D&A loss & acc fixed and dead,why?

[taichu012]

I just run this python program of DCGAN with keras, it seems work and after 20 mins, all outputs and numbers are fixed and NEVER changed again, it seems dead, but WHY? output is copied below:

48: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
49: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
50: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
51: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
52: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
53: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
54: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
55: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
56: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
57: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
58: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
59: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
60: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
61: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
62: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
63: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
64: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
65: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
66: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]
67: [D loss: 7.971192, acc: 0.500000] [A loss: 0.000000, acc: 1.000000]

[roatienza]

I adjusted the learning rate of RMSProp. Pls try again. The output near the end of 10k iteration should appear something like this:

9985: [D loss: 0.697829, acc: 0.535156] [A loss: 0.771172, acc: 0.343750]
9986: [D loss: 0.699841, acc: 0.513672] [A loss: 0.792130, acc: 0.296875]
9987: [D loss: 0.711574, acc: 0.507812] [A loss: 0.842314, acc: 0.199219]
9988: [D loss: 0.697459, acc: 0.521484] [A loss: 0.801781, acc: 0.253906]
9989: [D loss: 0.691388, acc: 0.521484] [A loss: 0.810089, acc: 0.269531]
9990: [D loss: 0.713812, acc: 0.490234] [A loss: 0.838145, acc: 0.210938]
9991: [D loss: 0.703769, acc: 0.478516] [A loss: 0.783158, acc: 0.335938]
9992: [D loss: 0.694213, acc: 0.531250] [A loss: 0.812030, acc: 0.246094]
9993: [D loss: 0.707447, acc: 0.503906] [A loss: 0.876013, acc: 0.156250]
9994: [D loss: 0.689719, acc: 0.556641] [A loss: 0.780946, acc: 0.281250]
9995: [D loss: 0.707479, acc: 0.521484] [A loss: 0.905610, acc: 0.101562]
9996: [D loss: 0.692887, acc: 0.529297] [A loss: 0.709554, acc: 0.511719]
9997: [D loss: 0.702180, acc: 0.523438] [A loss: 0.932314, acc: 0.101562]
9998: [D loss: 0.698255, acc: 0.519531] [A loss: 0.685984, acc: 0.542969]
9999: [D loss: 0.711334, acc: 0.515625] [A loss: 0.925216, acc: 0.085938]

[speedyray]

How long does it take to run 10K iterations on a 2.7 GHZ intel Core i5 processor Mac book?

I was at 150 iterations after so many hours? Is there a problem with code, system or I need a GPU?

[nihitpatel]

Mine system is having 16 gb of RAM and core i7 processor. For 50 iterations it took nearly 25 to 30 minutes. So for 10k iterations it could take even days. And yeah it is highly dependent on the kind of hardware you have. I would tell you to rent a cloud computer for doing the job.

…

On Feb 28, 2018 5:20 PM, "Raynold Gyasi" ***@***.***> wrote: How long does it take to run 10K iterations on a 2.7 GHZ intel Core i5 processor Mac book? I was at 150 iterations after so many hours? Is there a problem with code, system or I need a GPU? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#2 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ATkmsi_9pgScqHINDDL-nYo45Z3FUE-Vks5tZT2LgaJpZM4NsjHv> .