AlibabaResearch / efficientteacher

A Supervised and Semi-Supervised Object Detection Library for YOLO Series
GNU General Public License v3.0
823 stars 149 forks source link

私人数据集上的数据集在半监督中的划分 #131

Open Huyayi123 opened 8 months ago

Huyayi123 commented 8 months ago

你好,请问直接在进行半监督训练时,用自己的数据集的 train这个参数中训练集是用全部有标签的数据集,还是设置一定比例的有标签的数据集,比如10%。target这里是从有标签数据集中直接选出来的可以吗。target也是选取一定比例的整体数据集吗? Dataset: data_name: 'coco' train: data/custom_train.txt # 118287 images val: data/custom_val.txt # 5000 images test: data/custom_val.txt # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794^ target: data/custom_unlabeled.txt nc: 2 # number of classes np: 0 #number of keypoints names: [ 'rick', 'morty'] img_size: 640 batch_size: 128

zdundjkl commented 8 months ago

train是全部带标签的,target是全部不带标签的,训练之前自己得划分清楚。dataloader读数据是根据你的txt索引文档路径读的,你要是把target的图像数据设置为train.txt也是可以正常运行的,就默认这里不用对应的train标签了。