facenet-pytorch icon indicating copy to clipboard operation
facenet-pytorch copied to clipboard

Pretrained Pytorch face detection (MTCNN) and facial recognition (InceptionResnet) models

Results 80 facenet-pytorch issues
Sort by recently updated
recently updated
newest added

Why do some pictures return none when I call mtcnn?

Numpy is throwing deprecation warnings for creating arrays from nested sequences on line 183 of detect_face.py and on lines 339, 340, 341 of mtcnn.py when running the example training script....

Its working well on windows 10 using anaconda i am doing everything right. But when i started deployment of my app on ubuntu server using Flask from facenet_pytorch import MTCNN,...

I tried standard embeddings but the model is not discerning between brothers well. So I decided to try finetuning casia-webface/vggface2 and classifying with 4 classes and 1000 images each. I...

is there a way to use resnet-inception pretrained on vggface2 as a backbone for pytorch faster rcnn. This means that I only want the feature map of the model so...

### Problem We have our input images as a batched tensor `reals` of shape [B, C, H, W]. We feed this into mtcnn after permuting to change shape into [B,...

When packaging my module using PyInstaller where I have `import facenet_pytorch` This user warning comes out and I think it is leading torch problems down the line: > torchvision\__init__.py:26: UserWarning:...

https://github.com/timesler/facenet-pytorch/blob/555aa4bec20ca3e7c2ead14e7e39d5bbce203e4b/models/utils/training.py#L134 Is there need add `writer.iteration += 1` and modifiy the `writer.add_scalars(metric_name, {mode: metric_batch}, writer.iteration)` as the orginal code is not pass in `writer.iteration`? Beacause I find that the tensorboard...

Hello, In order to get less false positive face detection I tried switching MTCNN with RetinaFace using [this](https://github.com/biubug6/Pytorch_Retinaface) open source implementation. After extracting all faces from a given image I...