lr1234567

> @lr1234567 base size normally refers to the original dimension of the images of your dataset. However, it is important to know that, this repo along with other repo using...

Thank you for your reply. My picture is 256*256,crop_size is 480, base_size is 520, if the size of my picture is smaller than the default base_size and crop_size, the default...

你好，我也遇到了这个问题，请问您是怎么解决的？下面是报错日志 Traceback (most recent call last): File "train.py", line 340, in trainer = Trainer(args) File "train.py", line 167, in __init__ aux=args.aux, norm_layer=BatchNorm2d).to(self.device) File "/home/lr/桌面/awesome-semantic-segmentation-pytorch-master.2/core/models/model_zoo.py", line 137, in get_segmentation_model return models[model](**kwargs)...

> @lr1234567 `xception` backbone is not available. So try a different model such as PSPNet. 好的 感谢告知

> This basically means your cuda path was wrong. try setting cuda path manually before installing. Try `export PATH=/usr/local/cuda-9.0/bin:$PATH` before installing the requirements 你好，我运行了一下 export PATH=/usr/local/cuda-9.0/bin:$PATH 再运行仍然是那个问题，是不是我的cuda版本问题呀，cuda是10.0

def hist_info(pred, label, num_cls): assert pred.shape == label.shape k = (label >= 0) & (label < num_cls) labeled = np.sum(k) correct = np.sum((pred[k] == label[k])) return np.bincount(num_cls * label[k].astype(int) +...

I want to use bisenet model on my own dataset,but I don't know how to modify the part of loading dataset,how do i write ?

cityscapes.py ,how should i modify the file?

my dataset is a binary grayscale image

I want to change my binary dataset to try bisenet,don't know how to change cityscapes.py,would like to consult