thanks for the reply, but that does not work with my current server configuration. I think it has to do with the pytorch version which was recently released and I didnt want to make mass changes to the configuration before the last lecture.
Don’t fret, I plan on rebuilding the server over the winter break and going through the all the notebooks, lectures and such again.
I will start a new thread in the forums should anything arise.
Thanks
is cross connection same as skip connection ?
Why do you concat before calling conv2(conv1(x)), not after?
yes as per paper we deconv(merged with skip features) followed by convs
When the concatenation occurs in a densenet or Unet, where does the concatenated information get added? Is it an additional layer, or is it attached to the side, increasing the width of the image, as it looks like in the picture?
For what kind of problems is unet NOT a good idea?
Why were the batchnorm layers params being set to trainable?
Pardon me if it’s already answered:)
In particular I’d be interested to know if anyone know how good is unet for object detection
what is Pixelshuffle_ICNR in U-Net?
what purpose does crapification serve ??
Create damaged data for the purpose of learning how to fix them
We want to create a model that transforms low-resolution, possibly obstructed images into high-res versions. We need to create our own training set for this (since there isn’t an existing well-known one for this task)
Could we use this for de-interlacing video? temporally different half frames?
would we have to merge both halves of the interlaced pair as one image for the “bad” input?
I searched this thread before asking this.
I couldn’t understand what skip connection or identity connection does while upsampling. Does it “only add pixel channel” taken from the similar layer grid size (on downsampling layer)?
what is bigGAN?
Are there any compression algorithms using deep learning? It seems like it can well outperform JPEG
in fit one cycle we use p
ct start=0.8
does it means in every cycle it would start with 0.8 of peak of LR in cycle
Why we always train model first by just freezing layers and then unfreeze it and train it gain. Why we are not just unfreezing and training it directly?