You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
There are 3 models for each kind of pretrained models, for example, ucf101-img-vgg16-split1.mat, ucf101-img-vgg16-split2.mat and ucf101-img-vgg16-split3.mat. I find that you set nSplit=1 in the cnn_ucf101_fusion.m. What do the other two models mean and what are the differences among these three model? Thank you for your help.
The text was updated successfully, but these errors were encountered:
Hi,
The splits correspond to the ones defined by the authors of the UCF 101 dataset. Basically the dataset is split into train and test data three times. The dataset is not so big and this is just a manner to try to see how the models trained on it generalize to various types of the data. You should find out more about it on the UCF 101 web page http://crcv.ucf.edu/data/UCF101.php
@abursuc I have one quick question please. As I have read in a number of literatures, the datasets are usually split in 3.
Training set
Validation set and
Test set.
In the case of the train-test split of UCF101, do we split the Training set into two (Train set and Validation set)? I will be glad if you could give me some guidance on this please.
There are 3 models for each kind of pretrained models, for example, ucf101-img-vgg16-split1.mat, ucf101-img-vgg16-split2.mat and ucf101-img-vgg16-split3.mat. I find that you set nSplit=1 in the cnn_ucf101_fusion.m. What do the other two models mean and what are the differences among these three model? Thank you for your help.
The text was updated successfully, but these errors were encountered: