-
Thanks for doing this work, it was useful for me.
1. When I use Dlib model I face this error:
SystemError: new style getargs format but argument is not a tuple.
2. When I use DeepID model I …
-
Looked to lots of photo organizers and saw that none of them are perfect for combining AI tagging, location tagging and face detection. I'd like to search my photos by context, by location and by pers…
-
Hello, first of all. congrats on this great tool.
I found that installing from pypi and importing `DeepFace` gives you the following error:
```
ModuleNotFoundError: No module named 'dlib'
```
Dli…
-
Hi serengil, I am using latest python version running on window 10. And my laptop got 32 GB RAM and CPU is i7 (2.11GHz). It took 15 seconds to verify one pair of photos. I use the photos from your sam…
-
### Proposal
Allow paths in ids e.g. `project1/-abcdef` so that deep data structures can be supported. Deep structures are often used in Firebase apps and are particularly useful when locking things…
-
- I'm training a DeepID model.
- Datum are `/home/yuanshuai/sdcard/download/caltech-256/caltech-256-60-train.rec` and `/home/yuanshuai/sdcard/download/caltech-256/caltech-256-60-val.rec` from `http:…
-
http://www.weibo.com/1507467291/Bk2l29vEy
-
## Environment info
Jetson TX1, 4G RAM, Ubuntu16.04 64bit, MXNet 0.94
1. RAM is enough. I excluded the cause of the memory firstly. I made rec format data less 1MB using `im2rec.py`. However, it s…
-
Recently I'm making a serires benchmark of inference(not trainning) using MXNet. I found caffe DeepID model, but there's some problem when converting to MXNet model.
Besides, I found a MXNet DeepI…
-
Hello, I have a quetion didn't understand, is the final layer for face verification and identification is same,?which means the embedding size for contrastive is class nums of identity.