Comments (9)
看了下src,还需要实现rpn和roi pooling才能支持faster rcnn
roi pooling用caffe有直接改用它的forward就好,rpn没有C版本的,
之前实现了一个C版本rpn demo,并且稍微修改点算法,放回framework中比原版本性能要好些,
https://github.com/wangshankun/rcnn-optimize/tree/master/rpn_proposal
from paddle-lite.
To support faster rcnn model, several layers need to add, such as SmoothL1LossLayer、RoiPoolingLayer, as for caffe2mdl, customization for faster rcnn is needed too.
from paddle-lite.
I think this project needs to support the SSD model,
Please reference to OpenCV 3.3.0 DNN model.
from paddle-lite.
I want to know how to resolve it and When?
Thanks!
from paddle-lite.
To solve the issuse #49, a customied ReshapeLayer need to be added.
from paddle-lite.
To support ResNet, eltwiseLayer need to be customised. #47
from paddle-lite.
@wangshankun ,thank you for sharing your excellent optimization work on rpn layer, we will read your code carefully! If you want to be one of our contributors, please send PR to us.
from paddle-lite.
@cocodark 对此项目很感兴趣,但是我这边不具备ios、android开发和测试环境,虽然也是在嵌入式设开发,但是对android这套不熟悉,所有没办法高效的切入此项目;因此我才申请提出在Ubuntu下开发和demo的功能扩展: issues 54
#54
from paddle-lite.
@cocodark How are you getting along with v1.1?
from paddle-lite.
Related Issues (20)
- PaddleLite ascend310推理一直输出Failed to run the execution(2) HOT 3
- RK3568 RK3588在android11下进行paddleocr推理应用,paddlelite编译找不到合适tim-vx sdk版本和驱动 HOT 8
- paddleocr官方训练模型转为inference模型成功,然后转nb模型报错 HOT 1
- Raspberry Pi 5 (and 4) build_linux.sh building optimize tool fails HOT 1
- paddleLite在arm上推理与onnxruntime推理耗时差异过大 HOT 4
- INT8 量化模型在 ARM Android上的性能严重缩水,无法复现在benchmark.md中的加速比 HOT 2
- Lite/lite/operators/fill_constant_op.cc:44 InferShapeImpl] no valid out_shape. Must set one of shape_tensor, or shape_tensor_list, or shape. HOT 1
- Check failed: kernels.size() > 0 (0 vs. 0) HOT 1
- nb模型处理异常(iOS)引发的崩溃 HOT 4
- paddle ocr rec v3 模型推理崩溃(iOS) HOT 5
- 编译鸿蒙版本时,用鸿蒙提供的ohos工具编译Paddle Lite失败 HOT 10
- Facing crash with some devices only HOT 6
- 是否可以提供iOS metal相关的预编译库 HOT 8
- 关于arm下的paddle lite安装包文通 HOT 7
- loongarch64编译支持 HOT 2
- 线上发现一些Arm机型在获取CPU信息时越界。 HOT 1
- padddedetection 模型转换失败 HOT 13
- Paddle-Lite新需求收集(call for new feature request) HOT 6
- build.sh操作不成功 HOT 4
- PaddleLite生成缓存文件*.nnc需要在有目标芯片的环境上进行吗 HOT 22
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from paddle-lite.