Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement! TVM is an open deep learning compiler stack for CPUs, GPUs, and specialized accelerators. It aims to close the gap between the productivity-focused deep learning frameworks, and the performance- or efficiency-oriented …

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

https://lambdalabs.com/

https://www.floydhub.com/

https://colab.research.google.com/notebooks/intro.ipynb#recent=true

Amazon AWS

Below is a list of instances that have 1 GPU on Amazon …

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

Training a Model Implemented in PyTorch

https://github.com/ray-project/ray/tree/master/python/ray/util/sgd/pytorch/examples

Distributed PyTorch Using Apache Ray

RaySGD: Distributed Training Wrappers

Hyperparameter Optimization for …

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

https://github.com/awslabs/autogluon

https://autogluon.mxnet.io/

AutoGluon automatically inferences the problem type. However, you are still able to specify the probelm type if AutoGluon fails to infer the …

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

1. The best way to deal with different sized images is to downscale them to match dimensions from the smallest image available.

References

CNN - Image Resizing VS Padding (keeping aspect ratio or …

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

CS231n: Convolutional Neural Networks for Visual Recognition is a great introduction of CNN.

ConvNet Architectures

References

http://vision.stanford.edu/teaching/cs231n/