hwalsuklee / tensorflow-fast-style-transfer

A simple, concise tensorflow implementation of fast style transfer
Apache License 2.0
245 stars 70 forks source link

model training poorly with default #16

Closed scharnk closed 5 years ago

scharnk commented 5 years ago

Hi, I'm having trouble recreating the same quality models, for example the first one here is using your pre_trained rain_princess.ckpt file under normal default parameters specified in this repo, while the second image is using a model I trained using default parameters (~6-8hrs). Wondering why there is so much content loss compared to yours. I've changed many parameters from default and each model gets further away from looking as nice as yours. Any suggestions?/has anyone else encountered this before?

Thanks in advance for the help! Best, Kelsey

from your model rain_princess.ckpt: test_rainprincess

from default parameters: content_weight=7.5e0, style_weight=5e2, content_layer_weights=[1.0], style_layer_weights=[.2,.2,.2,.2,.2], num_epochs=2, batch_size=4 TESTrain_default

from parameters: content_weight=5e2, style_weight=5e2, content_layer_weights=[0.1], style_layer_weights=[.2,.2,.2,.2,.2], num_epochs=2, batch_size=4 TESTrain2

from parameters: content_weight=5e2, style_weight=5e2, content_layer_weights=[0.4], style_layer_weights=[.2,.2,.2,.2,.2], num_epochs=2, batch_size=8 TEST3_rainprincess_still

from parameters: content_weight=7.5e0, style_weight=5e2, content_layer_weights=[1.0], style_layer_weights=[.8,.8,.8,.8,.8], num_epochs=2, batch_size=8 TEST4_rainprincess_still

from parameters: content_weight=7.5e0, style_weight=5e4, content_layer_weights=[1.0], style_layer_weights=[.8,.8,.8,.8,.8], num_epochs=2, batch_size=8 TEST5_rainprincess_still

jszym commented 5 years ago

Have you found a solution to this @scharnk ? I've had similar results.

dakshvar22 commented 4 years ago

Hi @scharnk and @jszym have you guys been able to reproduce the quality of the pre-trained models? Something seems terribly off.