Need advice

[Edakksm]

Hi,

• We trained our model for 200 epochs.
• Ran predict as follows python runtime.py --inference --split 2
• Images got generated in 'results' folder
• But all the images generated were little off - please see below:

Can you please tell us what could have gone wrong?

[sriharsha-sammeta]

Yup, I also got the same exact result for trying it out on the test data using the above command. And the image looks like that only. I hope that author helps us with some direction to resolve this.

I am guessing that may be the command we used to run the test inference is long. Can the author please suggest the right command.

[sriharsha-sammeta]

Sorry. Found our mistake. We forgot to pass the pre_trained models path. Otherwise it would initialize weights randomly and use it to generate images, which makes sense.

The command should be:

python runtime.py --inference --split 2 --pre_trained_disc checkpoints/disc_190.pth --pre_trained_gen checkpoints/gen_190.pth

After this, I got really good images:

a cluster of flowers with white petals and no visible pistils

a flower large multiple layered slender petals of bright yellow with a short stamen.?

a flower with bright, tall, orange pointed petals and dark forest green pedicel.?

Looks cool. Thanks author. Awesome work :) Now, we will try to implement the same on birds and COCO dataset as well as try using WGAN.

Similarly on birds data set, it would be

python runtime.py --inference --pre_trained_disc checkpoints/birds/disc_190.pth --pre_trained_gen checkpoints/birds/gen_190.pth --save_path birds --dataset birds --split 2

[aelnouby]

@sriharsha-sammeta Thanks for answering.