lizhao

关于使用cpu的问题

2

作者您好，我看你的介绍时说可以使用cpu训练，但速度很慢，现在我受条件限制只能用cpu，在运行demo时报了这个错： ~\Nest-pytorch\install\trainer.py in network_trainer(data_loaders, model, criterion, optimizer, parameter, meters, hooks, max_epoch, test_interval, resume, log_path, device, use_data_parallel, use_cudnn_benchmark, random_seed) 74 device = torch.device(device) 75 if device.type == 'cuda': ---> 76 assert...

i do not find any Bilinear 2d pooling methods in keras ,can you provide it?

How can you get the kernel?

2

Nice job for solve the time problem of ZSSR! I notice you have a kernel in input, for SR problem, kernel is important, but you do not provide any code...

about py2.7 topy3.5

3

Sorry to bother you,but I notice that you use python2.7,now I want to transform it to python3.5,.But in py3.5,filter produce a generator format, not like py2.7(list format),I do not know...

about abs and fastMRI data

2

I check your code, you use abs between Data Consistency,but is there any information loss between abs? I mean MRI data always use complex value data to get phase information,...

about merge

4

I notice that you use merge to concat 4 layer,like this: res = merge([c1_1, c2_3, c3_3, c4_2], mode='concat', concat_axis=1) but as I know ,merge can only concat 2 layers,and the...

in data.py,after 'img = np.array([img])', image size from 580*420change to 96*96,what happened with np.array?

data processing problem

1

I use python3.5.2,numpy is 1.14.3,here is traceback: Traceback (most recent call last): File "C:/Users/lz666/PycharmProjects/ultrasound-nerve-segmentation/data.py", line 93, in create_train_data() File "C:/Users/lz666/PycharmProjects/ultrasound-nerve-segmentation/data.py", line 37, in create_train_data imgs[i] = img ValueError: setting an...

please give me a url link,thank you!

Sorry to bother you, I want training your model for singlecoil_knee challenge, which trainer file should I use?