martinenkoEduard
martinenkoEduard
What maximum FPS have you achieved?
How to train it with custom dataset? (folders as classes?_) FileNotFoundError: [Errno 2] No such file or directory: \faces_emore\\agedb_30\\meta\\sizes
Win 10 - RuntimeError: Distributed package doesn't have NCCL built in. Has anyone encountered this error?
Has anyone trained adaface on WebFace260M?
How do I convert AdaFace to onnx format? Will it have increased performance?
What is the computational cost of AdaFace in GFLOPs?
I am trying to teach webface42m but it says "out of memory" I am using Nvidia Geforce RTX 3080 TI with 12gb of RAM. When I lower custom_num_class it works...
\AdaFace with the following property self.m 0.4 self.h 0.333 self.s 64.0 self.t_alpha 0.01 Global seed set to 42 /home/administrator/anaconda3/envs/py388/lib/python3.8/site-packages/pytorch_lightning/trainer/connectors/accelerator_connector.py:441: LightningDeprecationWarning: Setting `Trainer(gpus=1)` is deprecated in v1.7 and will be removed...
Is it worth to user --use_16bit flag? Doesn't hurt model's perfomace?
What does --numworkers do?