Closed sudapure closed 3 years ago
Sure. It's ok to replace the backbone network. The only modification is to choose a proper location to append the ALM modules. Speed can be improved with lightweight backbones.
Sure. It's ok to replace the backbone network. The only modification is to choose a proper location to append the ALM modules. Speed can be improved with lightweight backbones.
in such case ? where can we use it for replace the model backbone..?
Sure. It's ok to replace the backbone network. The only modification is to choose a proper location to append the ALM modules. Speed can be improved with lightweight backbones.
in such case ? where can we use it for replace the model backbone..?
BNInception
class in inception_iccv.py
defined the backbone.
You can replace it with others, like ResNet, and modify the corresponding codes in the InceptionNet
class.
From the code-base and paper implementation it looks like inception backbone is very native and adaptive to the complete attribute specified localization network, however the
BNInceptionNet
is bit heavy and contribute to high number of latency time during inference which makes it practically not suitable for the real-time surveillance scenarios, so will it be possible to replace the inception backbone network with any other lightweight backbones like mobilenet ,effecientNet-l0, etc, if it is feasible then how much it could impact the speed/accuracy factor.