Closed aidonchuk closed 5 years ago
I didn't, but ENet and ERFNet in our paper are very very similar. They are all typical encoder-decoders of residual blocks with max-poolings and upconvolutions. Anyway, I'll soon upload example model definitions I used in the experiments.
Set max_input_h
and max_input_w
to maximum height/width of that module's input tensors.
What is box gen? What exactly do you run?
320х320 WxH, box gen method is def reset_parameters(self) box_convolution_module.py
Right, it's currently not very fast, I will speed it up. Still, I don't expect that you will run reset_parameters()
very often. Maybe just once before training.
It's work ok on small HxW with one layer. Pls try add it on UNET-like architecture. Thx for repo it's nice!
Here's an example of application: ENet. As far as I know, it's UNet-like, except skip connections.
Thx a lot. I'll try it.
subj How to set max height, max width? Single-process box gen takes too long.