[feature] add redimnet

[wsstriving]

Add ReDimNet as mentioned in #341

[wsstriving]

I have actually validated the performance of B2 and B3, the performance are acceptable, but it's hard to validate other bigger models due to the resource limitation ...

[czl66]

Hi, I was running redimnetb2 with 8x4090 on cnceleb, using your model and config (0602516), but my results seem not so good, the results are:

The final acc and final loss are comparable,

and the difference of two exp's config is listed as below:

Is this reasonable? Thanks for your reply。

[wsstriving]

Unfortunately, I am currently too busy to tune the experiments. I will present the results I have so far below. I believe we can first merge the implementations, as the performance is acceptable given the model's size. I would greatly appreciate any assistance from someone with sufficient resources to help with this implementation.

Main Problems:

The default SphereFace2 loss does not work well for me (it yields worse results than the arc_margin-based approaches).
While large margin fine-tuning is beneficial, its impact is limited.

Redimnet v0 arc_margin	No score norm		AS-Norm
	EER	minDCF	EER	minDCF
vox1_O	1.244	1.181	1.128	0.109
vox1_E	1.248	2.008	1.181	0.125
vox1_H	2.172	0.210	2.008	0.186

---

Redimnet v2 arc_margin	No score norm		AS-Norm
	EER	minDCF	EER	minDCF
vox1_O	0.712	0.059	0.718	0.072
vox1_E	0.894	0.095	0.869	0.094
vox1_H	1.621	0.161	1.545	0.149

---

Redimnet v3 arc_margin	No score norm		AS-Norm
	EER	minDCF	EER	minDCF
vox1_O	0.574	0.045	0.537	0.045
vox1_E	0.822	0.095	0.790	0.089
vox1_H	1.576	0.157	1.433	0.140

[Hunterhuan]

add redimnet model

[Hunterhuan]

add redimnet model

[didi1233]

@wsstriving Hello! Recently, I have been working on reproducing the models from your code and the updated code from the subsequent work of the paper's authors. If the training goes smoothly, I will provide the necessary assistance. My question is: are the results from your code before or after LMF?