-
Hi! Hope you are doing well, I enjoyed reading this paper and the code. I was trying to adapt this method to my own task on a custom dataset. Something strange i noticed for my task was:
Even with …
-
You mentioned ''we use an instance discrimination task as a pretext task" in your paper. I'm really confuse which task should be used. As I understand, you feed text images to encoder and train MOCO w…
-
# Figure out best way to refactor models
The current setup makes it hard to implement new and upcoming models. Additionally, there is a lot of code which is repeated between the different implement…
-
BPO | [6992](https://bugs.python.org/issue6992)
--- | :---
Nosy | @malemburg, @pitrou, @tarekziade
*Note: these values reflect the state of the issue at the time it was migrated and might not reflect…
-
Thank you for sharing this great work.
I have a question about the initizalition of Memory_Bank in your code.
https://github.com/maple-research-lab/AdCo/blob/68b27a8c8e464f4b2a6c7c80c036301f46a4aef…
-
Hi, this is good application. how to do downstream task using label dataset for image classification after we trained the pretext model ? thank you
-
Thank you very much for your inspiring work. However, I encountered a problem when reproducing the performance. I followed your code to do the self-supervised learning. I got about 60-70% accuracy in …
-
Hi,
I am wondering how you got the result for ImageNet in Fig.2? Specifically, how many samples and what kind of representations did you use to get such statistics?
Also, I realized that as MOCO…
-
Whenever one launches `avrdude`, it seems like the full absolute path to the `avrdude.conf` file must be given with the `-C` argument. I tried with a relative path (relative to the `avrdude` executabl…
-
Hi Ed,
Each time I open the latest version I am experiencing same error as before. This was fixed in a macosx build of 0.2.5-dev-rel2 you shared. Can you fix this in the full release or should I co…