DSFD-Pytorch-Inference
DSFD-Pytorch-Inference copied to clipboard
hukkelas
A High-Performance Pytorch Implementation of face detection models, including RetinaFace and DSFD
- Added model_weights param. - Fixed problem when you want to use cpu to infer. - Fixed problem with torch and setup. - Fixed imports. - Update test. - Update...
file mentioned [here](https://github.com/hukkelas/DSFD-Pytorch-Inference/blob/dde9c7dd9cdc9254c2ca345222c86a8ecfa17f5b/face_detection/retinaface/onnx.py#L22) is gone
img shape (1800, 2880, 3) n_anchors += x[0] * x[1] * len(min_sizes[0]) Traceback (most recent call last): File "test.py", line 29, in face_detect boxes = detector.detect(img) File "/lib/python3.8/site-packages/face_detection/base.py", line 56,...
Dear Håkon, first of all i want to thank you for providing this very useful and easy to use python module. Next, i have a small suggestion how to improve...
When I run build_detector, the pytorch .pth models were automatically saved in a default directory. How can I save in another directory, and then load model from that directory during...
Hi, during the inference of each model, the memory continuously increases with each image (only for single image inference). I have tried this on CPU as well as on GPU....
- The URL used for **DSFDDetector** is - [https://folk.ntnu.no/haakohu/WIDERFace_DSFD_RES152.pth](https://folk.ntnu.no/haakohu/WIDERFace_DSFD_RES152.pth) - The URL used for **RetinaNetResNet50** is - [https://folk.ntnu.no/haakohu/RetinaFace_ResNet50.pth](https://folk.ntnu.no/haakohu/RetinaFace_ResNet50.pth) - The URL used for **RetinaNetMobileNetV1** is - [https://folk.ntnu.no/haakohu/RetinaFace_mobilenet025.pth](https://folk.ntnu.no/haakohu/RetinaFace_mobilenet025.pth) But all the...
The [link](https://github.com/hukkelas/DSFD-Pytorch-Inference/blob/master/face_detection/dsfd/detect.py#L11) to the face_detector model is broken. Ideally this should be updated, in the meantime I'd like to share my [monkey-patch](https://github.com/hukkelas/DSFD-Pytorch-Inference/blob/master/face_detection/dsfd/detect.py), where the referenced model can be downloaded at...
