Humayun Irshad

Dear, insightface used multiple dataset like faces_emore or MS1M_Celab etc to training and validation accuracy. Can you explicitly mentioned that which dataset you tried and what are final loss and...

Error: ReTraining on Different TrainingSet - size of output embedding mismatch

2

Dear TreB1eN, Thank you for sharing the code. I am trying to retrain (fine tune) previously trained model on different training set. Number of classes (identities) is different in new...

Low Quality Faces (blurry) after detecting and warpalign faces using Facexlib

1

0 I am using Facexlib library to detect, crop (warpalign) and resize (512x512) the faces from photographic images (high resolutions 4K or above). In some cases, the output images are...

Low Quality Faces (blurry) after detecting and cv2.warpalign faces using Facexlib

2

I am using Facexlib library to detect, crop (warpalign) and resize (512x512) the faces from photographic images (high resolutions 4K or above). In some cases, the output images are low...

Error when exporting GFPGANv1 model pth to onnx, got error IndexError: Argument passed to at() was not in the map.

1

I am trying to convert GFPGANv1 model from pth to onnx format, but I got error. here is code: for conversion: ``` import cv2 from basicsr.utils import img2tensor from torchvision.transforms.functional...