tamaraalshekhli

I'm not sure but according to the error you've got its relating to the directory of your dataset: Epoch 1/1 Found 0 images belonging to 1 classes. Found 0 images...

@manvirvirk try this pice of code as addition to original one , hope will help : import cv2 import numpy as np def saveResult(save_path,npyfile,flag_multi_class = False,num_class = 2): for i,item...

just right after this part def labelVisualize(num_class,color_dict,img): img = img[:,:,0] if len(img.shape) == 3 else img img_out = np.zeros(img.shape + (3,)) for i in range(num_class): img_out[img == i,:] = color_dict[i]...

Hi, I have the same warning massages, and my prediction is not correct also , instead of extracting road the model gave me a lot of rectangles spread in random...

@edcaron thank you for your comment, Ive tried your suggestion it didn't work for me

@Jacobew Hi, I have the same problem did you figure out how to solve it ?

@mikael10j , thank you for your reply, I found difficulties to make this implementation works with my pipeline, did you managed to make it works for you? sorry for my...

@mikael10j thank you for your reply, im using keras and TF as abackend, please correct me if im wrong, according to the cod i need to define two models one...

@mikael10j thank you very much for your help, have you tried to train you MT model with different loss ? when i used for example binary cross entropy ( binary...

@ntelo007 hi, did you figure out how to implement the loss in keras? im facing the same problem