renmmmmmm

vs2017 +Try to remove code #include in ca_cuda.cu and psa_cuda.

Traceback (most recent call last): File "train_new.py", line 352, in trainer.train() File "train_new.py", line 231, in train outputs = self.model(images) File "/home/renshasha/anaconda3/envs/aaa/lib/python3.6/site-packages/torch/nn/modules/module.py", line 493, in __call__ result = self.forward(*input, **kwargs)...

Found 1449 images in the folder /home/all/datasets/VOC/VOCdevkit/VOC2012 Traceback (most recent call last): File "eval.py", line 116, in evaluator = Evaluator(args) File "eval.py", line 51, in __init__ norm_layer=BatchNorm2d).to(self.device)#args.local_rank, File "/home//awesome-semantic-segmentation-pytorch-master/core/models/model_zoo.py", line...

I have dowload the files from https://github.com/Lavender105/DFF/tree/master/data/cityscapes-preprocess/code for both cityscapes abd SDB dataset. then i can generate the edge ground truth. just follow the steps described on the https://github.com/Lavender105/DFF but...