zdl

Results 9 issues of zdl

我是用gen_wts.py 获得了模型的wts文件(该模型基于yolov7-tiny训练),成功的使用api搭建了网络,同时也生成了engine文件,但是我推理的时候出现什么也检测不到,我的推理后处理均是基于该项目的yolov5,这是什么原因导致的呢。。。 ![image](https://user-images.githubusercontent.com/46549527/178684625-6e373442-61aa-4a3a-b061-c111880c5713.png) ![image](https://user-images.githubusercontent.com/46549527/178684882-7e687b71-68a9-4b7e-9853-7e55b72b9c9b.png)

wontfix

环境: VS2019+cuda11.4+trt8.2+opencv4.5 包含目录: ![image](https://user-images.githubusercontent.com/46549527/175807795-1a70e674-41fa-44bd-a08b-5d2f4de809e0.png) 库目录: ![image](https://user-images.githubusercontent.com/46549527/175807809-e14c1149-5533-4b7c-b581-54848dca6f50.png) 报错信息:...请问这是哪里除了问题了吗, ![image](https://user-images.githubusercontent.com/46549527/175807778-784c4ef4-f258-4822-b0d3-e90ca99b8674.png)

我之前设置了trtpy set-key sxaivip 安装了trt get-env 之后在查看就报错,请问该怎么设置 Download failed: http://zifuture.com:1556/fs/sxaivip .txt Traceback (most recent call last): File "/root/miniconda3/envs/TensorRT/lib/python3.7/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/root/miniconda3/envs/TensorRT/lib/python3.7/runpy.py", line 85, in _run_code exec(code,...

### Search before asking - [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and found no similar questions. ### Question i use yolov8 train mydata ,but have Last error:...

question

我下载了最新的trt_pro的程序,使用了里面的exmple_simple_yolo,编译的时候没有出现问题,可以正常使用,但是使用自己模型就会出现问题: ![image](https://user-images.githubusercontent.com/46549527/201828293-43e7bc19-139d-4559-b26e-8e47de97a3dd.png) 我已经导出为动态的bs,pytorch=1.10,请问这是什么原因,我设置了绝对路径也是包这样的错误。。。

作者您好,我训练自己的数据集(格式为:Tusimple格式)出现一下错误:我应该如何修改呢 ![image](https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2/assets/46549527/61309815-e02b-4f8f-a47f-a2de17b1b59c) 数据集格式: ![image](https://github.com/cfzd/Ultra-Fast-Lane-Detection-v2/assets/46549527/4ee8b680-0b76-451e-b252-59bedf527c24) config如何: dataset= 'Tusimple' data_root= 'train_dataset' # Need to be modified before running epoch= 100 batch_size= 1 optimizer= 'SGD' learning_rate= 0.05 weight_decay= 0.0001 momentum= 0.9 scheduler= 'multi'...

### Required prerequisites - [X] I have read the documentation . - [X] I have searched the [Issue Tracker](https://github.com/baichuan-inc/baichuan-7B/issues) and [Discussions](https://github.com/baichuan-inc/baichuan-7B/discussions) that this hasn't already been reported. (+1 or comment...

bug

paddlex==2.0.0 cuda ==10.2 paddlepaddle==2.1 根据文档进行dll的导出,参考了文档里面的分割模型代码 https://github.com/PaddlePaddle/PaddleX/tree/develop/deploy/cpp/docs/csharp_deploy 出现一下问题: ![image](https://user-images.githubusercontent.com/46549527/142430610-3b2f6169-b6be-48ee-9071-70ba4deaeb57.png) 我的语义分割模型是基于paddlex训练的UNet模型, C#代码: byte[] color_map = get_color_map_list(256); string model_type = "seg"; string model_filename = "F:\\PaddleData2\\semantic_seg\\segmodel\\unet\\inference_model\\inference_model\\model.pdmodel"; string params_filename = "F:\\PaddleData2\\semantic_seg\\segmodel\\unet\\inference_model\\inference_model\\model.pdiparams"; string cfg_file = "F:\\PaddleData2\\semantic_seg\\segmodel\\unet\\inference_model\\inference_model\\model.yml";...

问题1: demo里面有没有量化后的demo案例吗?? 问题2:我已经将yolov5s进行了量化,也量化成功了。如下图所示: ![image](https://github.com/Tencent/TNN/assets/46549527/b9e115d6-5694-4c1b-bb6c-eeec90b887e8) 但是我在代码中测试发现输出全乱了,如果不使用量化模型输出是正常的。 ![image](https://github.com/Tencent/TNN/assets/46549527/d2c2ea88-e358-458d-9a8e-19b5bc2cd135) 这啥原因呢,还有就是我需要反量化吗??没看到API有反量化的参数呀