class-balanced-loss

class-balanced-loss copied to clipboard

focal loss modulator

8

how to infer the modulator the code in your repo ``` modulator = tf.exp(-gamma * labels * logits - gamma * tf.log1p( tf.exp(-1.0 * logits))) ``` for focal loss in...

bei-startdt

@richardaecn @KMnP thanks for open-sourcing the code , is it possible to use Cb loss in the object detection or segmentation architecture ?? did you experiment it with any std...

abhigoku10

My implementation in Pytorch doesn't work

4

Dear authors, thanks for your greate effort to make your code open-source. I re-implement you **CB-focal Loss** in Pytorch(Both in your tf-version and my own version), but can't reach the...

hbsz123

inference using the models

1

Respected Authors, Firstly, thank you for releasing the code. Is code available for inference from given pre-trained models? It would be really helpful if you could provide the same along...

Anurag14

How I set weights? If image1 (have class 1 and 2 and class3), the weight is (class1_num + class2_num + class3_num)?

Bonsen

In each batch, I firstly compute one independent E_{n} for that batch, but it doesn't work at all; but according to your code, E_{n} is global, there exists only one...

Yuranus

weights = weights / np.sum(weights) * int(hparams['data_version'])

1

the weights normalize function is not in the paper, why in the code need normalized ? and why to multiply the number of classes? ths .

nikenj

I found you might be the organizer of the [COCO Detection Challenge](https://competitions.codalab.org/competitions/20794). The codalab has closed the old website and your competition can‘t submit. Can you transfer the competition to the new...

alpc111