I tried the pretrained model to process my image and confused on some of the detection speed option.
As you can see from the source code , there are some detection speed option for adjustment. But some of the adjustment option may lead to error, which have been listed below.
I tested other cases and find out the reason may be the number in the options can not be divided by 32. I do not know if it is set on purpose, but I hope it can be fixed.
ps:
This is the pretrained model. Which I have been used.
YOLOv3 (Size = 237 mb, moderate performance and accuracy, with a moderate detection time)
TinyYOLOv3 (Size = 34 mb, optimized for speed and moderate performance, with fast detection time)
I tried the pretrained model to process my image and confused on some of the detection speed option.
As you can see from the source code , there are some detection speed option for adjustment. But some of the adjustment option may lead to error, which have been listed below.
https://github.com/OlafenwaMoses/ImageAI/blob/fe2d6bab3ddb1027c54abe7eb961364928869a30/imageai/Detection/__init__.py#L159
https://github.com/OlafenwaMoses/ImageAI/blob/fe2d6bab3ddb1027c54abe7eb961364928869a30/imageai/Detection/__init__.py#L175
I tested other cases and find out the reason may be the number in the options can not be divided by 32. I do not know if it is set on purpose, but I hope it can be fixed.
ps: This is the pretrained model. Which I have been used. YOLOv3 (Size = 237 mb, moderate performance and accuracy, with a moderate detection time) TinyYOLOv3 (Size = 34 mb, optimized for speed and moderate performance, with fast detection time)