search

tamarott / SinGAN

Official pytorch implementation of the paper: "SinGAN: Learning a Generative Model from a Single Natural Image"
https://tamarott.github.io/SinGAN.htm
Other
3.31k stars 611 forks source link

About “trained model already exist” and solution way #6

Open Huaxingweichen opened 5 years ago

Huaxingweichen commented 5 years ago

Congratulations on your paper get the best paper in iccv2019！ When I run your code, I input the path to my image and then tell me can't find the file. Later I realized I should input the file name and put the image to /Input/Images/. However, I get the “trained model already exist” . I read the source code and find the path already be created then I deleted the path. Finally, I can run it normally.

JonathanFly commented 5 years ago

That works, though what should really happen is that training is resumed if the model already exists. Not sure how difficult continuing from an existing checkpoint would be to add...

15732031137 commented 4 years ago

Dear tamarott, First of all, congratulations on your paper getting the best ICCV 2019 paper. Recently I had the honor to read that your paper had some problems during runtime, so to ask you, I first run python main_train.py --input_name huge.jpg without problems, but he from The photo produced at 0 scale is distorted, so I want to generate it from a finer scale, and then run the second command python random_samples.py --input_name huge.jpg-mode random_samples --gen_start_scale 2 But the result shows that the model already exists, Later, I changed another file name but it was still an image. In the end, the model still exists. May I ask why? Thank you very much! wish you a happy life!

I-am-anonymous-coder commented 4 years ago

The same problem is happening with me I am running the code with !python SinGAN/main_train.py --input_name rs.jpg --not_cuda but always with any Image present in Input/Images directory , I am always getting "trained model already exist". Even I tried with new images of my own by keeping it in "Input/Images directory" but still getiing that trained model already exist

JonathanFly commented 4 years ago

It shouldn't happen if you've never trained the model? If you see a /TrainedModels directory just rename it for now (or whatever directory it is storing the models in if you changed that, poke around until you find it.)

I-am-anonymous-coder commented 4 years ago

Thankyou very much for helping me out. But It was my mistake , I forgot to mention that I have already run that code in my system with new images and it got successful worked . I understood the reason behind it , why it was showing " already trained model exist " . Anyways thank you again

On Fri, 27 Dec, 2019, 6:08 AM Jonathan, notifications@github.com wrote:

It shouldn't happen if you've never trained the model? If you see a /TrainedModels directory just rename it for now (or whatever directory it is storing the models in if you changed that, poke around until you find it.)

— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/tamarott/SinGAN/issues/6?email_source=notifications&email_token=AM2UI26DHGLYFHIMQIVWIFLQ2VFBNA5CNFSM4JHJY7C2YY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEHWKHFA#issuecomment-569156500, or unsubscribe https://github.com/notifications/unsubscribe-auth/AM2UI26BN5347BDY6EU5MHLQ2VFBNANCNFSM4JHJY7CQ .