JaveyWang/Pyramid-Attention-Networks-pytorch
Implementation of Pyramid Attention Networks for Semantic Segmentation.
PythonGPL-3.0
Issues
- 0
Positioning of RELU in FPA
#13 opened by JohnMBrandt - 0
FPA tensor size unmatch
#10 opened by sparkfax - 18
Did the classification module help?
#6 opened by chenyzh28 - 0
上采样这儿是不是核大小应该为3?
#12 opened by ReckonerInheritor - 3
The file cls_labels.npy saves the class label of each image, format like {'filename' : '1, 0, 1, ..., 0'}. For simplicity, you can use the label from the x_mask, I think the program may seems like
#5 opened by chezhizhong - 1
FPA模块中的Global Pooling那个分支最后是否有upsample
#9 opened by wjy66 - 20
The file cls_labels.npy saves the class label of each image, format like {'filename' : '1, 0, 1, ..., 0'}. For simplicity, you can use the label from the x_mask, I think the program may seems like
#4 opened by tong1101 - 0
predict mask only 1/4 of original image
#11 opened by sparkfax - 0
Is this implementation correct ?
#8 opened by shuuchen - 0
The lack of Color_Classifier and loading of checkpoints while doing the eval
#7 opened by Kevinduan23 - 1
- 7
- 4
Softmax/Sigmoid for normalize attention?
#2 opened by John1231983