PSPNet-tensorflow issues

How to get inference mask image , in which RGB values are correlating to cityscapes original label ids?

I have added seg_map= sess.run(raw_output_up) in inference.py line112 and get mask images. However it's not related to cityscapes original label ids. Could you tell me how can i get inference...

LbinB

Prediction always zero

21

I am training the model with 480x360 images and 3 classes ( gray-scale labels with values 0,1,2). During the training the loss decreases and everything seems to work but during...

psuff

Whether Extended Coarse DATASET

train_fine set only contains 2975 images while coarse set contains more 20000 images. Which one did you train? Thank you for your reply.

Nedcome

I met the error as follow when I train the model. "OutOfRangeError (see above for traceback): FIFOQueue '_1_create_inputs/batch/fifo_queue' is closed and has insufficient elements (requested 1, current size 0)"

Strand2013

How to predict all images in a directory without loading model every time?

1

TongJiayan

The auxiliary loss

1

Apart from the main branch using softmax loss to train the final classifier, another classifier is applied after the fourth stage, i.e., the res4b22 residue block. Do anyone know how...

Ariel-JUAN

Can you share your training procedure

1

Hi，Thanks for your sharing your proj. can you share your training procedure?

shipengai

PACC instead of mIoU

1

Hi Hellochick, i would like to get PACC evaluation instead of mIoU metrics do you know how i can implement it in the code? (i am using cityscapes) original: mIoU,...

KodamaXYZ