| #| export | |
| import torch | |
| import torch.nn as nn | |
| from torchdiffeq import odeint_adjoint as odeint | |
| import pylab as plt | |
| from torch.utils.data import Dataset, DataLoader | |
| from typing import Callable, List, Tuple, Union, Optional |
This is a companion piece to my instructions on building TensorFlow from source. In particular, the aim is to install the following pieces of software
on an Ubuntu Linux system, in particular Ubuntu 20.04.
| # Hadamard Product for Low-Rank Bilinear Pooling, Kim et al., https://arxiv.org/abs/1610.04325 | |
| # Original implementation in LuaTorch: https://github.com/jnhwkim/MulLowBiVQA | |
| import torch | |
| class LowRankBilinearPooling(torch.nn.Module): | |
| def __init__(self, in_channels1, in_channels2, hidden_dim, out_channels, nonlinearity = torch.nn.Identity, sum_pool = True): | |
| super().__init__() | |
| self.nonlinearity = nonlinearity | |
| self.sum_pool = sum_pool |
Only non-stiff ODE solvers are tested since torchdiffeq does not have methods for stiff ODEs. The ODEs are chosen to be representative of models seen in physics and model-informed drug development (MIDD) studies (quantiative systems pharmacology) in order to capture the performance on realistic scenarios.
Below are the timings relative to the fastest method (lower is better). For approximately 1 million ODEs and less, torchdiffeq was more than an order of magnitude slower than DifferentialEquations.jl
| # ported from https://github.com/pvigier/perlin-numpy/blob/master/perlin2d.py | |
| import torch | |
| import math | |
| def rand_perlin_2d(shape, res, fade = lambda t: 6*t**5 - 15*t**4 + 10*t**3): | |
| delta = (res[0] / shape[0], res[1] / shape[1]) | |
| d = (shape[0] // res[0], shape[1] // res[1]) | |
| grid = torch.stack(torch.meshgrid(torch.arange(0, res[0], delta[0]), torch.arange(0, res[1], delta[1])), dim = -1) % 1 |
| import torch | |
| import torch.nn as nn | |
| from torch.autograd import Variable | |
| from torch.nn import functional as F | |
| """ | |
| Blog post: | |
| Taming LSTMs: Variable-sized mini-batches and why PyTorch is good for your health: | |
| https://medium.com/@_willfalcon/taming-lstms-variable-sized-mini-batches-and-why-pytorch-is-good-for-your-health-61d35642972e | |
| """ |
| #!/bin/bash | |
| # | |
| # script to extract ImageNet dataset | |
| # ILSVRC2012_img_train.tar (about 138 GB) | |
| # ILSVRC2012_img_val.tar (about 6.3 GB) | |
| # make sure ILSVRC2012_img_train.tar & ILSVRC2012_img_val.tar in your current directory | |
| # | |
| # https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md | |
| # | |
| # train/ |
In this article, I will share some of my experience on installing NVIDIA driver and CUDA on Linux OS. Here I mainly use Ubuntu as example. Comments for CentOS/Fedora are also provided as much as I can.
