Bin Li

I incorporated a simple weights initialization method which helps stabilize the training in the latest commit.

> > without it, the training can sometimes take a very long time to even start to converge on the Camleyon16 dataset. It is trained with a few interactions on...

> Hi @binli123, could you please let me know which things I should initialize using various initialization methods in PyTorch? Additionally, do you have an example? I'm currently working on...

The new initialization method seems more stable and there is no need for "init.pth"

The training speed has now improved significantly with the latest commit. I also incorporated the training/testing into the same pipeline in the latest commit. This change allows you to read...

I incorporated the training/testing into the same pipeline in the latest commit. You can set --eval_scheme=5-fold-cv-standalone-test which will perform a train/valid/test like this: >A standalone test set consisting of 20%...

@Vison307 I incorporated the training/testing into the same pipeline in the latest commit. I also incorporated an orthogonal weights initialization which helps making the training more table. You can set...

Based on the loss curve of SimCLR. I think you should let the model further converge. Make sure you have loaded the model weights correctly, and that the type of...

> > 您好，感谢您的出色工作！之前我尝试重现 Camelyon16 的结果，我总共使用了 271 个训练集，批量大小为 512 来训练 simclr 3 天并训练聚合器，但结果不如您提供的 simclr 权重 3 天训练（谷歌云端硬盘中的 model-v0）。像#46，聚合器的准确性将停留在60%左右，无法提高，我发现在这种情况下，每个补丁都会产生相同的注意力分数。能否提供相关的训练参数，比如deepzoom_tiler.py中的 -o 或 -t 参数，以及学习率、批量大小、纪元等。的西姆勒。 > > Hello, I would like to ask why...

I incorporated the training/testing into the same pipeline in the latest commit. This change allows you to read the evaluation results on a reserved test set. I also incorporated a...