monkeycc

proposal Install locally with pip

1

### proposal Docker images are very troublesome It is recommended to add Install locally with pip `pip install cvat ` ``` https://github.com/heartexlabs/label-studio https://github.com/PaddleCV-SIG/PaddleLabel https://github.com/open-mmlab/labelbee-client ``` Now more and more tools...

An output directory should be added

2

An output directory should be added

unsupported operand type(s) for +: 'WindowsPath' and 'str'

1

``` Traceback (most recent call last): File "E:\JSON2YOLO-master\general_json2yolo.py", line 397, in convert_vott_json(name='data', File "E:\JSON2YOLO-master\general_json2yolo.py", line 73, in convert_vott_json name = path + os.sep + name TypeError: unsupported operand type(s) for...

GPU编译报错 subprocess.CalledProcessError: Command '['D:\\Anaconda3\\Library\\bin\\cmake.exe', '--build', '.', '--config', 'Release', '--', '/maxcpucount:20']' returned non-zero exit status 1.

3

``` set "CUDA_DIRECTORY"="C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.6" set WITH_GPU=ON set ENABLE_ORT_BACKEND=ON set ENABLE_TRT_BACKEND=OFF set ENABLE_PADDLE_BACKEND=ON set ENABLE_VISION=ON set ENABLE_VISION_VISUALIZE=ON (fastdeploy) PS D:\FastDeploy\python> python setup.py build running build running build_py running...

视觉模型部署没有实例分割吗

4

视觉模型部署没有 实例分割 吗

Python如何解决模型加密问题 训练出来的模型 不想给别人用 python可以加密成pyd文件 或者用nuitka打包编译 但是模型怎么办

UnboundLocalError: local variable 'H' referenced before assignment

1

``` Traceback (most recent call last): File "d:\Image-Stitching-OpenCV\Image_Stitching.py", line 92, in main(imageA,imageB) File "d:\Image-Stitching-OpenCV\Image_Stitching.py", line 74, in main final=Image_Stitching().blending(imageA,imageB) File "d:\Image-Stitching-OpenCV\Image_Stitching.py", line 51, in blending H = self.registration(img1,img2) File "d:\Image-Stitching-OpenCV\Image_Stitching.py",...

想要把识别出来的 裁剪图片出来 ``` https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/segmentation_result.md fastdeploy.vision.SegmentationResult label_map(list of int): 成员变量，表示单张图片每个像素点的分割类别 score_map(list of float): 成员变量，与label_map一一对应的所预测的分割类别概率值(当导出模型时指定--output_op argmax)或者经过softmax归一化化后的概率值(当导出模型时指定--output_op softmax或者导出模型时指定--output_op none同时模型初始化的时候设置模型[类成员属性](https://github.com/PaddlePaddle/FastDeploy/blob/develop/examples/vision/segmentation/paddleseg/python)apply_softmax=true) shape(list of int): 成员变量，表示输出图片的shape，为H*W ``` PaddleX中 我看有可以解析mask的 但是fastdeploy 不知道怎么实现 想要把识别出来的 裁剪图片出来 或者不能用语义分割来裁剪 要用实例分割?

vision.vis_detection 可以自定义颜色吗 比如我要全部统一红色

Runtime initialized with Backend::ORT in Device:: CPU 和 GPU 有问题

2

## 环境 FastDeploy版本： fastdeploy-gpu-python 0.6.0 pip 系统平台: Windows x64(Windows11) 硬件： cuda11.6 cudnn8.4 编译语言： Python(3.7） 问题描述 ## 问题描述 ``` import cv2 import fastdeploy.vision as vision model = vision.detection.PPYOLOE("ppyoloe_crn_l_300e_coco/model.pdmodel", "ppyoloe_crn_l_300e_coco/model.pdiparams", "ppyoloe_crn_l_300e_coco/infer_cfg.yml") im...