Lzhushuai

I also met the same issues. I find it is because **RepBox_losses** is an empty List sometimes. I'm not sure what causes this situation. But I solve it by this...

他的代码写的是1000个step保存一下，你的数据集显然太小，没有跑到1000个step。把他的save_model参数改小一点就好了

` # Save the model checkpoints if (i+1) % args.save_step == 0: torch.save(decoder.state_dict(), os.path.join( args.model_path, 'decoder-{}-{}.ckpt'.format(epoch+1, i+1))) torch.save(encoder.state_dict(), os.path.join( args.model_path, 'encoder-{}-{}.ckpt'.format(epoch+1, i+1)))` ... `total_step = len(data_loader) for epoch in range(args.num_epochs):...