For VPU - we use grouped-convolution, but we refrain from using Squeeze-and-excitement (SE) blocks - specifically this includes the following models: EfficientNet-lite / MixNet [76] / GhostNet [21] / MobileNetV3 #5565
No. yolov4 is for GPU.
We are exploring different models for yolov4-vpu,, but it seems we will not use: Grouped/Depthwise-conv, SE-blocks, Swish/Mish-activations.
yolov4 use group-conv ?