There seems to be something strange when the data is loading
MellowMemories opened this issue · comments
Look at this official configuration written by USB, which means that for every training epoch, it will perform 1024 iterations, and each iteration will use 8 labeled images. Therefore, we can conclude that for each epoch, we would need 1024 * 8 = 8192 labeled images .
However, in this configuration, we only have 400 labeled images . I don’t understand this. How can it work? Is it reasonable?
By the way, I am a complete novice in deep learning and semi-supervised learning.
Thanks a lot!
Distributedsampler will replicate the data to fulfill training iterations in one epoch
In semi-supervised learning, figuring out what counts as an "epoch" is tricky. Classical semi-supervised methods, as implemented in this USB package, use batches that contain both labeled and unlabeled examples in a particular ratio (often called
PS : I may be wrong, but I believe that the definition of one epoch being everywhere 1024 steps in USB might originate from this FixMatch original choice on Cifar-100
Thank you very much for clarifying my doubts.
I now have a clear understanding of the code organization and program execution flow in this repository, and I have read through all the recent papers on semi-supervised learning. I have gained a preliminary understanding of the methods used in the field of semi-supervised learning: supervised loss + auxiliary loss + pseudo-labeling loss. Building upon this foundation, the 'USB' code has done an excellent job abstracting the workflow for semi-supervised learning. You and your team have done great work.
Regarding data loading, with my own practice and your guidance, I believe I have grasped it quite well. Currently, I have divided my dataset into training set, validation set, and test set in a ratio of 7:1:2. In the training set, 20% of the data is labeled while 80% is unlabeled. Since in the 'train_step' function of the program, data is loaded based on labeled data as a reference point, all I need to do is divide the size of my labeled data by 'train_batch_size' to obtain 'num_train_iters'. This ensures that each labeled data will be used once within one epoch only. Based on this method of data loading, I am also pursuing my own work.
Once again, thank you for your explanations!
Thank you very much for clarifying my doubts.
I now have a clear understanding of the code organization and program execution flow in this repository, and I have read through all the recent papers on semi-supervised learning. I have gained a preliminary understanding of the methods used in the field of semi-supervised learning: supervised loss + auxiliary loss + pseudo-labeling loss. Building upon this foundation, the 'USB' code has done an excellent job abstracting the workflow for semi-supervised learning. You and your team have done great work.
Regarding data loading, with my own practice and your guidance, I believe I have grasped it quite well. Currently, I have divided my dataset into training set, validation set, and test set in a ratio of 7:1:2. In the training set, 20% of the data is labeled while 80% is unlabeled. Since in the 'train_step' function of the program, data is loaded based on labeled data as a reference point, all I need to do is divide the size of my labeled data by 'train_batch_size' to obtain 'num_train_iters'. This ensures that each labeled data will be used once within one epoch only. Based on this method of data loading, I am also pursuing my own work.
Once again, thank you for your explanations!
Thank you for opening this issue, it has enlightened me. As someone new to the field, I'm currently facing difficulty understanding the execution flow within this repository, particularly regarding how the label ratio is utilized in training the SSL algorithms && deciding how to choose the num_labels parameter. Is there any intuition behind this?.
It would be immensely helpful if you could provide a screenshot of the configuration used in the example you mentioned in your comment.
Additionally, I'm curious about your preferred method for running the code. Did you rely on the notebooks such as Beginner_Example.ipynb or Custom_Dataset.ipynb found in the notebooks folder, or is there a better approach?
Any guidance you can offer would be greatly appreciated. Thanks a lot.
Stale issue message