mobilenetv3-segmentation
mobilenetv3-segmentation copied to clipboard
Tramac
Image size
Why is it requiring such huge images of >512? Original mobilenetV3 accepts small 244*244 images.
The segmentation head expects big images (from datasets like Cityscapes). Check the LRASPP implementation in the paper. I was able to fix this by using AdaptiveAvgPooling instead of AvgPool in the LRASPP implementation.
The segmentation head expects big images (from datasets like Cityscapes). Check the LRASPP implementation in the paper. I was able to fix this by using AdaptiveAvgPooling instead of AvgPool in the LRASPP implementation.
When i exported ONNX model, ONNX cannot support adaptive_avg_pool2d.How can i fix the problem?Or when i export PNNX model ,PNNX cannot support node Tensor.expand_as.
