-
Where can I get or generate the validation list required for the training? I'm trying to train the network on MS-Celeb-1M.
Also, is the pretrained model trained on the Full Image Thumbnails, FaceCrop…
-
Could you share your method to demonstrate the visualization of deep features?
It's very interesting. Thanks.
-
Using `facenet/src/freeze_graph.py`, I was able to create the frozen graph by these training command:
> $ python src/train_softmax.py
--logs_base_dir ~/logs/mbnet/
--models_base_dir ~/model…
-
### Context of the issue.
I install the torch and openface.
And I download the model celeb-classifier.nn4.small2.v1.pkl from http://openface-models.storage.cmusatyalab.org/celeb-classifier.nn4.small…
-
I tried to use your resface.py as inference network while using Facenet as trainning logic.
But I am not sure how to use function AM_logits_compute, neither using it to replace prelogits_center_loss…
-
(sry bad english)
I tried to train model with various detailed faces of one celeb ~650 photos which I got from search engines.
Aligned SFW: [AlexandraDaddario.zip](https://github.com/deepfakes/fac…
-
I tried to use the seed finder with the keywords: political news
Then DDT said:
Query failed. Try Bing.
But under the SeedFinder, there is no option to switch the search engine.
I went back to…
-
When trying to run openface - http://cmusatyalab.github.io/openface/demo-3-classifier/
I am seeing below issue.
psakhamo@ironmaiden:~/torch/openface$ ./batch-represent/main.lua -outDir data/mydataset…
-
I was wondering if the far_target is chosen in a random way or someway else. I am currently running FaceNet with my own face dataset, but I got a bad validation rate (14%) when I use 1e-3 as the far_t…
-
I recently tried the classifier.py demo and it's working very well, now i wanted to test the classifier with the webcam feed and maybe later on i'am planning to test with an RTSP feed coming from a vi…