-
Hey!
Any objections adding Hierarchical Triplet Loss (HTL), described [here](https://arxiv.org/pdf/1810.06951)? Happy to work on a Pull Request.
-
Hi, when i use FaceNet train CASIA-Webface, i first use Softmax Loss, and after 90 epoch, the model gets 98% accuracy and 95% validation rate.
Then, i want to use Triplet Loss to finetune the model, …
-
My understanding of the current classifier and task with 60X res data can be found here: https://docs.google.com/document/d/1j3UePmDJL_1V_9j7v3I4nLgAgKuFXXuqmlW8ZFOyTk0/edit?usp=sharing.
Given this…
-
Hi Kevin
Would you mind add my Selectively Contrastive Triplet loss (which is published in ECCV2020)? The major idea of this paper is to overcome the local minima during the triplet optimization. T…
-
What is the advantage of SNTG loss over triplet loss?
What is their difference?
@xinmei9322
-
i tried to use the finetuning notebook, i trained the resnet model using softmax cross entropy for the first trial and with a triplet loss for the second both gived false embeddings. i changed the fac…
-
Hi,
In `TripletMarginLoss` you have default margin set to **0.05**:
```
class TripletMarginLoss(BaseMetricLossFunction):
"""
Args:
margin: The desired difference between the …
-
Hi , I trained sbert with triplet loss with default distance_metric --> Euclidian distance got descent embeddings and cosine score between relevant/irrelevant sentences. But when i tried with TripletD…
-
Is there an implementation available of the triplet loss layer in the [FaceNet paper](http://arxiv.org/abs/1503.03832)?
Thanks for your work on making this a great toolbox!
-
loss:
name: 'triplet'
softmax:
label_smooth: True
train:
optim: 'amsgrad'
lr: 0.0015
max_epoch: 250
batch_size: 64
fixbase_epoch: 0
open_layers: ['classifier']
lr_sc…