Closed kaushikb258 closed 4 years ago
Actually got training to work with the following fix in ASPP (replaced AdaptiveAvgPool with AvgPool):
self.img_pooling = nn.AvgPool2d(1) # nn.AdaptiveAvgPool2d(1)
But not sure why training is not working with AdaptiveAvgPool2d
your batchsize is not even
I tried training on cityscapes from scratch using 'python train.py' and get this error:
raise ValueError('Expected more than 1 value per channel when training, got input size {}'.format(size)) ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 256, 1, 1])
It is something in the _AtrousSpatialPyramidPoolingModule class in network/gscnn.py
img_features = self.img_conv(img_features)