martlgap / octuplet-loss

Repo for our Paper: Octuplet Loss: Make Your Face Recognition Model Robust to Image Resolution

Hi there 👋 it's Martin,

I am research associate at the Institute of Human-Machine Communication, Technical University of Munich, with the aim of obtaining a doctorate (PhD).

Working on tasks related to cross-resolution face verification.

---

🛠 Technologies & Tools

---

📈 Stats

---

🧑🏼‍💻 Languages

---

✉️ Contact

octuplet-loss's Issues

implementation with pytorch

Dear @Martlgap ,
first of all thank you for this magnificent work you have done. I wanted to ask you the steps I should take to achieve this face recognition with pytorch. I saw that in the github he released a python file that uses pytorch, I think it is the neural network. To implement everything and make it work what steps should I do starting from the 'pt_octuplet_loss.py' file.
Sorry for disturbing.
Thank you in advance for your reply.

training dataset

hi Martlgap,

Your work was amazing. Are you willing to provide the dataset file ("/mnt/ssd2/test_embs.pkl") ? Meanwhile, the file seems contains both basic training data and downsimpled data, am I correct?

Thx

Resolution of low resolution pictures And Batches

Dear @Martlgap ,
first of all thank you for this magnificent work you have done. I wanted to ask you two questions.
1.How many batches are there in one epoch。(I don't know how you generate minibatch. But I randomly selected different identity pictures as a minibatch, so I need to know this.)
2.Whether the resolution of low resolution pictures in one batch is random, or the resolution of low resolution pictures in one batch is the same, but different batches are different ?
Thank you in advance for your reply.

No such file or directory: '/mnt/ssd2/test_embs.pkl'

where is "/mnt/ssd2/test_embs.pkl"?

can you upload this file?

About data preprocessing for pretraining process

Thanks for your work
But I'm still puzzled about the data preprocessing for the pretrained face model. Apart from the finetuning process, is the data downsampling used to pretrain the face model?

Is there a finetuned checkpoint available?

Hello! Thank you for your work. Could you please provide the finetuned weights?

Generating embedding database

Hello, are you able to share code to generate embeddings database from our own dataset? So that we can use for inference?

Thanks!