seafriday

shortcut error in csresnext50-panet-spp-original-optimal.cfg

4

in the cfg file, the first shortcut layer cut is from -4, which is convolutional layer with filters=64, while the convolutional layer before this [shortcut] is filters=128, they cannot be...

inference speed is much slower than as stated

2

Hi, thank you for the work ! I have test on my own segmentation task, with image input size 1536*1536, the inference speed on my 1080ti is about 300ms per...

what is the top-1 acc for weights/hardnet_petite_base.pth on imagenet

2

what is the top-1 acc for weights/hardnet_petite_base.pth on imagenet

Is Cityscapes "mIOU" metric correspond to "Mean IoU" or "Overall Acc" in metrics.py

1

Is Cityscapes "mIOU" metric correspond to "Mean IoU" or "Overall Acc" in metrics.py and what is about the loss value when the model converge?

In such case, how do you compute the Centripetal Shift ?

can the decode part be implemented inside the tensorrt model?

1

it would be nice if the decode part is treated as part of the tensorrt model rather than postprocess outside, i tried to embed it, for that i use torch.nonzero()...