OSV_ q The size of tensor a (704) must match the size of tensor b (320) at non-singleton dime

====>> Wed Mar 16 12:16:26 2022   Pass time: 0:02:06.581927
==>>   save samples 13!

barbara
Load Data: barbara
====>>   Build Net

====>>   Load I model

====>>   Train
torch.Size([1, 3, 544, 704]) torch.Size([1, 3, 544, 704])
Traceback (most recent call last):
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 410, in <module>
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 301, in train
    lc_time = time.asctime(time.localtime(time.time()))
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 97, in loss_func
    u11 = (f1 - dive1 + b2).to(torch.float32)
RuntimeError: The size of tensor a (704) must match the size of tensor b (320) at non-singleton dimension 3

Process finished with exit code 1

The image dimension should be wrong , Find the problem ： The originally defined code fixes the image dimension

q1 = torch.zeros([1, 3, 320, 320])

So it changes to the dimension of the input image , success

 q1 = torch.zeros(f.shape)
 q1 = q1.to(device)
 b1 = b2 = q2 = q1

It's already running , Enter the parameter adjustment process

do not know why , When I increase batch_size=5 after （ Turned out to be 1）, Just report a mistake

====>>   Train
Traceback (most recent call last):
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 395, in <module>
    train(opt)
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 295, in train
    print(outstr + '    Loss = %f' % loss.data.cpu().numpy())
UnboundLocalError: local variable 'loss' referenced before assignment

Process finished with exit code 1

http://t.csdn.cn/VwT8M

Analyze local variables and global variables , Add this line outside the loop

 loss = None

But there was an error

====>>   Train
Traceback (most recent call last):
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 395, in <module>
    train(opt)
  File "C:/Users/shang/Desktop/STDN_LI/TVGnet/OSV_q.py", line 295, in train
    print(outstr + '    Loss = %f' % loss.data.cpu().numpy())
AttributeError: 'NoneType' object has no attribute 'data'

Process finished with exit code 1

http://t.csdn.cn/EwpTS

Not good either. , Don't change it yet batch_size Well , Try adjusting other parameters first