examples VS aws-graviton-getting-started

For “cloud-native” apps, JuiceFS is not needed.

S3 is not designed for intensive metadata operations, like listing, renaming etc. For these operations, you will need a somewhat POSIX-complaint system. For example, if you want to train on ImageNet dataset, the “canonical” way [1] is to extract the images and organize them into folders, class by class. The whole dataset is discovered by directory listing. This where JuiceFS shines.

Of course, if the dataset is really massive, you will mostly end-up with in-house solutions.

[1]: https://github.com/pytorch/examples/blob/main/imagenet/extra...

Pytorch includes a simple neural network example for the MNIST data: https://github.com/pytorch/examples/blob/main/mnist/main.py

It only takes a few minutes to train with default parameters and will have >99% accuracy on the MNIST test set.

pytorch-examples

Pretty much just grab one of these, swap in your own database, go home early: https://pytorch.org/examples/

[5] https://github.com/pytorch/examples/tree/main/word_language_...

The cherry on top of the cake I've added my father's name at the top of the code in the comments. I hope that for the next upcoming 200-300 years, someone will read modify and improve or perform experiments with my code.(Vivek V patel), My code can be found at official PyTorch's Website https://pytorch.org/examples/(Image Classification Using Forward-Forward Algorithm)

I am straying out of my domain knowledge to attempt a basic reinforcement learning task in a toy environment and have become fairly familiar with the REINFORCE algorithm for policy gradient agents, especially PyTorch’s implementation (found here). It is clear to me now that there are superior methods to train RL agents (PPO for instance), but as I read, these feel beyond my current intellectual or time resources. As such, I’d like to eek out as much power through modifications of REINFORCE as possible before determining how I might move on.

import torch import torch.nn as nn import torch.nn.functional as F # Simplified version of https://github.com/pytorch/examples/blob/main/mnist/main.py#L21 class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 32, 3, 1) def forward(self, x): x = self.conv1(x) output = F.relu(x) return output

EMR serverless + Athena + Glue works for us. We are evaluating Graviton instance to further optimize stuff. AWS link if you are interested

Now we turn our attention to carbon emissions which are presented in Table 8. In the table, the AMD – CPU only and AMD – T408 server watts/hour are actual measurements on the test system during operation. To estimate the AWS server watts/hour, we reduced the CPU-only AMD number by 60%, which is the savings that Amazon claims that Graviton3 CPUs provide over other CPUs. In all three cases, we multiplied this by the number of servers, then hours, days, and years, to compute the three-year power consumption total.

https://aws.amazon.com/ec2/graviton/ https://cloud.google.com/compute/docs/instances/arm-on-compute

From the relevant product page [0]:

"AWS Graviton3 processors feature always-on memory encryption, dedicated caches for every vCPU, and support for pointer authentication."

Further reading on pointer authentication [1].

[0] https://aws.amazon.com/ec2/graviton/

[1] https://www.qualcomm.com/content/dam/qcomm-martech/dm-assets...

Amazon makes their own Arm CPUs, like the Graviton3: https://aws.amazon.com/ec2/graviton/

Read More about Graviton Processors

According to BlackBerry, both QNX and IVY can run on EC2 instances powered by AWS’ Graviton2 processor. Graviton2 is an internally-developed processor that AWS debuted at re:Invent last year. It promises to provide up to 40% better price performance than comparable chips. "