If we replace AlexNet with a Resnet50 model for training a fast-RCNN network, how should we initialize the ROI pooling layer? I saw for VGG and AlexNet, it's as follows:
local ROIPooling = detection.ROIPooling(6,6):setSpatialScale(1/16)
How should we calculate the spatial scale for a ResNet50?
If we replace AlexNet with a Resnet50 model for training a fast-RCNN network, how should we initialize the ROI pooling layer? I saw for VGG and AlexNet, it's as follows: local ROIPooling = detection.ROIPooling(6,6):setSpatialScale(1/16) How should we calculate the spatial scale for a ResNet50?