FCN-pytorch
FCN-pytorch copied to clipboard
yunlongdong
Another pytorch implementation of FCN (Fully Convolutional Networks)
can you tell me please why this model gave me a very bad output segmented image? it trained successfully but when I am using the model to segment a new...
You have used BCE loss in your train file but I don't see you using sigmoid activation. Will that not affect anything as we use sigmoid activation when using BCE...
你好，在FCN.py中有一行代码不是很理解，请指教 ` for layer in range(begin, end): x = self.features[layer](x) # print(x.shape) output["x%d"%(idx+1)] = x `x=self.features[layer](x)表示什么意思
"imgA = cv2.imread('last/'+img_name)" my doubt is that the input data's format is BGR but VGG is compatible to RGB
请教一下 我认为您这样做会出现一个像素点label为【1，1】或【0，0】的情况啊 还有您的代码似乎做的是对通道的分类 不是对像素点的分类 比如对224*224*3的图片，label应该是224*224*n_classes 吧 但是您的是224*224*3*n_classes
Metadata
Owner
Metadata
Another pytorch implementation of FCN (Fully Convolutional Networks)