加载中…
加载中…
checkpoint-1209/optimizer.pt 687 MBcheckpoint-2148/optimizer.pt 687 MBcheckpoint-2148/pytorch_model.bin 343 MBpytorch_model.bin 343 MBcheckpoint-1209/model.safetensors 343 MBmodel.safetensors 343 MBcheckpoint-1209/rng_state.pth 14.6 kBcheckpoint-2148/rng_state.pth 14.6 kBcheckpoint-1209/training_args.bin 4.4 kBtraining_args.bin 4.4 kBcheckpoint-2148/training_args.bin 4 kBcheckpoint-1209/scheduler.pt 0.6 kBcheckpoint-2148/scheduler.pt 0.6 kBReturns whether there is an open or a closed eye given an image from surrounding area with about 99% accuracy.
See https://www.kaggle.com/code/dima806/closed-eye-image-detection-vit for more details.
Classification report:
precision recall f1-score support
closeEye 0.9921 0.9888 0.9904 4296
openEye 0.9889 0.9921 0.9905 4295
accuracy 0.9905 8591
macro avg 0.9905 0.9905 0.9905 8591
weighted avg 0.9905 0.9905 0.9905 8591