cat-state

to use

HF_API_TOKEN=<token> sbatch hf-infer.sbatch

then run

HF_API_TOKEN=<token> HOSTNAME=<hostname of infernce server> python gradio-tgl.py

setup env following hf inference server instructions but chance /usr/local to path to conda env instead.

optical-nn

This repository for organising information as pertaining to the DIY construction of a non-linear optical neural network.

Module

          +------------SINGLE LAYER+--------------------------+
          |                                                   |
          |     +-----+ +--------------+ +-----+ +-------+    |
 +-----&gt; | W1 | | NON | | W2 | | μLENS | |

	import os
	import sys
	with open(sys.argv[0]) as f:
	code = f.read() # read the code of this file ASAP, for logging
	import uuid
	import time
	import copy
	from dataclasses import dataclass
	from functools import lru_cache
	from pathlib import Path


	import torch
	E = 5e6 # Young's modulus
	nu = 0.4 # Poisson's ratio
	mu = E / (2 * (1 + nu)) # Shear modulus
	lambda_ = (E * nu) / ((1 + nu) * (1 - 2 * nu)) # Lame's first parameter
	rest_x = torch.randn(N, 3).cuda()
	rest_x = rest_x / rest_x.norm(dim=-1, keepdim=True)
	rest_x = (rest_x - rest_x.mean(dim=0))

	import torch
	import matplotlib.pyplot as plt
	from mpl_toolkits.mplot3d import Axes3D
	import numpy as np

	def quantize_coords(coords: torch.Tensor, bits: int = 21):
	max_int = (1 << bits) - 1
	coords = coords.clamp(0, 1)
	return (coords * max_int).long()

	#!/bin/bash

	#SBATCH --job-name=nemo-trlx
	#SBATCH --partition=a100-cu117
	#SBATCH --nodes=4
	#SBATCH --gres=gpu:8
	#SBATCH --ntasks-per-node=8
	#SBATCH --output="%x.out"
	#SBATCH --signal=B:INT@60