Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
torch.nn.utils.clip_grad_norm_(model.parameters(), args.clip)
optimizer.step()
torch.nn.utils.clips_grad_norm_ (which is in-place)
instead …Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
Install a desktop environment, say, lxqt.
Do NOT install a desktop manager (lightdm, kdm, xdm, etc.).
Download NoMachine and install it.
Transformations in torchvision.transforms work on images, tensors (representing images)
and possibly on numpy arrays (representing images).
However,
a transformation (e.g., ToTensor) might work differently on different input types.
So you'd be clear about what exactly a transformation function does.
A good practice is to always convert your non-tensor input data to tensors using the transformation ToTensor
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
https://www.mathworks.com/company/newsletters/articles/what-is-int8-quantization-and-why-is-it-popular-for-deep-neural-networks.html
https://engineering.fb.com/ai-research/floating-point-math/
Rethinking floating point for deep learning
Training Deep Neural Networks with 8-bit Floating Point Numbers