Inference phase
foralliance opened this issue · 2 comments
foralliance commented
@sfzhang15 您好,
在测试时,是按照paper中的参数:
we first filter out most boxes by a confidence threshold of 0.05 and keep the top 400 boxes before applying NMS, then we perform NMS with jaccard overlap of 0.3 and keep the top 200 boxes.
还是直接按照deploy.prototxt中的参数:
layer {
name: "detection_out"
type: "DetectionOutput"
bottom: "mbox_loc"
bottom: "mbox_conf_flatten"
bottom: "mbox_priorbox"
top: "detection_out"
include {
phase: TEST
}
detection_output_param {
num_classes: 2
share_location: true
background_label_id: 0
nms_param {
nms_threshold: **0.3**
top_k: **5000**
}
code_type: CENTER_SIZE
keep_top_k: **750**
confidence_threshold: **0.05**
}
}
貌似paper中的参数(设置的很小(500/200))为了加速用的
sfzhang15 commented
@foralliance
文章中那个是inference时的设置,就是实际用的时候;测试的时候就是prototxt那么设置
foralliance commented
@sfzhang15
thanks