Closed xylcbd closed 1 year ago
Yes we provide some tensorboard log like in https://github.com/keyu-tian/SparK/tree/main/downstream_d2#fine-tuned-resnet-50-weights-log-files-and-performance.
I couldn't find the experiment log of non-pretrained finetuning, but I found a MoCo V2 log. Here's an AP curve of ResNet-50-SparK (blue) vs. ResNet-50-MoCoV2 (orange). It's a COCO MaskRCNN FPN 1x finetuning configuration.
I think MoCo V2 should converge faster than non-pretrained, so the advantage of SparK is evident.
Is there any loss curve for that? thanks