alexgkendall / SegNet-Tutorial

Files for a tutorial to train SegNet for road scenes using the CamVid dataset
http://mi.eng.cam.ac.uk/projects/segnet/tutorial.html
847 stars 517 forks source link

test_segmentation_camvid.py #42

Open Timo-hab opened 8 years ago

Timo-hab commented 8 years ago

Hi,

it comes to that line: scipy.misc.toimage(rgb, cmin=0.0, cmax=255).save(IMAGE_FILE+'_segnet.png')

I get the error: IMAGE_FILE is not defined.

How can I get the names of the image files? Thank you in advance!

pammirato commented 7 years ago

anyone know this?

Almo1982 commented 7 years ago

Hi,

i didnt get this to work too. I just implemented my own nomenclature for the required Images, then you replace the "IMAGE_FILE" with your needed nomenclature string.

solved it for me.

Regards Stefan

Grarya commented 7 years ago

Hi,

IMAGE_FILE is suppose to be replace by the path where you want to save the images. For example:

IMAGE_FILE = "path/to/predictions/'

Then just run the script and it will work.

Regards, Grarya

HaoWumarz commented 6 years ago

Hi @Grarya I have replaced the IMAGE_FILE by their path, but how should I define the name of the predicted results

Grarya commented 6 years ago

Hi @HaoWumarz,

I have used the following command: scipy.misc.toimage(rgb, cmin=0.0, cmax=1).save(IMAGE_FILE+ str(i)+'_segnet.png') where: IMAGE_FILE is the path i: is from the for

The rest is up to you. Regards, Grarya

HaoWumarz commented 6 years ago

Hello @Grarya

Thank you! It solved for me.

Regard, Hao

ArunJ1 commented 5 years ago

Hi @HaoWumarz,

I have used the following command: scipy.misc.toimage(rgb, cmin=0.0, cmax=1).save(IMAGE_FILE+ str(i)+'_segnet.png') where: IMAGE_FILE is the path i: is from the for

The rest is up to you. Regards, Grarya

Thanks...It really helps