ASL

ASL copied to clipboard

What is the best practice to increase the number of tags of an existing model without retraining the whole model again? Possible solutions like freezing layers or train a seperate...

stugito

A great work. You provide some pretrained models. I want to use these models. What are the means and variances of these datasets? Did you use the mean and variance...

ffgg11

Hi! First of all thank you for this interesting work! I'm trying to apply this loss function to my multi-label dataset and to choose a good set of hyper-parameters. I'm...

Jessegator

怎么样多卡训练，谢谢。也就是怎么样运行train.py进行多卡训练。我的训练主机是4xRTX4090的卡。谢谢。

cinding

Can this be used for multilabel dataset in classification

1

Hi Team, I would like to know if this loss function can be used in a multilabel classification or not. Thanks,

alumini

Add tf_losses.py file which initializes edited version of AsymmetricLoss.forward() function for use with tensorflow.

Mooster1

Hi - Thanks for this terrific paper and thank you for sharing the code! Just wanted to point out that the tests in `tests/test_asl.py` are not valid, and they all...

noa-codes

Thank you for your great work. ASL adopts 'clamp' to prevent 'inf' in the loss calculation. Actually, 'clamp' cannot back-propagate the gradients, because it is not derivable, i.e., ASL ignores...

Breeze-zyuhan

Training issue

1

Dataset | gamma neg | highest map (after 40 epcoh) -- | -- | -- f/m: 460/694 | 4 | 86.69 f/m: 460/694 | 3 | 87.94 f/m: 460/694 |...

snehashis1997