问题
During the process of making a lmdb file,we are supposed to make a train.txt and val.txt file,i have already made a train.txt file which consists of the image name space its corresponding label.Ex image1.JPG 0.
Now that i have to make the val.txt file im confused as to how do i give it its corresponding values since it is my test data and i am hoping to predict those.Can anyone tell me what thisval.txt file is and what is it supposed to be doing.
回答1:
You are confusing test and validation sets. A validation set is a set where you know the labels (like in training) but you do not train on it. The validation set is used to make sure you are not overfitting the training data.
At test time you may present your model with unlabeled data and make prediction for these samples.
来源：https://stackoverflow.com/questions/45446829/caffe-lmdb-train-and-val-txt