About
The models were fine-tuned using 4xA100 GPUs on the Doclaynet-base dataset, which consists of 6910 training images, 648 validation images, and 499 test images.
The models were fine-tuned using 4xA100 GPUs on the Doclaynet-base dataset, which consists of 6910 training images, 648 validation images, and 499 test images.