神木
神木
i using py_cpu_nms instead of cpu_nms or gpu_nms . there are any result different ?
Any one using this tf-faster-rcnn on Caltech Pedestrian Detection? I using fasterrcnn with vgg16 only get 22% missrate Q_Q  my e-mail:[email protected]
When i trans nn_base from resnet to vgg there are big different can u using vgg as nn_base before? resnet :good detection vgg:bad detection
When i trans nn_base from resnet to vgg there are big different can u using vgg as nn_base before? resnet :good detection vgg:bad detection