| %Make sure to have \usepackage{tikz} | |
| %https://tex.stackexchange.com/a/45815/140440 - for grid | |
| %https://tex.stackexchange.com/a/381175/140440 - for alignment in equation | |
| % This function draws a matrix. | |
| \newcommand{\mat}[2]{% cols, rows | |
| \vcenter{\hbox{ %Vertical alignment | |
| \begin{tikzpicture}[scale=0.3, align=center] |
| %Make sure to have \usepackage{tikz} | |
| %https://tex.stackexchange.com/a/45815/140440 - for grid | |
| %https://tex.stackexchange.com/a/381175/140440 - for alignment in equation | |
| % This function draws a matrix. | |
| \newcommand{\mat}[2]{% cols, rows | |
| \vcenter{\hbox{ %Vertical alignment | |
| \begin{tikzpicture}[scale=0.3, align=center] |
| #!/usr/bin/bash | |
| # Download split TSV files here https://ai.google.com/research/ConceptualCaptions/download | |
| # create split folodrs val/ and trn/ | |
| # run as follows | |
| # cd val/; bash ../download_gcc.sh ../val.tsv | |
| # cd trn/; bash ../download_gcc.sh ../trn.tsv | |
| """ | |
| TreeLSTM[1] implementation in Pytorch | |
| Based on dynet benchmarks : | |
| https://github.com/neulab/dynet-benchmark/blob/master/dynet-py/treenn.py | |
| https://github.com/neulab/dynet-benchmark/blob/master/chainer/treenn.py | |
| Other References: | |
| https://github.com/pytorch/examples/tree/master/word_language_model | |
| https://github.com/pfnet/chainer/blob/29c67fe1f2140fa8637201505b4c5e8556fad809/chainer/functions/activation/slstm.py | |
| https://github.com/stanfordnlp/treelstm |
| # Make sure that caffe is on the python path: | |
| caffe_root = '/usr0/bin/caffe/' # this file is expected to be in {caffe_root}/examples | |
| import sys | |
| sys.path.insert(0, caffe_root + 'python') | |
| import caffe | |
| from images import crop_image | |
| import numpy as np | |
| mean = 'caffedata/ilsvrc_2012_mean.npy' |
| ''' | |
| Extract Features from a pre-trained caffe CNN Layer | |
| based on https://github.com/karpathy/neuraltalk/blob/master/python_features/extract_features.py | |
| ''' | |
| import sys | |
| import os.path | |
| import argparse | |
| import numpy as np | |
| from scipy.misc import imread, imresize |
Bu tutorialin amaci eParse deneylerinin tekrarlamak ya da yeni deneyler yapabilmek icin bir referans olusturmak.
Parser’in repository’si burada. Burada oldukca aciklayici bir README mevcut. Bu dokumana devam etmeden mutlaka okunmasini oneririm.
Kelime vektorleri @ai-ku servers:/ai/home/vcirik/embeddings** altinda. Orada bir README
