Bryan Wong

Couldn't find coreset implementation

1

Hi, I couldn't find the coreset implementation in your code. How can I find it? Thanks!

Hi, I am trying to load ResNet50 pretrained on ImageNet with Barlow Twins as provided [here](https://mmselfsup.readthedocs.io/en/latest/papers/barlowtwins.html). However, I failed to load ResNet50 models (using the `timm` package) with the following...

TCGA Dataset Training and Testing Distributions

1

Hi, could you please share with me the distribution of slides used for training and testing in the TCGA dataset, along with their respective labels? I noticed that it's mentioned...

Dear Sir, How can I set the values for those variables if my total data is 270 and my labeled data is only 20 with a batch size of 4?...

Some Questions

12

Hello, I would appreciate it if you could respond to some of my questions below: 1. Could you clarify why SelfPatch loss is only evaluated when v == iq (student...

Thanks for the great implementation! When it is trained with 40 labels only, why is the batch size still 64?

Hi, thank you for the great paper! Is there a specific way to set the following hyperparameters? As I plan to implement FeatMatch to other datasets ``` "pk": 20, "l_ratio":...

Self.args in alpha_mix_sampling.py

1

Hi, could you let me know how I can find the value of self.args? I couldn't find similar names in the rest of the files. For example, if you mention...

Dear Sir or Madam, I tried to run your VGG16 training model. However, there is an error when I fit the model. It said that Incompatible shapes: [64,6,4] vs. [64,28]....

Cambridgeltl Access Token

1

Hi, I was wondering how to get Cambridgeltl Access token, so that I can create and run the dashboard for the demo. Thanks!