HouBiaoLiu
HouBiaoLiu
我在进行ocr_test测试时,使用第0块显卡;现在我想通过命令行参数传递使用哪块选卡,于是做了如下修改 bool Classifier::Init(const string& model_path, int gpu_id) { const string trained_file = model_path + "/model.caffemodel"; const string model_file = model_path + "/deploy.prototxt"; string mean_file = model_path + "/mean.binaryproto"; const string...
First:download cuhk-03.mat and the new training/testing protocol split cuhk03_new_protocol_config_detected.mat cuhk03_new_protocol_config_labeled.mat, place all in the directory '/data/person-reid/cuhk03/' Second: I use my own code to generate the bounding_box_train query bounding_box_test, and Is...
这个操作没有啊
我在进行ocr_test测试时,使用第0块显卡;现在我想通过命令行参数传递使用哪块选卡,于是做了如下修改 bool Classifier::Init(const string& model_path, int gpu_id) { const string trained_file = model_path + "/model.caffemodel"; const string model_file = model_path + "/deploy.prototxt"; string mean_file = model_path + "/mean.binaryproto"; const string...
执行export_prune_onnx.py 导出onnx时报错,在于attempt_load函数中fuse操作,去掉fuse操作可正常导出,这个fuse操作也将bn层的eps也fuse到卷积中了
 两者mAP不一致 正常吗
我稀疏训练用的多卡分布式训练的, 在运行脚本slim_prune_yolov5s对模型进行裁剪时,报错在utils/prune_utils.py中gather_bn_weights函数  是SyncBatchNorm