Ultra-Light-Fast-Generic-Face-Detector-1MB
Ultra-Light-Fast-Generic-Face-Detector-1MB copied to clipboard
模型加了detection_out层再转ncnn出错
您好: 我在caffe的prototxt的上加上了detectin_output层,重新训练,然后转为ncnn模型(没有转no_bn,也没有做量化),然后脚本在写: ncnn::Mat out; ex.extract("detection_out", out); TIME_END("run model");
的时候,出现了: terminate called after throwing an instance of 'std::length_error' what(): vector::_M_default_append Aborted (core dumped)
这样的错误,请问您知道这是什么原因造成的么? 在caffe的prototxt文件加入的层如下: layer { name: "detection_out" type: "DetectionOutput" bottom: "box_loc" bottom: "box_conf_flatten" bottom: "box_priorbox" top: "detection_out" include { phase: TEST } transform_param { mean_value: 103.94 mean_value: 116.78 mean_value: 123.68 } detection_output_param { num_classes: 2 share_location: true background_label_id: 0 nms_param { nms_threshold: 0.3 top_k: 200 } code_type: CENTER_SIZE keep_top_k: -1 confidence_threshold: 0.7 visualize: false visualize_threshold: 0.3 } }