yghstill commented 2 years ago

PP-PicoDet是轻量级实时移动端目标检测模型，我们提出了从小到大的一系列模型，包括S、M、L等，超越现有SOTA模型。

模型特色：

🌟精度高：1M参数量以内mAP(0.5:0.95)达到30.6，3.3M参数量mAP(0.5:0.95)达到40.9。
🚀速度快：在SD865上达到150FPS。
😊部署友好：我们支持PaddleInference/PaddleLite/MNN/NCNN/OpenVINO，并且提供C++/Python/Android demo。

链接：

详细算法细节请参考paper：https://arxiv.org/abs/2111.00902
Readme&配置文件： https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.3/configs/picodet

欢迎大家试用，有疑问欢迎讨论盖楼~

和其他模型对比：

FAQ汇总： （持续更新中）

版本要求： 训练导出模型要求Paddle版本统一，同时 PaddlePaddle >= 2.1.2。
学习率、GPU数和batch-size关系： 采用线性伸缩准则，发布的配置文件基本都是4卡GPU训练的，例如：变成单卡，请学习率除以4，如果batch size从80变成40，请学习率再除以2。
配置优先级： 一般picodet_x_coco.yml中的配置优先级高于__base__中配置，picodet_x_coco.yml中的所有设置会覆盖__base__中配置，所以修改picodet_x_coco.yml的配置即可。
在自己数据集上训练模型： 支持COCO和VOC两种数据格式，同时建议采用迁移学习加快收敛，具体步骤：从PicoDet的Readme中拷贝COCO上训好的pretrain weights链接，更新配置文件中pretrain_weights参数为COCO上训好的权重。

为了方便大家交流沟通，欢迎扫码添加微信群，继续交流有关PP-PicoDet的使用及建议~

yghstill commented 2 years ago

@zhouweic36 paddlelite android demo可以参考：https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/picodet#deploy

txx-899 commented 2 years ago

您好，请问训练时保存的参数文件.pdparams比官方的参数量大是为什么呢？另PicoDet技术交流群二维码有新的吗？谢谢

yghstill commented 2 years ago

您好，请问训练时保存的参数文件.pdparams比官方的参数量大是为什么呢？另PicoDet技术交流群二维码有新的吗？谢谢

官方文档描述的是参数量，是单独计算出来的，一般大约为模型体积的1/4。PicoDet技术交流群二维码已更新。

lguowang commented 2 years ago

大家好，我用pp训练了PicoDet，然后导出模型进行sering部署，但预测时出现主要的错误： {'err_no': 8, 'err_msg': "(data_id=0 log_id=0) [ppyolo|0] Failed to postprocess: 'transpose_17.tmp_0.lod'", 'key': [], 'value': [], 'tensors': []} 请问 fetch_list: 要配置成什么样的？请问 fetch_list: 要配置成什么样的？请问 fetch_list: 要配置成什么样的？

serving_server 中的 serving_server_conf.prototxt ： feed_var { name: "image" alias_name: "image" is_lod_tensor: false feed_type: 1 shape: 1 shape: 3 shape: 416 shape: 416 } fetch_var { name: "transpose_10.tmp_0" alias_name: "transpose_10.tmp_0" is_lod_tensor: false fetch_type: 1 shape: 1 shape: 2704 shape: 4 } fetch_var { name: "transpose_11.tmp_0" alias_name: "transpose_11.tmp_0" is_lod_tensor: false fetch_type: 1 shape: 1 shape: 2704 shape: 32 } fetch_var { name: "transpose_12.tmp_0" alias_name: "transpose_12.tmp_0" is_lod_tensor: false fetch_type: 1 shape: 1 shape: 676 shape: 4 } fetch_var { name: "transpose_13.tmp_0" alias_name: "transpose_13.tmp_0" is_lod_tensor: false fetch_type: 1 shape: 1 shape: 676 shape: 32 } fetch_var { name: "transpose_14.tmp_0" alias_name: "transpose_14.tmp_0" is_lod_tensor: false fetch_type: 1 shape: 1 shape: 169 shape: 4 } fetch_var { name: "transpose_15.tmp_0" alias_name: "transpose_15.tmp_0" is_lod_tensor: false fetch_type: 1 shape: 1 shape: 169 shape: 32 } fetch_var { name: "transpose_16.tmp_0" alias_name: "transpose_16.tmp_0" is_lod_tensor: false fetch_type: 1 shape: 1 shape: 49 shape: 4 } fetch_var { name: "transpose_17.tmp_0" alias_name: "transpose_17.tmp_0" is_lod_tensor: false fetch_type: 1 shape: 1 shape: 49 shape: 32 }

