-
## 🚀 Feature
I would like to contribute to the pytorch (in python and c++) by adding the [ contrastive loss/siamese_margin_loss](http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf) f…
-
hello i utilize your useful program for face recognition,my implemented network is inception resnet v2 and
1. batch_size=16,
2.lr=0.001
3.embeding_size=128
4.train_size=708
5.eval_size=396
6.ma…
-
8th plase: DeepLabV3 with different encoders.
Group Normalization for small batch
Mask threshold (due to bad metric)
Weighted BCE loss for classification-segmentation models.
Ensemble of 3 top we…
-
I try to write a triplet loss in DARKNET。
-
Hi ,
Background -
I am trying to finetune the BGE-Large model - 'BAAI/bge-large-en-v1.5' on custom domain specific dataset.
I am using data in format - triplets - (anchor, postive sample, negat…
-
I want to implement triplet loss of FACENET in DARKNET for face comparison. How can I do that?
-
I always get an ResourceExhaustedError: OOM error whenever using this code. I'm unable to use any batch size greater than 256. Can you point out which parts are the most memory intensive?
```
R…
-
Thank you for your awesome work in the sentence embedding space !
I would like your help on couple of questions:
- Please point out the models which are fine-tuned using contrastive learning loss a…
-
#### Ajustar os seguintes parâmetros
- Regularização (L1, L2, Dropout, Clipping);
- Early Stopping;
- Taxa de aprendizagem (lr);
- Funções de ativação (testar a softsign no lugar da tanh);
- Ot…
-
Hi everyone,
When training using triplet loss i found this very confusing:
```python
for i in range(nrof_batches):
batch_size = min(nrof_examples-i*args.batch_size, args.batch_size)
…