Hi! First of all, thank you for making the training and evalution code open-source. I am currently training LightGlue with the superpoint+lightglue_homography.yaml config using a batch size of 128 on a single Nvidia Tesla A100 GPU with 40 GB VRAM. I use python/3.8.5, cuda/11.8.0, cudnn/8.4.0.27, and torch/2.1.2.
However, I have observed that the total validation/training loss does not decrease below 0.8 during homography pretraining. This result is different compared to Figure 5 in the paper where the loss goes below 0.2. I am seeking insights or suggestions on why this discrepancy might be occurring. Are there any specific considerations or adjustments to the configuration that I might be overlooking?
Hi! First of all, thank you for making the training and evalution code open-source. I am currently training LightGlue with the
superpoint+lightglue_homography.yamlconfig using a batch size of 128 on a single Nvidia Tesla A100 GPU with 40 GB VRAM. I usepython/3.8.5,cuda/11.8.0,cudnn/8.4.0.27, andtorch/2.1.2.However, I have observed that the total validation/training loss does not decrease below 0.8 during homography pretraining. This result is different compared to Figure 5 in the paper where the loss goes below 0.2. I am seeking insights or suggestions on why this discrepancy might be occurring. Are there any specific considerations or adjustments to the configuration that I might be overlooking?