TricubeNet

TricubeNet copied to clipboard

Hello, can you provide a pre training model

5

aso538

Thank you for your excellent work, but I noticed that in the paper, it mentions four datasets: DOTA, SKU110K-R, MSRA-TD500, and ICDAR2015. However, the code only supports DOTA and HRSC2016...

no5-hao

could you share me a file structure for a dataset ! thanks

no5-hao

Saving weight

2

` best_loss = 999999999 best_dist = 999999999 start = time.time() for epoch in range(0, args.epochs): if distributed: train_sampler.set_epoch(epoch) # train for one epoch train(train_loader, model, criterion, optimizer, scheduler, device, start,...

18219716332