319)::EnablePaddleToTrt While using TrtBackend with EnablePaddleToTrt, require the FastDeploy is compiled with Paddle Inference Backend, please rebuild your FastDeploy. 重新编译 CMake Error at cmake/paddle_inference.cmake:67 (message): Paddle Backend doesn't...

tomjeans

Due to the unsupported operators, the conversion is aborted.

11

/home/aistudio/work/FastDeploy/examples/vision/detection/paddledetection/quantize/python [INFO] fastdeploy/vision/common/processors/transform.cc(45)::FuseNormalizeCast Normalize and Cast are fused to Normalize in preprocessing pipeline. [INFO] fastdeploy/vision/common/processors/transform.cc(93)::FuseNormalizeHWC2CHW Normalize and HWC2CHW are fused to NormalizeAndPermute in preprocessing pipeline. [INFO] fastdeploy/vision/common/processors/transform.cc(159)::FuseNormalizeColorConvert BGR2RGB and NormalizeAndPermute...

weijingsu

### PR types(PR类型) The title of this pull request should be `[PR type] Description of this pull request`, e.g `[Model] PP-Matting deployment support` PR的标题应该为 `[PR type] Description of this pull...

triple-Mu

### PR types(PR类型) Model ### Describe - Refactor YOLOv5 module

wjj19950828

Dynamic Batch Inference

18

I have exported my yolov7 model with dynamic axes as tensorrt.Engine runs fine on single batch but I want to be able to make inference with multiple images.How can I...

UygarUsta99

PPYOLO不支持TRT后端

1

使用命令运行`python infer_ppyolo.py --model_dir ppyolo_mbv3_small_coco --image 000000014439.jpg --device gpu --use_trt True` 发现 `PaddleDetection/PPYOLO is not supported with backend Backend::TRT.` 而且cpu推理时间比gpu推理时间快

jo-dean

拆分PaddleDetection模块为Preprocessor、Postprocessor，支持批量预测

jiangjiajun