torch2coreml icon indicating copy to clipboard operation
torch2coreml copied to clipboard

Issue with CycleGAN models

Open devajith opened this issue 7 years ago • 1 comments

i'm trying to convert one of the CycleGAN pre trained model with 'convert-fast-neural-style.py'. i got the output model but when i used it in my app, not getting the expected output. I guess the issue with arguments provided inside the 'convert-fast-neural-style.py'. is there any way i can inspect a pre trained model to find the correct arguments for the conversion.

Model Used : https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/models/apple2orange_cpu.t7

devajith avatar Dec 20 '17 07:12 devajith

@devajith I got the same issue about converting the CycleGAN model. And now do you solve the problem of that? If so, could you send the converted CycleGAN .mlmodel to me? My email is [email protected] . Thank you very much.

hankobe avatar May 16 '18 02:05 hankobe