mixfacenets
mixfacenets copied to clipboard
fdbtrs
Official repository for MixFaceNets: Extremely Efficient Face Recognition Networks
Hello, First of all, thank you for sharing your code. I ran into a few problems when trying to run your eval.py code, it would seem like the value of...
Running `eval.py` with `147836backbone.pth`, as hardcoded in the `eval.py` script, for any of the six models (MixFaceNet-M, ShuffleMixFaceNet-M, MixFaceNet-S, ShuffleMixFaceNet-S, MixFaceNet-XS, ShuffleMixFaceNet-XS) throws the following exception: ``` Exception has occurred:...
I am having this issue, could anyone come up with a fix? **Traceback (most recent call last):** _File ".\mixfacenets-main\train.py", line 22, in from utils.utils_amp import MaxClipGradScaler File ".\mixfacenets-main\utils\utils_amp.py", line 4,...
Hi, Thanks a lot for your work. I tried to run the evaluation script of (in pocketnets github repo) for both pocketnets and mixfacenets. All models were evaluated as expected...
As you did in your code(`function load_bin()`), assuming `image_size == (112, 112)`, `data_list[flip][idx][:] = torch.from_numpy(img.asnumpy())` indicates that width and height of the origin image must be equal, right? So, how...
