muyi

Did you solve this problem？

There are little difference between python2 and python3 in this project.

1.https://blog.csdn.net/qq_29921623/article/details/80047339 before example = _convert_to_example(filename, bboxes, image_buffer, height, width) add filename = filename.encode() 2.deleted the Nan valude in pcd0132cpos.txt and pcd0165cpos.txt file

同学你好 你现在还有在做抓取相关的么

看一下论文 V. EXPERIMENTS AND EVALUATION C. Pretraining z > > But I still don not understand why the loss is stable at 30000-40000! > > 同学，我是做抓取新手。在开始阅读代码的时候，我对一步就很不理解，他说需要将imagenet数据转换为tfrecord,然后需要下imagenet的数据集。。。这里我很不理解，文章不是用的cornell grasping dataset，为什么需要下载imagenet数据集，主要是看到Imagenet数据集太大，学校网速太慢了，希望大佬能给解答一下，谢谢。。。

就是这个代码的论文呀 论文名字是：Real-Time Grasp Detection Using Convolutional Neural Networks 第 V 章 C 节 > > 看一下论文 > > V. EXPERIMENTS AND EVALUATION > > C. Pretraining > > z >...

在这说吧，看到会回复你的 > > 就是这个代码的论文呀 > > 论文名字是：Real-Time Grasp Detection Using Convolutional Neural Networks > > 第 V 章 C 节 > > > > 看一下论文 > > > > V....

> Not sure what the problem is and I don't work on this anymore. But those links/joints are declared here: https://github.com/philwall3/UR5-with-Robotiq-Gripper-and-Kinect/blob/master/robotiq_85_gripper-master/robotiq_85_description/urdf/robotiq_85_gripper.urdf.xacro ### **this urdf file different with thr official** ###...

Do you success calibration with Kinova Jaco2 arm now?