Open PhanThanhTrung opened 2 years ago
I don't know if this is a bug, but I can't save the model when training model mapping. I found that you didn't implement save function in
Pix2PixHDModel_Mapping
. I see that some people also have the same trouble in #193. I hope that this pull request would help.
@PhanThanhTrung
hello,when I run train_domain_B.py,it occurs this error:
Traceback (most recent call last): File "train_domain_B.py", line 48, in model = create_model(opt) File "D:\pythonProject\6_18\BringOldBack\Global\models\models.py", line 17, in create_model model.initialize(opt) File "D:\pythonProject\6_18\BringOldBack\Global\models\pix2pixHD_model.py", line 40, in initialize opt.n_blocks_local, opt.norm, gpu_ids=self.gpu_ids, opt=opt) File "D:\pythonProject\6_18\BringOldBack\Global\models\networks.py", line 60, in define_G netG = GlobalGenerator_v2(input_nc, output_nc, ngf, k_size, n_downsample_global, n_blocks_global, norm_layer, opt=opt) NameError: name 'GlobalGenerator_v2' is not defined
how did you solve it? looking forward to your reply soon. thank you.
@CodeMadUser when you call python3 train_domain_B.py
you should add the flag --use_v2
. If you use this flag, your code will init GlobalGenerator_DCDCv2
instead of GlobalGenerator_v2
. You can't init GlobalGenerator_v2
instance because the author doesn't define that object.
@CodeMadUser when you call
python3 train_domain_B.py
you should add the flag--use_v2
. If you use this flag, your code will initGlobalGenerator_DCDCv2
instead ofGlobalGenerator_v2
. You can't initGlobalGenerator_v2
instance because the author doesn't define that object.
ok,I get it.thank you.
@CodeMadUser when you call
python3 train_domain_B.py
you should add the flag--use_v2
. If you use this flag, your code will initGlobalGenerator_DCDCv2
instead ofGlobalGenerator_v2
. You can't initGlobalGenerator_v2
instance because the author doesn't define that object.
excuse me, I don't find document about train VAE_B_scratch, how to solve it ? looking forward to your reply soon. thank you.
I don't know if this is a bug, but I can't save the model when training model mapping. I found that you didn't implement save function in
Pix2PixHDModel_Mapping
. I see that some people also have the same trouble in #193. I hope that this pull request would help.