TA的每日心情 | 奋斗
1 小时前 |
|---|
签到天数: 3387 天 连续签到: 9 天 [LV.Master]2000FPS
|
发表于 2020-11-14 11:35:46
|
显示全部楼层
|阅读模式
来自：广东省东莞市 电信
注册登陆后可查看附件和大图，以及购买相关内容
您需要 登录 才可以下载或查看，没有账号？注册会员
x
MVTEC Halcon 20.05.0.1 Progress Deep Learning Core Win32/Win64 HALCON深度学习内核20.05.0.1 32位/64位Windows版
HALCON 20.05.0.1 Deep Learning Core - Additional Core Functionality Required for Deep Learning (x86sse2-win32 / x64-win64), Add-on to Full/Runtime Version：
文件名: halcon-20.05.0.1-windows-deep-learning-core.exe
文件大小: 1023390920 字节 (975.98 MB)
修改日期: 2020-11-05 13:29
版本: 20.5.0.1
MD5: 50eb0a9e1dfa71bc7f4e89197f321264
SHA1: 8528e0a0d981fbb6f85fba2100ff5158673365f2
SHA256: eddefed461422bcb3ba315a77fb7f8ef8fe77afa14df605b93ad3cbd8756be1a
CRC32: f7167444
MVTEC官方下载（需要注册、国外IP地址可能被墙）
www.mvtec.com
百度网盘下载地址：
链接:提取码: idhc
Release Notes for HALCON 20.05.0.1 Progress
Hotfix for HALCON 20.05.0.0 Progress
This document provides the release notes for MVTec HALCON 20.05.0.1 Progress, as released in July 2020, which is a Hotfix for HALCON 20.05.0.0 Progress. For general information like licensing or supported operating systems, see the release notes of HALCON 20.05.0.0 Progress.
Contents
Detailed Description of Changes in HALCON 20.05.0.1 Progress (Hotfix)
Deep Learning
Matching
Licensing
Release Notes of Previous HALCON Versions
Detailed Description of Changes in HALCON 20.05.0.1 Progress (Hotfix)
The changes in HALCON 20.05.0.1 Progress are described with respect to HALCON 20.05.0.0 Progress.
Deep Learning
If the system parameter "cudnn_deterministic" was specified as "true" and the model parameter "optimize_for_inference" was also "true", the training of this deep learning model did not use the corresponding deterministic cuDNN backward algorithm for convolution layers as required. Hence, the training of such a model was most likely not deterministic on a GPU. This problem has been fixed.
Matching
find_shape_model, find_shape_models, find_scaled_shape_model, find_scaled_shape_models, find_aniso_shape_model, find_aniso_shape_models, and find_shape_model_3d did not abort in a timeout error in rare cases where the operator was parallelized and a timeout was set. This problem has been fixed.
Licensing
When using a license bound to a dongle, HDevelop could periodically fail to communicate with the dongle and complain about a licensing error in response. This problem has been fixed.
Release Notes of Previous HALCON Versions
Follow this link to read about the changes of previous HALCON versions.
|
|
