Torch 미세먼지 팁 모음

-

What is Torch?

Torch is a scientific computing framework based on Lua[JIT] with strong CPU and CUDA backends.
Strong points of Torch:
  • Efficient Tensor library (like NumPy) with an efficient CUDA backend
  • Neural Networks package -- build arbitrary acyclic computation graphs with automatic differentiation
    • also with fast CUDA and CPU backends
  • Good community and industry support - several hundred community-built and maintained packages.
  • Easy to use Multi-GPU support and parallelizing neural networks

댓글

  1. 제갈식2016년 8월 8일 PM 7:23

    *.t7 데이타 파일 만들기

    the simplest thing you can do is to store the images in a table and save the table.
    images = {}
    for i=1,10 do
    images[i] = image.load(...)
    end
    torch.save('myimages.t7',images)

    That requires having all the images in memory, which might be prohibitive. Also, there is no compression in standard torch files, so it could become quite a big file. You can eventually compress the images in memory using compressJPEG before saving.

    Another option is to save the images to a different format, like hdf5 https://github.com/deepmind/torch-hdf5 , which allows you to save image per image in the same file and with compression, or LMDB https://github.com/eladhoffer/lmdb.torch .

    답글삭제

댓글 쓰기

이 블로그의 인기 게시물

파이썬으로 Homomorphic Filtering 하기

-
이미지
import cv2 # For OpenCV modules (For Image I/O and Contour Finding) import numpy as np # For general purpose array manipulation import scipy . fftpack # For FFT2 #### imclearborder definition def imclearborder ( imgBW , radius ): # Given a black and white image, first find all of its contours imgBWcopy = imgBW . copy () contours , hierarchy = cv2 . findContours ( imgBWcopy . copy (), cv2 . RETR_LIST , cv2 . CHAIN_APPROX_SIMPLE ) # Get dimensions of image imgRows = imgBW . shape [ 0 ] imgCols = imgBW . shape [ 1 ] contourList = [] # ID list of contours that touch the border # For each contour... for idx in np . arange ( len ( contours )): # Get the i'th contour cnt = contours [ idx ] # Look at each point in the contour for pt in cnt : rowCnt = pt [ 0 ][ 1 ] colCnt = pt [ 0 ][ 0 ] # If this is within the radius of th...
자세한 내용 보기

파이썬으로 2D FFT/iFFT 하기: numpy 버전

-
이미지
import cv2 import numpy as np from matplotlib import pyplot as plt img = cv2 . imread ( 'messi5.jpg' , 0 ) f = np . fft . fft2 ( img ) fshift = np . fft . fftshift ( f ) magnitude_spectrum = 20 * np . log ( np . abs ( fshift )) plt . subplot ( 121 ), plt . imshow ( img , cmap = 'gray' ) plt . title ( 'Input Image' ), plt . xticks ([]), plt . yticks ([]) plt . subplot ( 122 ), plt . imshow ( magnitude_spectrum , cmap = 'gray' ) plt . title ( 'Magnitude Spectrum' ), plt . xticks ([]), plt . yticks ([]) plt . show () rows , cols = img . shape crow , ccol = rows / 2 , cols / 2 fshift [ crow - 30 : crow + 30 , ccol - 30 : ccol + 30 ] = 0 f_ishift = np . fft . ifftshift ( fshift ) img_back = np . fft . ifft2 ( f_ishift ) img_back = np . abs ( img_back ) plt . subplot ( 131 ), plt . imshow ( img , cmap = 'gray' ) plt . title ( 'Input Image' ), plt . xticks ([]), ...
자세한 내용 보기