Pytorch_Retinaface icon indicating copy to clipboard operation
Pytorch_Retinaface copied to clipboard

Retinaface get 80.99% in widerface hard val using mobilenet0.25.

Results 116 Pytorch_Retinaface issues
Sort by recently updated
recently updated
newest added

Hi biu, When i run command line for training. I'm facing this issue: RuntimeError: CUDA out of memory. Tried to allocate 200.00 MiB (GPU 0; 3.94 GiB total capacity; 2.79...

Steps to reproduce : 1. Downloaded the annotations zip file from dropbox : https://www.dropbox.com/s/7j70r3eeepe4r2g/retinaface_gt_v1.1.zip?dl=0 2. Couldn't find val/wider_val.txt which is neccessary for running test_widerface.py

Hi, I am interested in retinaface. As mentioned in the paper, retinaface uses a mesh decoder with Graph Convolution. Where is this module in the project? Thank you

File "D:\gitspace\Pytorch_Retinaface\data\wider_face.py", line 42, in __getitem__ height, width, _ = img.shape AttributeError: 'NoneType' object has no attribute 'shape' why it goes wrong?

你好,我想尝试用这个框架检测其他物体,如人体,请问anchor的比例在哪里修改