我配置的config.yml: dag: is_thread_op: false tracer: interval_s: 30 http_port: 18888 op: ppyolo: concurrency: 1

local_service_conf:
  client_type: local_predictor
  device_type: 1
  devices: '0'
  fetch_list: 
  - transpose_17.tmp_0
  model_config: serving_server/

rpc_port: 9998 worker_num: 2

请问 fetch_list: 要配置成什么样的？请问 fetch_list: 要配置成什么样的？

sdreamforchen commented 2 years ago

python tools/export_model.py -c configs/picodet/picodet_L_640_coco.yml -o weights=https://paddledet.bj.bcebos.com/models/pretrained/ESNet_x1_25_pretrained.pdparams --output_dir=inference_model TestReader.inputs_def.image_shape=[3,640,640] 1改了下激活函数+2执行上面的指令，一路调试，现在遇到这个报错，实在不知道怎么走下去了。 [Hint: 'cudaErrorInitializationError'. The API call failed because the CUDA driver and runtime could not be initialized. ] (at /paddle/paddle/fluid/platform/gpu_info.cc:108) 3安装了paddlepaddle-gpu2.2.2+paddledet2.3.0+paddle2onnx0.9.1

sdreamforchen commented 2 years ago

另外，想请教下，看了下cfg文件，数据增强只用了这个吗- RandomFlip: {prob: 0.5}

yghstill commented 2 years ago

@sdreamforchen 数据增强包含crop和flip还有RandomDistort

导出未修改的模型预测结果正常吗？需要看下你修改的位置，改了什么激活函数。

sdreamforchen commented 2 years ago

您好，我改了hard sigmoid和hard swish（基于relu6实现），因为我的下游嵌入式对这两个函数支持也存在一定的问题；改了后用eval.py测试了下，各方面都是对的，就是延迟厉害，Titan RTX才17帧，l-640模型。 1 转为onnx后，出现了一个新的问题：我下载的官方的onnx和我转换后的onnx的conv和bn处在差异，官方的是融合一起的，而我的是分开的，这个不知道是为啥，通过netron查看的。 2 另外，通过安装nccl之类的操作，目前用单卡训练，出现我配置export CUDA_VISIBLE_DEVICES=4，但是train还是去用GPU:0，而eval没有问题。这个问题，我可以慢慢去学习paddle，看看代码，如果方便就麻烦回答一下吧。谢谢。

sdreamforchen commented 2 years ago

@sdreamforchen 数据增强包含crop和flip还有RandomDistort

导出未修改的模型预测结果正常吗？需要看下你修改的位置，改了什么激活函数。

之所以改激活函数，是因为转换后的onnx的hardsigmoid函数。下游嵌入式会报错。今天用netron确认了问题，查看了转换的alpha不是0.2是0.166667

yghstill commented 2 years ago

@sdreamforchen

网络预测时延测试的话需要在具体的硬件上测试，eval.py脚本打印的FPS只是训练前向，和预测库预测不太一样，预测库做过预测加速，更快些。
转onnx后需要使用onnx-simplifier工具对模型进行简化融合操作，就可以看到conv bn已经fuse了。
关于训练GPU的问题一般指定CUDA_VISIBLE_DEVICES变量即可，看下是否是环境变量没有生效？

tb5874 commented 2 years ago

Hello, yghstill PaddleDetection is wonderful platform. Thank you.

Should i ask some question of PaddleDetection-PP-PicoDet with Pytouch to TensorRT?

I found some information about Pytouch to TensorRT. I think that TensorRT improve calculation performance when PP-PicoDet doing Parallel Processing. If your PP-PicoDet team have Idea or Plan about Pytouch to TensorRT, could you tell me?

When I ask a question, i immediately found your guide 'Convert to ONNX'. Currently, Is that the best-way for Pytouch to TensorRT ? ( PyTorch -> ONNX-> TensorRT ) Have your team another plan ?

Thank you.

When I wake up in the morning, I thought that question was worng. ;) sorry. Please Ignore above all Question.. So now, Question is that ' Have your team Convert-Plan about ONNX to TensorRT ?' X_D Please Understand me.. Thank you.

yghstill commented 2 years ago

@tb5874 PP-PicoDet is a mobile model, and it is not planned to support TensorRT, but the upcoming PP-YOLOE model will support the function of TensorRT, welcome to pay attention.

sdreamforchen commented 2 years ago

So good！想请问下，nccl想过的提示是，让我们安装nccl2.这个和conda install -c anaconda nccl是不一样的吗？还是必须用https://docs.nvidia.com/deeplearning/nccl/install-guide/index.html这个方法是安装nccl？

tb5874 commented 2 years ago

@yghstill Thank you for your kind explanation. So, If i use low computing power( CPU with GPU, like Nvidia Jetson Xavier NX, but not mean restrained Nvidia Platform. ) ( But i know, currently easily applicable GPU is Nvidia. So i don't care if you restrain Nvidia. ) Your best recommand model is upcoming PP-YOLO-E ?

I have AMD Ryzen5 5600G( 6 core, 3.9GHz ) with RTX3060. ( but i have another GPU(RTX3090). So i will test it. ) and Nvidia Jetson Xavier NX( 6 core, 1.4GHz) with Volta architecture(384 CUDAcore, 48 TENSORcore) I just want to test this wonderful Object Detector :)

Target is low computing power, Like above environment. ( Nvidia Jetson Xavier NX or normal desktop )

Should i ask some best recommend of PaddleDetection Object Detector. like above environment ?

Thank you.

yghstill commented 2 years ago

@tb5874 It is also recommended that you use the PP-YOLOE model. We tested it on Jetson Xavier NX and it performs well

tb5874 commented 2 years ago

@yghstill Thank you ! So now, For understand upcomming PP-YOLOE, PP-YOLO is background? or PP-YOLOE is another paper? When i read PP-YOLO paper ( https://arxiv.org/pdf/2007.12099.pdf ), i found PP-YOLO with Method 'E + Grid Sensitive'. That is not mean PP-YOLOE ? X_D..

If that is not mean PP-YOLOE, should i pre-test PP-YOLOE ?

Thank you.

yghstill commented 2 years ago

@tb5874 PP-YOLOE is another paper, and it is coming soon.