skrymets

cssclass
cornell-note

Cues

Notes

The Cornell Note-taking System is a popular and effective method for organizing and summarizing information during lectures, readings, or any other form of learning.

adefossez

vadimkantorov

# 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

Nikronic

There are several approaches

• Mount Google Drive in local Colab VM
• Upload and download via browser
• Use colab_util.py in python script

diaoenmao

def extract_patches_2d(img,patch_shape,step=[1.0,1.0],batch_first=False):
    patch_H, patch_W = patch_shape[0], patch_shape[1]
    if(img.size(2)<patch_H):
        num_padded_H_Top = (patch_H - img.size(2))//2
        num_padded_H_Bottom = patch_H - img.size(2) - num_padded_H_Top
        padding_H = nn.ConstantPad2d((0,0,num_padded_H_Top,num_padded_H_Bottom),0)
        img = padding_H(img)
    if(img.size(3)<patch_W):
        num_padded_W_Left = (patch_W - img.size(3))//2
        num_padded_W_Right = patch_W - img.size(3) - num_padded_W_Left

yt114

There are several approaches

• Mount Google Drive in local Colab VM
• Upload and download via browser
• Use colab_util.py in python script

peteflorence

Here's a simple implementation of bilinear interpolation on tensors using PyTorch.

I wrote this up since I ended up learning a lot about options for interpolation in both the numpy and PyTorch ecosystems. More generally than just interpolation, too, it's also a nice case study in how PyTorch magically can put very numpy-like code on the GPU (and by the way, do autodiff for you too).

For interpolation in PyTorch, this open issue calls for more interpolation features. There is now a nn.functional.grid_sample() feature but at least at first this didn't look like what I needed (but we'll come back to this later).

In particular I wanted to take an image, W x H x C, and sample it many times at different random locations. Note also that this is different than upsampling which exhaustively samples and also doesn't give us fle

kevinzakka

"""
Create train, valid, test iterators for CIFAR-10 [1].
Easily extended to MNIST, CIFAR-100 and Imagenet.

[1]: https://discuss.pytorch.org/t/feedback-on-pytorch-for-kaggle-competitions/2252/4
"""

import torch
import numpy as np

RodolfoFerro

# 2 Dimension Fourier Transform:
def FT_2D(X):
  m, n = X.shape
  return np.array([ [ sum([ sum([ X[i,j]*np.exp(-1j*2*np.pi*(k_m*i/m + k_n*j/n)) for i in range(m) ]) for j in range(n) ]) for k_n in range(n) ] for k_m in range(m) ])

brannondorsey

Image-to-Image Translation with Conditional Adversarial Networks

Notes from arXiv:1611.07004v1 [cs.CV] 21 Nov 2016

• Euclidean distance between predicted and ground truth pixels is not a good method of judging similarity because it yields blurry images.
• GANs learn a loss function rather than using an existing one.
• GANs learn a loss that tries to classify if the output image is real or fake, while simultaneously training a generative model to minimize this loss.
• Conditional GANs (cGANs) learn a mapping from observed image x and random noise vector z to y: y = f(x, z)
• The generator G is trained to produce outputs that cannot be distinguished from "real" images by an adversarially trained discrimintor, D which is trained to do as well as possible at detecting the generator's "fakes".
• The discriminator D, learns to classify between real and synthesized pairs. The generator learns to fool the discriminator.
• Unlike an unconditional GAN, both th