liruixinxinxin

  what is the wrong with my code...

Analysis of the Discrepancy Between Precision/Recall from Confusion Matrix and mAP During Training

1

Hello everyone, I am using MMDetection for training, and after training the model, I use the test phase to generate a .pkl file. Then, I added code in confusion_matrix.py to...

Hi Team, I want to know the value of lowest value of learning rate in Pretrain and Distill , But the paper just supply the peak value of learning rate,...

Clarification Regarding "All Patch Representations" in the Pre-training Diagram

1

I hope this email finds you well. I am currently working on understanding your work regarding the pre-training procedure for masked audio prediction, and I have encountered a question related...

Some Question of Pre-training

1

Pre-training Loss Convergence Value: In the Masked Audio Modeling (MAM) task, the model uses cross-entropy loss to optimize the prediction of discrete labels. Could you please share the approximate loss...