![](https://img-blog.csdnimg.cn/20201014180756928.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
pytorch
文章平均质量分 55
weixin_44576543
QQ 1154957554 欢迎交流探讨
展开
-
websocket_flask
1.使用socket协议构建server client文件,服务端构建maskrcnn分割模型,客户端发送图片返回分割结果;使用纯socket通信,通信传输效率较低,接收数据需要1024byte连续接收。实现client send req: (GET / HTTP/1.1 Host: 127.0.0.1:9999)1. 接受静态请求,`html`,`png`等文件。4. `root`是根目录,包含资源文件,脚本等。2. 接受动态请求,脚本类型为`python`Http服务器实现-resent分类任务。原创 2023-01-09 22:47:00 · 286 阅读 · 1 评论 -
cvzone base the mediapipe and opencv
GitHub - cvzone/cvzone: This is a Computer vision package that makes its easy to run Image processing and AI functions. At the core it uses OpenCV and Mediapipe libraries.You can simply use pip to install the latest version of cvzone.pip install cvzone原创 2021-12-22 11:33:24 · 3059 阅读 · 0 评论 -
pytorch_visdom可视化
1 pytorch show by visdomTraceback (most recent call last): File "/home/sx/anaconda3/envs/py35/lib/python3.5/site-packages/visdom/__init__.py", line 711, in _send data=json.dumps(msg), File "/home/sx/anaconda3/envs/py35/lib/python3.5/site-package原创 2021-11-22 18:08:05 · 983 阅读 · 0 评论 -
pytorch model_vision显示网络结构
1 show the model structureimport torch.nn as nnimport torchfrom torchsummary import summary# from models.resnet import mobilenetdef conv_bn(inp, oup, stride = 1): return nn.Sequential( nn.Conv2d(inp, oup, 3, stride, 1, bias=False), .原创 2021-11-19 09:41:56 · 207 阅读 · 0 评论