question~

[CXSunshine]

Hello，
when I run the code，I have some touble in understanding the errors that the program generated.
Traceback (most recent call last):
File "main.py", line 33, in
main()
File "main.py", line 28, in main
model.train()
File "F:\pythonprogram\semi-supervised-GAN-master\train.py", line 132, in train
plot.flush()
File "F:\pythonprogram\semi-supervised-GAN-master\vlib\plot.py", line 37, in flush
prints.append("{}\t{}".format(name, np.mean(vals.values())))
File "C:\Users\admin\Anaconda3\lib\site-packages\numpy\core\fromnumeric.py", line 2957, in mean
out=out, **kwargs)
File "C:\Users\admin\Anaconda3\lib\site-packages\numpy\core_methods.py", line 82, in _mean
ret = ret / rcount
TypeError: unsupported operand type(s) for /: 'dict_values' and 'int'

Can you help me solve this problem？

[CXSunshine]

I just get the test accuracy 0.5333，not the 0.99？

[LDOUBLEV]

@CXSunshine hi, I fine-tune the code by loading trained weights for MNIST generation. the final weights in model_saved file have higher test accuracy, you can test it. on the other side , the d loss function is something wrong. i made some change. i will test it when i have free time. and it is glad to get your advice to help me improve the code.

[CXSunshine]

ok，i will have a try.
Progress together！hahah~

[wudongya1226]

@CXSunshine @LDOUBLEV
I also have the same mistakes as you.
TypeError: unsupported operand type(s) for /: 'dict_values' and 'int'
Could you please tell me how do you solve it?