Hi! Thank you for the great work.
I’m fine-tuning this model, and using the checkpoint trained with focal seems to lower performance on COCO and RefCOCOg. Could the batch size be influencing this as well?
I am training on 4 GPUs, the setting is "TRAIN.BATCH_SIZE_TOTAL 20 \ TRAIN.BATCH_SIZE_PER_GPU 5 \ DATALOADER_NUM_WORKERS 4" ,and results on RefCOCOg (~62-63% cIoU),COCO(~38.1% mAP, ~60.7% mIoU).
Would increasing the epoch parameter, reducing the LR_MULTIPLIER for the backbone (to 0.05), or lowering WARMUP_ITERS（to 5） be helpful?
Hi! Thank you for the great work.
I’m fine-tuning this model, and using the checkpoint trained with focal seems to lower performance on COCO and RefCOCOg. Could the batch size be influencing this as well?
I am training on 4 GPUs, the setting is "TRAIN.BATCH_SIZE_TOTAL 20 \ TRAIN.BATCH_SIZE_PER_GPU 5 \ DATALOADER_NUM_WORKERS 4" ,and results on RefCOCOg (~62-63% cIoU),COCO(~38.1% mAP, ~60.7% mIoU).
Would increasing the epoch parameter, reducing the LR_MULTIPLIER for the backbone (to 0.05), or lowering WARMUP_ITERS（to 5） be helpful?