DeepCore
DeepCore copied to clipboard
PatrickZH
Code for coreset selection methods
Hi, Chengcheng Guo and Bo Zhao: Thanks for your thorough research and clean codes. However, I have some questions about uncertainty based implementation. As mentioned in the DeepCore paper, samples...
Hi, Thank you very much for providing a comprehensive data pruning library! I would like to introduce a new data pruning library, which is an extension of DeepCore for **Re-labeling...
Dear Authors, Thank you very much for your work and providing the code. I just wanted to ask whether the numbers reported, i.e the test accuracy numbers are the best...
Hi, thanks for sharing this codebase! I notice that there might be a small mistake in the implementation of Glister, in line 131 of the file **deepcore/methods/glister.py**, `flatten(), upadate_state=self.update_val_gradients` I...
Hello, Thanks for the great work. As asked before ([here](https://github.com/PatrickZH/DeepCore/issues/4#issuecomment-1441100968)) I do not see why in several methods like GraNd and submodular functions, you use the concatenation of loss gradient...
Is it possible to provide detailed setup to reproduce Table 1 in the paper. I have tried multiple combinations of parameters, but the coreset results are not comparable to random...
First of all, thank you so much for providing such a good github repository. I ran the code myself, and the code is very reproducible and helpful to concatenate my...
Hi. Thank you for the great work. I wanted to ask, is there a way where I can use adaptive gradmatch in the codebase? If not, can you guide me...
Hi, Thank you for providing such a powerful tool for data-efficient training! I’ve been working on a medical imaging project focused on liver lesion segmentation in patients with colorectal cancer....
I notice that choose balance==True have a great improvement in model performance than balance==False, but is the model discussed in the method list use this technique in their original code?
