robotic-grasping
robotic-grasping copied to clipboard
How to use image-wise (IW) and object-wise (OW) data splits mentioned in the paper?
You can use the ds-shuffle
parameter for it. The default is object-wise (OW) and setting it to True
with give you image-wise (IW).
The default value is OW. If IW is required, do I need to change the "DS-shuffle" part in the training and test code to true, and use "DS-shuffle" in the command line?
image-wise。at test time ,do l need ds-shuffle=True?
Hi, skumra! I have the same question. I don't understand why I turn "ds-shuffle" it will become IW? It just make the index become shuffled.
Hi, skumra! I have the same question. I don't understand why I turn "ds-shuffle" it will become IW? It just make the index become shuffled.
I understand the reason. I am sillyB.
image-wise。at test time ,do l need ds-shuffle=True?
When I set the flag to True in the testing time, the accuracy is only76%