xings-sdnu

> > 13章的生成对抗网络无法从百度网盘上下载，请问老师或者好心人帮忙给我一份，谢谢 > > 应该是这个：https://pan.baidu.com/s/1Yn53uxFLCbja13_6Ay44MA 谢谢大佬！！

pred = np.squeeze(torch.sigmoid(pred)).cpu().data.numpy() filename = os.path.join(r'D:\MyworkSpace\depth\BS-Net-main\output_1', str(i) + '.png') cv2.imwrite(filename, pred) 这样就可以输出深度图了

把--use_aux改为False就可以了：`parser.add_argument('--use_aux', default='False', type=str2bool)`

chane the use_aux to False can work: parser.add_argument('--use_aux', default='False', type=str2bool)

> one of the variables needs for gradient computation has been modified Hello，did you resolve it? Please help me.