[sidarape]

I tried that (https://www.tensorflow.org/versions/r0.9/how_tos/image_retra...) which seems to work well.

[dharma1]

yep, that's good if you want to retrain a pre-trained model for specific categories on new image data (that are pretty close to imagenet type images)

[sidarape]

What do you mean by "pretty close"? What would be "not close"?

[dharma1]

Something that looks very different to the ImageNet dataset. Microscope, ultrasound, satellite, x-ray etc images

[sidarape]

Ok, I see. Thank you.